diff --git "a/train.log" "b/train.log"
--- "a/train.log"
+++ "b/train.log"
@@ -36762,3 +36762,4236 @@ Eval results for step (40000 / 100000 | Eval Loss: 1.0607950687408447 | Eval wer
 
 60%|██████    | 3/5 [02:25<01:11, 35.91s/it]
 
 80%|████████  | 4/5 [02:25<00:21, 21.96s/it]
 
100%|██████████| 5/5 [02:26<00:00, 14.25s/it]
100%|██████████| 5/5 [02:26<00:00, 29.29s/it]
+
+
+
Evaluating eval...:   0%|          | 0/1900 [00:00<?, ?it/s]
+
+
Evaluating eval...:   0%|          | 1/1900 [00:03<1:46:36,  3.37s/it]
+
+
Evaluating eval...:   0%|          | 2/1900 [00:04<1:07:08,  2.12s/it]
+
+
Evaluating eval...:   0%|          | 3/1900 [00:05<54:47,  1.73s/it]  
+
+
Evaluating eval...:   0%|          | 4/1900 [00:07<48:25,  1.53s/it]
+
+
Evaluating eval...:   0%|          | 5/1900 [00:08<44:58,  1.42s/it]
+
+
Evaluating eval...:   0%|          | 6/1900 [00:09<42:08,  1.33s/it]
+
+
Evaluating eval...:   0%|          | 7/1900 [00:10<40:35,  1.29s/it]
+
+
Evaluating eval...:   0%|          | 8/1900 [00:11<39:29,  1.25s/it]
+
+
Evaluating eval...:   0%|          | 9/1900 [00:13<38:32,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 10/1900 [00:14<38:20,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 11/1900 [00:15<38:29,  1.22s/it]
+
+
Evaluating eval...:   1%|          | 12/1900 [00:16<38:04,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 13/1900 [00:17<37:58,  1.21s/it]
+
+
Evaluating eval...:   1%|          | 14/1900 [00:19<37:31,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 15/1900 [00:20<37:17,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 16/1900 [00:21<37:09,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 17/1900 [00:22<37:11,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 18/1900 [00:23<36:55,  1.18s/it]
+
+
Evaluating eval...:   1%|          | 19/1900 [00:24<36:33,  1.17s/it]
+
+
Evaluating eval...:   1%|          | 20/1900 [00:26<36:47,  1.17s/it]
+
+
Evaluating eval...:   1%|          | 21/1900 [00:27<37:14,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 22/1900 [00:28<37:07,  1.19s/it]
+
+
Evaluating eval...:   1%|          | 23/1900 [00:29<36:47,  1.18s/it]
+
+
Evaluating eval...:   1%|▏         | 24/1900 [00:30<37:04,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 25/1900 [00:31<36:36,  1.17s/it]
+
+
Evaluating eval...:   1%|▏         | 26/1900 [00:33<36:16,  1.16s/it]
+
+
Evaluating eval...:   1%|▏         | 27/1900 [00:34<37:05,  1.19s/it]
+
+
Evaluating eval...:   1%|▏         | 28/1900 [00:35<36:49,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 29/1900 [00:36<36:42,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 30/1900 [00:37<36:46,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 31/1900 [00:39<36:45,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 32/1900 [00:40<37:14,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 33/1900 [00:41<37:18,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 34/1900 [00:42<37:53,  1.22s/it]
+
+
Evaluating eval...:   2%|▏         | 35/1900 [00:44<38:25,  1.24s/it]
+
+
Evaluating eval...:   2%|▏         | 36/1900 [00:45<38:20,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 37/1900 [00:46<38:03,  1.23s/it]
+
+
Evaluating eval...:   2%|▏         | 38/1900 [00:47<37:30,  1.21s/it]
+
+
Evaluating eval...:   2%|▏         | 39/1900 [00:48<37:07,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 40/1900 [00:49<36:53,  1.19s/it]
+
+
Evaluating eval...:   2%|▏         | 41/1900 [00:51<36:33,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 42/1900 [00:52<37:10,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 43/1900 [00:53<37:01,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 44/1900 [00:54<37:08,  1.20s/it]
+
+
Evaluating eval...:   2%|▏         | 45/1900 [00:55<36:35,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 46/1900 [00:57<36:20,  1.18s/it]
+
+
Evaluating eval...:   2%|▏         | 47/1900 [00:58<35:56,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 48/1900 [00:59<35:44,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 49/1900 [01:00<35:43,  1.16s/it]
+
+
Evaluating eval...:   3%|▎         | 50/1900 [01:01<36:20,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 51/1900 [01:02<36:28,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 52/1900 [01:04<36:14,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 53/1900 [01:05<35:59,  1.17s/it]
+
+
Evaluating eval...:   3%|▎         | 54/1900 [01:06<36:17,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 55/1900 [01:07<36:56,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 56/1900 [01:08<37:00,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 57/1900 [01:10<36:53,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 58/1900 [01:11<37:01,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 59/1900 [01:12<36:46,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 60/1900 [01:13<36:17,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 61/1900 [01:14<37:34,  1.23s/it]
+
+
Evaluating eval...:   3%|▎         | 62/1900 [01:16<37:02,  1.21s/it]
+
+
Evaluating eval...:   3%|▎         | 63/1900 [01:17<36:44,  1.20s/it]
+
+
Evaluating eval...:   3%|▎         | 64/1900 [01:18<36:31,  1.19s/it]
+
+
Evaluating eval...:   3%|▎         | 65/1900 [01:19<36:02,  1.18s/it]
+
+
Evaluating eval...:   3%|▎         | 66/1900 [01:20<35:48,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 67/1900 [01:21<35:43,  1.17s/it]
+
+
Evaluating eval...:   4%|▎         | 68/1900 [01:23<37:30,  1.23s/it]
+
+
Evaluating eval...:   4%|▎         | 69/1900 [01:24<36:41,  1.20s/it]
+
+
Evaluating eval...:   4%|▎         | 70/1900 [01:25<37:03,  1.21s/it]
+
+
Evaluating eval...:   4%|▎         | 71/1900 [01:26<36:51,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 72/1900 [01:28<36:59,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 73/1900 [01:29<36:46,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 74/1900 [01:30<36:35,  1.20s/it]
+
+
Evaluating eval...:   4%|▍         | 75/1900 [01:31<36:19,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 76/1900 [01:32<36:15,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 77/1900 [01:34<36:12,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 78/1900 [01:35<36:10,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 79/1900 [01:36<36:11,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 80/1900 [01:37<36:02,  1.19s/it]
+
+
Evaluating eval...:   4%|▍         | 81/1900 [01:38<35:42,  1.18s/it]
+
+
Evaluating eval...:   4%|▍         | 82/1900 [01:40<36:34,  1.21s/it]
+
+
Evaluating eval...:   4%|▍         | 83/1900 [01:41<37:09,  1.23s/it]
+
+
Evaluating eval...:   4%|▍         | 84/1900 [01:42<36:50,  1.22s/it]
+
+
Evaluating eval...:   4%|▍         | 85/1900 [01:43<36:30,  1.21s/it]
+
+
Evaluating eval...:   5%|▍         | 86/1900 [01:44<35:54,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 87/1900 [01:46<36:10,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 88/1900 [01:47<35:57,  1.19s/it]
+
+
Evaluating eval...:   5%|▍         | 89/1900 [01:48<37:54,  1.26s/it]
+
+
Evaluating eval...:   5%|▍         | 90/1900 [01:49<37:15,  1.24s/it]
+
+
Evaluating eval...:   5%|▍         | 91/1900 [01:51<37:14,  1.23s/it]
+
+
Evaluating eval...:   5%|▍         | 92/1900 [01:52<36:33,  1.21s/it]
+
+
Evaluating eval...:   5%|▍         | 93/1900 [01:53<36:13,  1.20s/it]
+
+
Evaluating eval...:   5%|▍         | 94/1900 [01:54<35:35,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 95/1900 [01:55<35:09,  1.17s/it]
+
+
Evaluating eval...:   5%|▌         | 96/1900 [01:56<36:07,  1.20s/it]
+
+
Evaluating eval...:   5%|▌         | 97/1900 [01:58<35:31,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 98/1900 [01:59<35:49,  1.19s/it]
+
+
Evaluating eval...:   5%|▌         | 99/1900 [02:00<35:28,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 100/1900 [02:01<35:23,  1.18s/it]
+
+
Evaluating eval...:   5%|▌         | 101/1900 [02:02<36:17,  1.21s/it]
+
+
Evaluating eval...:   5%|▌         | 102/1900 [02:04<36:47,  1.23s/it]
+
+
Evaluating eval...:   5%|▌         | 103/1900 [02:05<36:28,  1.22s/it]
+
+
Evaluating eval...:   5%|▌         | 104/1900 [02:06<36:04,  1.21s/it]
+
+
Evaluating eval...:   6%|▌         | 105/1900 [02:07<35:49,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 106/1900 [02:08<35:14,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 107/1900 [02:10<35:39,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 108/1900 [02:11<35:13,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 109/1900 [02:12<35:36,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 110/1900 [02:13<35:15,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 111/1900 [02:14<35:31,  1.19s/it]
+
+
Evaluating eval...:   6%|▌         | 112/1900 [02:16<36:14,  1.22s/it]
+
+
Evaluating eval...:   6%|▌         | 113/1900 [02:17<35:47,  1.20s/it]
+
+
Evaluating eval...:   6%|▌         | 114/1900 [02:18<35:15,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 115/1900 [02:19<35:04,  1.18s/it]
+
+
Evaluating eval...:   6%|▌         | 116/1900 [02:20<34:43,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 117/1900 [02:21<34:53,  1.17s/it]
+
+
Evaluating eval...:   6%|▌         | 118/1900 [02:23<35:15,  1.19s/it]
+
+
Evaluating eval...:   6%|▋         | 119/1900 [02:24<35:04,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 120/1900 [02:25<35:32,  1.20s/it]
+
+
Evaluating eval...:   6%|▋         | 121/1900 [02:26<35:06,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 122/1900 [02:27<35:02,  1.18s/it]
+
+
Evaluating eval...:   6%|▋         | 123/1900 [02:29<35:00,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 124/1900 [02:30<35:12,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 125/1900 [02:31<35:07,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 126/1900 [02:32<35:22,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 127/1900 [02:33<35:32,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 128/1900 [02:35<35:06,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 129/1900 [02:36<34:48,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 130/1900 [02:37<34:39,  1.17s/it]
+
+
Evaluating eval...:   7%|▋         | 131/1900 [02:38<34:49,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 132/1900 [02:39<35:12,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 133/1900 [02:40<34:40,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 134/1900 [02:42<34:50,  1.18s/it]
+
+
Evaluating eval...:   7%|▋         | 135/1900 [02:43<35:03,  1.19s/it]
+
+
Evaluating eval...:   7%|▋         | 136/1900 [02:44<35:32,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 137/1900 [02:45<36:13,  1.23s/it]
+
+
Evaluating eval...:   7%|▋         | 138/1900 [02:47<36:00,  1.23s/it]
+
+
Evaluating eval...:   7%|▋         | 139/1900 [02:48<35:30,  1.21s/it]
+
+
Evaluating eval...:   7%|▋         | 140/1900 [02:49<35:20,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 141/1900 [02:50<35:14,  1.20s/it]
+
+
Evaluating eval...:   7%|▋         | 142/1900 [02:51<35:58,  1.23s/it]
+
+
Evaluating eval...:   8%|▊         | 143/1900 [02:53<35:46,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 144/1900 [02:54<35:01,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 145/1900 [02:55<35:05,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 146/1900 [02:56<34:43,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 147/1900 [02:57<35:09,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 148/1900 [02:59<34:38,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 149/1900 [03:00<34:43,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 150/1900 [03:01<35:34,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 151/1900 [03:02<35:22,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 152/1900 [03:03<35:13,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 153/1900 [03:05<35:13,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 154/1900 [03:06<35:08,  1.21s/it]
+
+
Evaluating eval...:   8%|▊         | 155/1900 [03:07<35:00,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 156/1900 [03:08<34:54,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 157/1900 [03:10<35:56,  1.24s/it]
+
+
Evaluating eval...:   8%|▊         | 158/1900 [03:11<35:30,  1.22s/it]
+
+
Evaluating eval...:   8%|▊         | 159/1900 [03:12<34:47,  1.20s/it]
+
+
Evaluating eval...:   8%|▊         | 160/1900 [03:13<34:38,  1.19s/it]
+
+
Evaluating eval...:   8%|▊         | 161/1900 [03:14<35:17,  1.22s/it]
+
+
Evaluating eval...:   9%|▊         | 162/1900 [03:15<34:42,  1.20s/it]
+
+
Evaluating eval...:   9%|▊         | 163/1900 [03:17<34:06,  1.18s/it]
+
+
Evaluating eval...:   9%|▊         | 164/1900 [03:18<34:19,  1.19s/it]
+
+
Evaluating eval...:   9%|▊         | 165/1900 [03:19<34:21,  1.19s/it]
+
+
Evaluating eval...:   9%|▊         | 166/1900 [03:20<34:19,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 167/1900 [03:21<35:05,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 168/1900 [03:23<34:27,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 169/1900 [03:24<34:11,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 170/1900 [03:25<34:07,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 171/1900 [03:26<34:00,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 172/1900 [03:27<34:12,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 173/1900 [03:29<34:18,  1.19s/it]
+
+
Evaluating eval...:   9%|▉         | 174/1900 [03:30<34:34,  1.20s/it]
+
+
Evaluating eval...:   9%|▉         | 175/1900 [03:31<34:00,  1.18s/it]
+
+
Evaluating eval...:   9%|▉         | 176/1900 [03:32<33:35,  1.17s/it]
+
+
Evaluating eval...:   9%|▉         | 177/1900 [03:33<35:19,  1.23s/it]
+
+
Evaluating eval...:   9%|▉         | 178/1900 [03:35<35:15,  1.23s/it]
+
+
Evaluating eval...:   9%|▉         | 179/1900 [03:36<34:41,  1.21s/it]
+
+
Evaluating eval...:   9%|▉         | 180/1900 [03:37<34:30,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 181/1900 [03:38<34:08,  1.19s/it]
+
+
Evaluating eval...:  10%|▉         | 182/1900 [03:39<34:58,  1.22s/it]
+
+
Evaluating eval...:  10%|▉         | 183/1900 [03:41<34:53,  1.22s/it]
+
+
Evaluating eval...:  10%|▉         | 184/1900 [03:42<34:25,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 185/1900 [03:43<34:13,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 186/1900 [03:44<33:49,  1.18s/it]
+
+
Evaluating eval...:  10%|▉         | 187/1900 [03:45<34:08,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 188/1900 [03:47<34:11,  1.20s/it]
+
+
Evaluating eval...:  10%|▉         | 189/1900 [03:48<33:48,  1.19s/it]
+
+
Evaluating eval...:  10%|█         | 190/1900 [03:49<33:44,  1.18s/it]
+
+
Evaluating eval...:  10%|█         | 191/1900 [03:50<33:47,  1.19s/it]
+
+
Evaluating eval...:  10%|█         | 192/1900 [03:51<34:39,  1.22s/it]
+
+
Evaluating eval...:  10%|█         | 193/1900 [03:53<35:37,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 194/1900 [03:54<35:14,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 195/1900 [03:55<35:09,  1.24s/it]
+
+
Evaluating eval...:  10%|█         | 196/1900 [03:56<34:48,  1.23s/it]
+
+
Evaluating eval...:  10%|█         | 197/1900 [03:58<35:35,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 198/1900 [03:59<35:34,  1.25s/it]
+
+
Evaluating eval...:  10%|█         | 199/1900 [04:00<34:48,  1.23s/it]
+
+
Evaluating eval...:  11%|█         | 200/1900 [04:01<34:09,  1.21s/it]
+
+
Evaluating eval...:  11%|█         | 201/1900 [04:02<33:39,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 202/1900 [04:04<33:18,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 203/1900 [04:05<33:43,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 204/1900 [04:06<33:35,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 205/1900 [04:07<33:29,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 206/1900 [04:08<33:24,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 207/1900 [04:10<34:02,  1.21s/it]
+
+
Evaluating eval...:  11%|█         | 208/1900 [04:11<33:32,  1.19s/it]
+
+
Evaluating eval...:  11%|█         | 209/1900 [04:12<33:22,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 210/1900 [04:13<33:05,  1.17s/it]
+
+
Evaluating eval...:  11%|█         | 211/1900 [04:14<33:13,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 212/1900 [04:15<33:15,  1.18s/it]
+
+
Evaluating eval...:  11%|█         | 213/1900 [04:17<33:56,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 214/1900 [04:18<34:01,  1.21s/it]
+
+
Evaluating eval...:  11%|█▏        | 215/1900 [04:19<33:50,  1.20s/it]
+
+
Evaluating eval...:  11%|█▏        | 216/1900 [04:20<33:37,  1.20s/it]
+
+
Evaluating eval...:  11%|█▏        | 217/1900 [04:22<33:41,  1.20s/it]
+
+
Evaluating eval...:  11%|█▏        | 218/1900 [04:23<33:59,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 219/1900 [04:24<33:47,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 220/1900 [04:25<34:03,  1.22s/it]
+
+
Evaluating eval...:  12%|█▏        | 221/1900 [04:26<33:49,  1.21s/it]
+
+
Evaluating eval...:  12%|█▏        | 222/1900 [04:28<33:29,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 223/1900 [04:29<32:59,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 224/1900 [04:30<32:37,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 225/1900 [04:31<32:36,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 226/1900 [04:32<32:42,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 227/1900 [04:33<32:37,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 228/1900 [04:35<32:59,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 229/1900 [04:36<32:35,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 230/1900 [04:37<32:46,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 231/1900 [04:38<32:48,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 232/1900 [04:39<32:31,  1.17s/it]
+
+
Evaluating eval...:  12%|█▏        | 233/1900 [04:40<32:50,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 234/1900 [04:42<32:40,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 235/1900 [04:43<32:42,  1.18s/it]
+
+
Evaluating eval...:  12%|█▏        | 236/1900 [04:44<33:09,  1.20s/it]
+
+
Evaluating eval...:  12%|█▏        | 237/1900 [04:45<33:13,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 238/1900 [04:46<33:27,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 239/1900 [04:48<34:07,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 240/1900 [04:49<33:25,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 241/1900 [04:50<33:02,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 242/1900 [04:51<33:02,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 243/1900 [04:52<32:39,  1.18s/it]
+
+
Evaluating eval...:  13%|█▎        | 244/1900 [04:54<32:34,  1.18s/it]
+
+
Evaluating eval...:  13%|█▎        | 245/1900 [04:55<32:59,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 246/1900 [04:56<33:03,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 247/1900 [04:57<33:07,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 248/1900 [04:58<33:08,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 249/1900 [05:00<32:37,  1.19s/it]
+
+
Evaluating eval...:  13%|█▎        | 250/1900 [05:01<32:53,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 251/1900 [05:02<33:34,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 252/1900 [05:03<33:05,  1.20s/it]
+
+
Evaluating eval...:  13%|█▎        | 253/1900 [05:05<33:42,  1.23s/it]
+
+
Evaluating eval...:  13%|█▎        | 254/1900 [05:06<33:19,  1.22s/it]
+
+
Evaluating eval...:  13%|█▎        | 255/1900 [05:07<33:04,  1.21s/it]
+
+
Evaluating eval...:  13%|█▎        | 256/1900 [05:08<32:45,  1.20s/it]
+
+
Evaluating eval...:  14%|█▎        | 257/1900 [05:09<32:18,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 258/1900 [05:10<32:17,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 259/1900 [05:12<32:20,  1.18s/it]
+
+
Evaluating eval...:  14%|█▎        | 260/1900 [05:13<32:27,  1.19s/it]
+
+
Evaluating eval...:  14%|█▎        | 261/1900 [05:14<32:22,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 262/1900 [05:15<32:05,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 263/1900 [05:16<32:11,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 264/1900 [05:18<32:09,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 265/1900 [05:19<32:31,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 266/1900 [05:20<32:17,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 267/1900 [05:21<32:35,  1.20s/it]
+
+
Evaluating eval...:  14%|█▍        | 268/1900 [05:22<32:19,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 269/1900 [05:23<32:17,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 270/1900 [05:25<32:08,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 271/1900 [05:26<31:44,  1.17s/it]
+
+
Evaluating eval...:  14%|█▍        | 272/1900 [05:27<32:08,  1.18s/it]
+
+
Evaluating eval...:  14%|█▍        | 273/1900 [05:28<32:13,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 274/1900 [05:29<32:18,  1.19s/it]
+
+
Evaluating eval...:  14%|█▍        | 275/1900 [05:31<32:17,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 276/1900 [05:32<32:32,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 277/1900 [05:33<32:21,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 278/1900 [05:34<32:07,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 279/1900 [05:35<32:08,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 280/1900 [05:37<32:15,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 281/1900 [05:38<32:23,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 282/1900 [05:39<32:29,  1.20s/it]
+
+
Evaluating eval...:  15%|█▍        | 283/1900 [05:40<32:10,  1.19s/it]
+
+
Evaluating eval...:  15%|█▍        | 284/1900 [05:41<32:10,  1.19s/it]
+
+
Evaluating eval...:  15%|█▌        | 285/1900 [05:43<31:50,  1.18s/it]
+
+
Evaluating eval...:  15%|█▌        | 286/1900 [05:44<32:23,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 287/1900 [05:45<32:11,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 288/1900 [05:46<33:19,  1.24s/it]
+
+
Evaluating eval...:  15%|█▌        | 289/1900 [05:48<32:57,  1.23s/it]
+
+
Evaluating eval...:  15%|█▌        | 290/1900 [05:49<32:30,  1.21s/it]
+
+
Evaluating eval...:  15%|█▌        | 291/1900 [05:50<32:09,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 292/1900 [05:51<32:05,  1.20s/it]
+
+
Evaluating eval...:  15%|█▌        | 293/1900 [05:52<31:46,  1.19s/it]
+
+
Evaluating eval...:  15%|█▌        | 294/1900 [05:53<31:38,  1.18s/it]
+
+
Evaluating eval...:  16%|█▌        | 295/1900 [05:55<31:44,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 296/1900 [05:56<32:05,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 297/1900 [05:57<32:33,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 298/1900 [05:58<32:40,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 299/1900 [05:59<32:09,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 300/1900 [06:01<32:19,  1.21s/it]
+
+
Evaluating eval...:  16%|█▌        | 301/1900 [06:02<32:35,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 302/1900 [06:03<32:29,  1.22s/it]
+
+
Evaluating eval...:  16%|█▌        | 303/1900 [06:04<32:01,  1.20s/it]
+
+
Evaluating eval...:  16%|█▌        | 304/1900 [06:05<31:32,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 305/1900 [06:07<31:41,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 306/1900 [06:08<31:35,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 307/1900 [06:09<31:29,  1.19s/it]
+
+
Evaluating eval...:  16%|█▌        | 308/1900 [06:10<31:25,  1.18s/it]
+
+
Evaluating eval...:  16%|█▋        | 309/1900 [06:11<31:33,  1.19s/it]
+
+
Evaluating eval...:  16%|█▋        | 310/1900 [06:13<31:48,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 311/1900 [06:14<32:02,  1.21s/it]
+
+
Evaluating eval...:  16%|█▋        | 312/1900 [06:15<31:52,  1.20s/it]
+
+
Evaluating eval...:  16%|█▋        | 313/1900 [06:16<31:32,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 314/1900 [06:17<31:33,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 315/1900 [06:19<31:50,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 316/1900 [06:20<31:23,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 317/1900 [06:21<31:40,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 318/1900 [06:22<31:30,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 319/1900 [06:23<31:51,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 320/1900 [06:25<31:35,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 321/1900 [06:26<31:01,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 322/1900 [06:27<31:09,  1.18s/it]
+
+
Evaluating eval...:  17%|█▋        | 323/1900 [06:28<31:12,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 324/1900 [06:29<30:44,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 325/1900 [06:30<30:44,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 326/1900 [06:32<30:45,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 327/1900 [06:33<30:47,  1.17s/it]
+
+
Evaluating eval...:  17%|█▋        | 328/1900 [06:34<31:36,  1.21s/it]
+
+
Evaluating eval...:  17%|█▋        | 329/1900 [06:35<31:05,  1.19s/it]
+
+
Evaluating eval...:  17%|█▋        | 330/1900 [06:36<31:17,  1.20s/it]
+
+
Evaluating eval...:  17%|█▋        | 331/1900 [06:38<32:35,  1.25s/it]
+
+
Evaluating eval...:  17%|█▋        | 332/1900 [06:39<32:21,  1.24s/it]
+
+
Evaluating eval...:  18%|█▊        | 333/1900 [06:40<32:11,  1.23s/it]
+
+
Evaluating eval...:  18%|█▊        | 334/1900 [06:41<31:25,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 335/1900 [06:43<30:46,  1.18s/it]
+
+
Evaluating eval...:  18%|█▊        | 336/1900 [06:44<31:03,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 337/1900 [06:45<30:52,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 338/1900 [06:46<31:24,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 339/1900 [06:47<31:35,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 340/1900 [06:49<31:15,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 341/1900 [06:50<31:31,  1.21s/it]
+
+
Evaluating eval...:  18%|█▊        | 342/1900 [06:51<31:01,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 343/1900 [06:52<30:47,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 344/1900 [06:53<30:56,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 345/1900 [06:55<30:58,  1.20s/it]
+
+
Evaluating eval...:  18%|█▊        | 346/1900 [06:56<30:49,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 347/1900 [06:57<30:46,  1.19s/it]
+
+
Evaluating eval...:  18%|█▊        | 348/1900 [06:58<30:20,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 349/1900 [06:59<30:08,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 350/1900 [07:00<30:14,  1.17s/it]
+
+
Evaluating eval...:  18%|█▊        | 351/1900 [07:02<30:48,  1.19s/it]
+
+
Evaluating eval...:  19%|█▊        | 352/1900 [07:03<30:49,  1.19s/it]
+
+
Evaluating eval...:  19%|█▊        | 353/1900 [07:04<31:02,  1.20s/it]
+
+
Evaluating eval...:  19%|█▊        | 354/1900 [07:05<30:56,  1.20s/it]
+
+
Evaluating eval...:  19%|█▊        | 355/1900 [07:06<31:18,  1.22s/it]
+
+
Evaluating eval...:  19%|█▊        | 356/1900 [07:08<31:29,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 357/1900 [07:09<30:57,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 358/1900 [07:10<31:09,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 359/1900 [07:11<30:46,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 360/1900 [07:12<30:54,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 361/1900 [07:14<30:32,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 362/1900 [07:15<31:20,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 363/1900 [07:16<30:47,  1.20s/it]
+
+
Evaluating eval...:  19%|█▉        | 364/1900 [07:17<30:27,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 365/1900 [07:18<30:21,  1.19s/it]
+
+
Evaluating eval...:  19%|█▉        | 366/1900 [07:20<30:09,  1.18s/it]
+
+
Evaluating eval...:  19%|█▉        | 367/1900 [07:21<30:55,  1.21s/it]
+
+
Evaluating eval...:  19%|█▉        | 368/1900 [07:22<31:31,  1.23s/it]
+
+
Evaluating eval...:  19%|█▉        | 369/1900 [07:23<31:15,  1.22s/it]
+
+
Evaluating eval...:  19%|█▉        | 370/1900 [07:25<30:50,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 371/1900 [07:26<30:41,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 372/1900 [07:27<30:26,  1.20s/it]
+
+
Evaluating eval...:  20%|█▉        | 373/1900 [07:28<30:13,  1.19s/it]
+
+
Evaluating eval...:  20%|█▉        | 374/1900 [07:29<29:54,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 375/1900 [07:30<29:40,  1.17s/it]
+
+
Evaluating eval...:  20%|█▉        | 376/1900 [07:32<30:04,  1.18s/it]
+
+
Evaluating eval...:  20%|█▉        | 377/1900 [07:33<30:41,  1.21s/it]
+
+
Evaluating eval...:  20%|█▉        | 378/1900 [07:34<30:52,  1.22s/it]
+
+
Evaluating eval...:  20%|█▉        | 379/1900 [07:35<30:30,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 380/1900 [07:37<30:39,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 381/1900 [07:38<30:51,  1.22s/it]
+
+
Evaluating eval...:  20%|██        | 382/1900 [07:39<31:14,  1.24s/it]
+
+
Evaluating eval...:  20%|██        | 383/1900 [07:40<30:37,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 384/1900 [07:41<30:17,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 385/1900 [07:43<30:09,  1.19s/it]
+
+
Evaluating eval...:  20%|██        | 386/1900 [07:44<30:29,  1.21s/it]
+
+
Evaluating eval...:  20%|██        | 387/1900 [07:45<30:21,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 388/1900 [07:46<30:13,  1.20s/it]
+
+
Evaluating eval...:  20%|██        | 389/1900 [07:47<30:09,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 390/1900 [07:49<30:00,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 391/1900 [07:50<30:04,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 392/1900 [07:51<29:39,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 393/1900 [07:52<29:25,  1.17s/it]
+
+
Evaluating eval...:  21%|██        | 394/1900 [07:53<29:29,  1.18s/it]
+
+
Evaluating eval...:  21%|██        | 395/1900 [07:54<29:17,  1.17s/it]
+
+
Evaluating eval...:  21%|██        | 396/1900 [07:56<29:59,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 397/1900 [07:57<30:06,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 398/1900 [07:58<29:48,  1.19s/it]
+
+
Evaluating eval...:  21%|██        | 399/1900 [07:59<30:17,  1.21s/it]
+
+
Evaluating eval...:  21%|██        | 400/1900 [08:01<30:40,  1.23s/it]
+
+
Evaluating eval...:  21%|██        | 401/1900 [08:02<30:26,  1.22s/it]
+
+
Evaluating eval...:  21%|██        | 402/1900 [08:03<30:05,  1.20s/it]
+
+
Evaluating eval...:  21%|██        | 403/1900 [08:04<30:09,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 404/1900 [08:05<30:17,  1.22s/it]
+
+
Evaluating eval...:  21%|██▏       | 405/1900 [08:07<30:29,  1.22s/it]
+
+
Evaluating eval...:  21%|██▏       | 406/1900 [08:08<30:05,  1.21s/it]
+
+
Evaluating eval...:  21%|██▏       | 407/1900 [08:09<29:56,  1.20s/it]
+
+
Evaluating eval...:  21%|██▏       | 408/1900 [08:10<30:44,  1.24s/it]
+
+
Evaluating eval...:  22%|██▏       | 409/1900 [08:11<30:33,  1.23s/it]
+
+
Evaluating eval...:  22%|██▏       | 410/1900 [08:13<30:11,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 411/1900 [08:14<30:19,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 412/1900 [08:15<29:49,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 413/1900 [08:16<30:02,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 414/1900 [08:17<29:50,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 415/1900 [08:19<29:16,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 416/1900 [08:20<28:56,  1.17s/it]
+
+
Evaluating eval...:  22%|██▏       | 417/1900 [08:21<29:39,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 418/1900 [08:22<29:23,  1.19s/it]
+
+
Evaluating eval...:  22%|██▏       | 419/1900 [08:23<29:10,  1.18s/it]
+
+
Evaluating eval...:  22%|██▏       | 420/1900 [08:25<29:32,  1.20s/it]
+
+
Evaluating eval...:  22%|██▏       | 421/1900 [08:26<29:43,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 422/1900 [08:27<29:44,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 423/1900 [08:28<30:03,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 424/1900 [08:30<30:01,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 425/1900 [08:31<29:46,  1.21s/it]
+
+
Evaluating eval...:  22%|██▏       | 426/1900 [08:32<29:51,  1.22s/it]
+
+
Evaluating eval...:  22%|██▏       | 427/1900 [08:33<29:51,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 428/1900 [08:34<29:17,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 429/1900 [08:35<29:24,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 430/1900 [08:37<28:53,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 431/1900 [08:38<28:55,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 432/1900 [08:39<29:15,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 433/1900 [08:40<29:17,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 434/1900 [08:42<29:45,  1.22s/it]
+
+
Evaluating eval...:  23%|██▎       | 435/1900 [08:43<29:12,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 436/1900 [08:44<29:13,  1.20s/it]
+
+
Evaluating eval...:  23%|██▎       | 437/1900 [08:45<28:43,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 438/1900 [08:46<28:35,  1.17s/it]
+
+
Evaluating eval...:  23%|██▎       | 439/1900 [08:47<28:55,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 440/1900 [08:49<28:40,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 441/1900 [08:50<28:45,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 442/1900 [08:51<28:27,  1.17s/it]
+
+
Evaluating eval...:  23%|██▎       | 443/1900 [08:52<28:43,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 444/1900 [08:53<28:37,  1.18s/it]
+
+
Evaluating eval...:  23%|██▎       | 445/1900 [08:54<28:47,  1.19s/it]
+
+
Evaluating eval...:  23%|██▎       | 446/1900 [08:56<28:55,  1.19s/it]
+
+
Evaluating eval...:  24%|██▎       | 447/1900 [08:57<28:34,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 448/1900 [08:58<28:26,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 449/1900 [08:59<28:27,  1.18s/it]
+
+
Evaluating eval...:  24%|██▎       | 450/1900 [09:00<28:21,  1.17s/it]
+
+
Evaluating eval...:  24%|██▎       | 451/1900 [09:02<28:36,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 452/1900 [09:03<28:19,  1.17s/it]
+
+
Evaluating eval...:  24%|██▍       | 453/1900 [09:04<28:54,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 454/1900 [09:05<29:04,  1.21s/it]
+
+
Evaluating eval...:  24%|██▍       | 455/1900 [09:06<28:51,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 456/1900 [09:08<28:51,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 457/1900 [09:09<28:51,  1.20s/it]
+
+
Evaluating eval...:  24%|██▍       | 458/1900 [09:10<28:42,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 459/1900 [09:11<28:13,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 460/1900 [09:12<28:01,  1.17s/it]
+
+
Evaluating eval...:  24%|██▍       | 461/1900 [09:13<28:29,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 462/1900 [09:15<28:18,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 463/1900 [09:16<28:10,  1.18s/it]
+
+
Evaluating eval...:  24%|██▍       | 464/1900 [09:17<28:22,  1.19s/it]
+
+
Evaluating eval...:  24%|██▍       | 465/1900 [09:18<28:18,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 466/1900 [09:19<27:58,  1.17s/it]
+
+
Evaluating eval...:  25%|██▍       | 467/1900 [09:20<28:01,  1.17s/it]
+
+
Evaluating eval...:  25%|██▍       | 468/1900 [09:22<28:06,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 469/1900 [09:23<28:08,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 470/1900 [09:24<28:03,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 471/1900 [09:25<28:06,  1.18s/it]
+
+
Evaluating eval...:  25%|██▍       | 472/1900 [09:26<28:41,  1.21s/it]
+
+
Evaluating eval...:  25%|██▍       | 473/1900 [09:28<28:15,  1.19s/it]
+
+
Evaluating eval...:  25%|██▍       | 474/1900 [09:29<28:04,  1.18s/it]
+
+
Evaluating eval...:  25%|██▌       | 475/1900 [09:30<28:01,  1.18s/it]
+
+
Evaluating eval...:  25%|██▌       | 476/1900 [09:31<27:51,  1.17s/it]
+
+
Evaluating eval...:  25%|██▌       | 477/1900 [09:32<28:39,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 478/1900 [09:34<28:34,  1.21s/it]
+
+
Evaluating eval...:  25%|██▌       | 479/1900 [09:35<29:03,  1.23s/it]
+
+
Evaluating eval...:  25%|██▌       | 480/1900 [09:36<28:46,  1.22s/it]
+
+
Evaluating eval...:  25%|██▌       | 481/1900 [09:37<29:28,  1.25s/it]
+
+
Evaluating eval...:  25%|██▌       | 482/1900 [09:39<28:44,  1.22s/it]
+
+
Evaluating eval...:  25%|██▌       | 483/1900 [09:40<28:20,  1.20s/it]
+
+
Evaluating eval...:  25%|██▌       | 484/1900 [09:41<28:51,  1.22s/it]
+
+
Evaluating eval...:  26%|██▌       | 485/1900 [09:42<28:20,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 486/1900 [09:43<27:55,  1.18s/it]
+
+
Evaluating eval...:  26%|██▌       | 487/1900 [09:44<27:47,  1.18s/it]
+
+
Evaluating eval...:  26%|██▌       | 488/1900 [09:46<28:09,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 489/1900 [09:47<28:05,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 490/1900 [09:48<27:52,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 491/1900 [09:49<27:58,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 492/1900 [09:50<27:58,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 493/1900 [09:52<28:08,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 494/1900 [09:53<27:50,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 495/1900 [09:54<27:41,  1.18s/it]
+
+
Evaluating eval...:  26%|██▌       | 496/1900 [09:55<27:52,  1.19s/it]
+
+
Evaluating eval...:  26%|██▌       | 497/1900 [09:56<28:07,  1.20s/it]
+
+
Evaluating eval...:  26%|██▌       | 498/1900 [09:58<28:24,  1.22s/it]
+
+
Evaluating eval...:  26%|██▋       | 499/1900 [09:59<28:10,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 500/1900 [10:00<28:03,  1.20s/it]
+
+
Evaluating eval...:  26%|██▋       | 501/1900 [10:01<28:10,  1.21s/it]
+
+
Evaluating eval...:  26%|██▋       | 502/1900 [10:03<28:28,  1.22s/it]
+
+
Evaluating eval...:  26%|██▋       | 503/1900 [10:04<28:47,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 504/1900 [10:05<29:17,  1.26s/it]
+
+
Evaluating eval...:  27%|██▋       | 505/1900 [10:06<29:10,  1.26s/it]
+
+
Evaluating eval...:  27%|██▋       | 506/1900 [10:08<28:33,  1.23s/it]
+
+
Evaluating eval...:  27%|██▋       | 507/1900 [10:09<28:05,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 508/1900 [10:10<28:14,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 509/1900 [10:11<28:42,  1.24s/it]
+
+
Evaluating eval...:  27%|██▋       | 510/1900 [10:12<28:15,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 511/1900 [10:14<27:51,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 512/1900 [10:15<27:33,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 513/1900 [10:16<27:17,  1.18s/it]
+
+
Evaluating eval...:  27%|██▋       | 514/1900 [10:17<27:06,  1.17s/it]
+
+
Evaluating eval...:  27%|██▋       | 515/1900 [10:18<27:43,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 516/1900 [10:19<27:40,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 517/1900 [10:21<27:22,  1.19s/it]
+
+
Evaluating eval...:  27%|██▋       | 518/1900 [10:22<27:50,  1.21s/it]
+
+
Evaluating eval...:  27%|██▋       | 519/1900 [10:23<28:00,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 520/1900 [10:24<27:36,  1.20s/it]
+
+
Evaluating eval...:  27%|██▋       | 521/1900 [10:26<28:03,  1.22s/it]
+
+
Evaluating eval...:  27%|██▋       | 522/1900 [10:27<28:01,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 523/1900 [10:28<28:30,  1.24s/it]
+
+
Evaluating eval...:  28%|██▊       | 524/1900 [10:29<28:18,  1.23s/it]
+
+
Evaluating eval...:  28%|██▊       | 525/1900 [10:30<27:48,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 526/1900 [10:32<27:40,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 527/1900 [10:33<27:55,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 528/1900 [10:34<27:50,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 529/1900 [10:35<27:57,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 530/1900 [10:37<27:34,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 531/1900 [10:38<27:23,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 532/1900 [10:39<27:52,  1.22s/it]
+
+
Evaluating eval...:  28%|██▊       | 533/1900 [10:40<27:34,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 534/1900 [10:41<27:30,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 535/1900 [10:43<27:21,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 536/1900 [10:44<27:20,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 537/1900 [10:45<27:17,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 538/1900 [10:46<27:11,  1.20s/it]
+
+
Evaluating eval...:  28%|██▊       | 539/1900 [10:47<27:23,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 540/1900 [10:49<27:22,  1.21s/it]
+
+
Evaluating eval...:  28%|██▊       | 541/1900 [10:50<27:02,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 542/1900 [10:51<27:22,  1.21s/it]
+
+
Evaluating eval...:  29%|██▊       | 543/1900 [10:52<27:03,  1.20s/it]
+
+
Evaluating eval...:  29%|██▊       | 544/1900 [10:53<26:59,  1.19s/it]
+
+
Evaluating eval...:  29%|██▊       | 545/1900 [10:55<27:47,  1.23s/it]
+
+
Evaluating eval...:  29%|██▊       | 546/1900 [10:56<27:50,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 547/1900 [10:57<28:07,  1.25s/it]
+
+
Evaluating eval...:  29%|██▉       | 548/1900 [10:58<28:07,  1.25s/it]
+
+
Evaluating eval...:  29%|██▉       | 549/1900 [11:00<27:55,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 550/1900 [11:01<28:03,  1.25s/it]
+
+
Evaluating eval...:  29%|██▉       | 551/1900 [11:02<27:46,  1.24s/it]
+
+
Evaluating eval...:  29%|██▉       | 552/1900 [11:03<28:03,  1.25s/it]
+
+
Evaluating eval...:  29%|██▉       | 553/1900 [11:05<27:36,  1.23s/it]
+
+
Evaluating eval...:  29%|██▉       | 554/1900 [11:06<27:05,  1.21s/it]
+
+
Evaluating eval...:  29%|██▉       | 555/1900 [11:07<26:50,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 556/1900 [11:08<26:49,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 557/1900 [11:09<26:35,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 558/1900 [11:11<26:46,  1.20s/it]
+
+
Evaluating eval...:  29%|██▉       | 559/1900 [11:12<26:29,  1.19s/it]
+
+
Evaluating eval...:  29%|██▉       | 560/1900 [11:13<26:44,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 561/1900 [11:14<26:42,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 562/1900 [11:15<26:44,  1.20s/it]
+
+
Evaluating eval...:  30%|██▉       | 563/1900 [11:17<26:53,  1.21s/it]
+
+
Evaluating eval...:  30%|██▉       | 564/1900 [11:18<27:18,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 565/1900 [11:19<27:02,  1.22s/it]
+
+
Evaluating eval...:  30%|██▉       | 566/1900 [11:20<27:18,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 567/1900 [11:21<27:29,  1.24s/it]
+
+
Evaluating eval...:  30%|██▉       | 568/1900 [11:23<27:22,  1.23s/it]
+
+
Evaluating eval...:  30%|██▉       | 569/1900 [11:24<27:26,  1.24s/it]
+
+
Evaluating eval...:  30%|███       | 570/1900 [11:25<28:37,  1.29s/it]
+
+
Evaluating eval...:  30%|███       | 571/1900 [11:27<27:42,  1.25s/it]
+
+
Evaluating eval...:  30%|███       | 572/1900 [11:28<27:25,  1.24s/it]
+
+
Evaluating eval...:  30%|███       | 573/1900 [11:29<26:58,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 574/1900 [11:30<26:51,  1.22s/it]
+
+
Evaluating eval...:  30%|███       | 575/1900 [11:31<26:36,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 576/1900 [11:33<26:41,  1.21s/it]
+
+
Evaluating eval...:  30%|███       | 577/1900 [11:34<26:33,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 578/1900 [11:35<26:26,  1.20s/it]
+
+
Evaluating eval...:  30%|███       | 579/1900 [11:36<26:20,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 580/1900 [11:37<26:09,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 581/1900 [11:38<26:03,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 582/1900 [11:40<26:45,  1.22s/it]
+
+
Evaluating eval...:  31%|███       | 583/1900 [11:41<26:22,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 584/1900 [11:42<26:06,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 585/1900 [11:43<25:56,  1.18s/it]
+
+
Evaluating eval...:  31%|███       | 586/1900 [11:44<26:18,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 587/1900 [11:46<25:57,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 588/1900 [11:47<25:41,  1.17s/it]
+
+
Evaluating eval...:  31%|███       | 589/1900 [11:48<25:47,  1.18s/it]
+
+
Evaluating eval...:  31%|███       | 590/1900 [11:49<25:58,  1.19s/it]
+
+
Evaluating eval...:  31%|███       | 591/1900 [11:50<25:49,  1.18s/it]
+
+
Evaluating eval...:  31%|███       | 592/1900 [11:52<26:09,  1.20s/it]
+
+
Evaluating eval...:  31%|███       | 593/1900 [11:53<26:12,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 594/1900 [11:54<26:18,  1.21s/it]
+
+
Evaluating eval...:  31%|███▏      | 595/1900 [11:55<26:01,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 596/1900 [11:56<26:09,  1.20s/it]
+
+
Evaluating eval...:  31%|███▏      | 597/1900 [11:58<26:23,  1.21s/it]
+
+
Evaluating eval...:  31%|███▏      | 598/1900 [11:59<26:07,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 599/1900 [12:00<25:57,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 600/1900 [12:01<25:55,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 601/1900 [12:02<25:52,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 602/1900 [12:04<25:29,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 603/1900 [12:05<25:25,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 604/1900 [12:06<25:26,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 605/1900 [12:07<25:33,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 606/1900 [12:08<25:52,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 607/1900 [12:09<25:29,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 608/1900 [12:11<25:53,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 609/1900 [12:12<25:59,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 610/1900 [12:13<25:42,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 611/1900 [12:14<25:25,  1.18s/it]
+
+
Evaluating eval...:  32%|███▏      | 612/1900 [12:16<25:45,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 613/1900 [12:17<25:37,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 614/1900 [12:18<25:58,  1.21s/it]
+
+
Evaluating eval...:  32%|███▏      | 615/1900 [12:19<25:45,  1.20s/it]
+
+
Evaluating eval...:  32%|███▏      | 616/1900 [12:20<25:30,  1.19s/it]
+
+
Evaluating eval...:  32%|███▏      | 617/1900 [12:21<25:16,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 618/1900 [12:23<25:05,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 619/1900 [12:24<25:22,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 620/1900 [12:25<25:13,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 621/1900 [12:26<25:26,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 622/1900 [12:27<25:37,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 623/1900 [12:29<25:38,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 624/1900 [12:30<25:55,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 625/1900 [12:31<26:17,  1.24s/it]
+
+
Evaluating eval...:  33%|███▎      | 626/1900 [12:32<25:49,  1.22s/it]
+
+
Evaluating eval...:  33%|███▎      | 627/1900 [12:33<25:25,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 628/1900 [12:35<25:13,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 629/1900 [12:36<25:28,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 630/1900 [12:37<25:23,  1.20s/it]
+
+
Evaluating eval...:  33%|███▎      | 631/1900 [12:38<25:41,  1.21s/it]
+
+
Evaluating eval...:  33%|███▎      | 632/1900 [12:39<25:14,  1.19s/it]
+
+
Evaluating eval...:  33%|███▎      | 633/1900 [12:41<24:57,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 634/1900 [12:42<24:44,  1.17s/it]
+
+
Evaluating eval...:  33%|███▎      | 635/1900 [12:43<24:49,  1.18s/it]
+
+
Evaluating eval...:  33%|███▎      | 636/1900 [12:44<25:10,  1.20s/it]
+
+
Evaluating eval...:  34%|███▎      | 637/1900 [12:45<25:22,  1.21s/it]
+
+
Evaluating eval...:  34%|███▎      | 638/1900 [12:47<25:29,  1.21s/it]
+
+
Evaluating eval...:  34%|███▎      | 639/1900 [12:48<25:24,  1.21s/it]
+
+
Evaluating eval...:  34%|███▎      | 640/1900 [12:49<25:30,  1.21s/it]
+
+
Evaluating eval...:  34%|███▎      | 641/1900 [12:50<25:26,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 642/1900 [12:52<25:24,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 643/1900 [12:53<25:54,  1.24s/it]
+
+
Evaluating eval...:  34%|███▍      | 644/1900 [12:54<25:41,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 645/1900 [12:55<25:35,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 646/1900 [12:56<25:44,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 647/1900 [12:58<25:33,  1.22s/it]
+
+
Evaluating eval...:  34%|███▍      | 648/1900 [12:59<25:12,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 649/1900 [13:00<25:17,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 650/1900 [13:01<25:33,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 651/1900 [13:03<25:38,  1.23s/it]
+
+
Evaluating eval...:  34%|███▍      | 652/1900 [13:04<25:08,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 653/1900 [13:05<24:46,  1.19s/it]
+
+
Evaluating eval...:  34%|███▍      | 654/1900 [13:06<25:07,  1.21s/it]
+
+
Evaluating eval...:  34%|███▍      | 655/1900 [13:07<25:01,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 656/1900 [13:09<24:52,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 657/1900 [13:10<24:40,  1.19s/it]
+
+
Evaluating eval...:  35%|███▍      | 658/1900 [13:11<25:07,  1.21s/it]
+
+
Evaluating eval...:  35%|███▍      | 659/1900 [13:12<25:11,  1.22s/it]
+
+
Evaluating eval...:  35%|███▍      | 660/1900 [13:13<24:53,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 661/1900 [13:15<24:49,  1.20s/it]
+
+
Evaluating eval...:  35%|███▍      | 662/1900 [13:16<25:09,  1.22s/it]
+
+
Evaluating eval...:  35%|███▍      | 663/1900 [13:17<25:19,  1.23s/it]
+
+
Evaluating eval...:  35%|███▍      | 664/1900 [13:18<25:10,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 665/1900 [13:19<24:54,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 666/1900 [13:21<24:40,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 667/1900 [13:22<25:32,  1.24s/it]
+
+
Evaluating eval...:  35%|███▌      | 668/1900 [13:23<25:09,  1.22s/it]
+
+
Evaluating eval...:  35%|███▌      | 669/1900 [13:24<24:44,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 670/1900 [13:26<24:37,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 671/1900 [13:27<24:46,  1.21s/it]
+
+
Evaluating eval...:  35%|███▌      | 672/1900 [13:28<24:35,  1.20s/it]
+
+
Evaluating eval...:  35%|███▌      | 673/1900 [13:29<24:23,  1.19s/it]
+
+
Evaluating eval...:  35%|███▌      | 674/1900 [13:30<24:29,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 675/1900 [13:32<24:22,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 676/1900 [13:33<24:11,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 677/1900 [13:34<24:17,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 678/1900 [13:35<24:55,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 679/1900 [13:36<24:24,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 680/1900 [13:38<24:25,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 681/1900 [13:39<24:43,  1.22s/it]
+
+
Evaluating eval...:  36%|███▌      | 682/1900 [13:40<24:36,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 683/1900 [13:41<24:23,  1.20s/it]
+
+
Evaluating eval...:  36%|███▌      | 684/1900 [13:42<24:08,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 685/1900 [13:43<23:57,  1.18s/it]
+
+
Evaluating eval...:  36%|███▌      | 686/1900 [13:45<24:30,  1.21s/it]
+
+
Evaluating eval...:  36%|███▌      | 687/1900 [13:46<24:09,  1.19s/it]
+
+
Evaluating eval...:  36%|███▌      | 688/1900 [13:47<23:50,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 689/1900 [13:48<23:45,  1.18s/it]
+
+
Evaluating eval...:  36%|███▋      | 690/1900 [13:49<23:57,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 691/1900 [13:51<23:57,  1.19s/it]
+
+
Evaluating eval...:  36%|███▋      | 692/1900 [13:52<23:37,  1.17s/it]
+
+
Evaluating eval...:  36%|███▋      | 693/1900 [13:53<23:41,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 694/1900 [13:54<23:41,  1.18s/it]
+
+
Evaluating eval...:  37%|███▋      | 695/1900 [13:55<23:57,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 696/1900 [13:57<24:03,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 697/1900 [13:58<23:56,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 698/1900 [13:59<24:13,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 699/1900 [14:00<24:49,  1.24s/it]
+
+
Evaluating eval...:  37%|███▋      | 700/1900 [14:01<24:21,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 701/1900 [14:03<24:11,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 702/1900 [14:04<24:19,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 703/1900 [14:05<23:48,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 704/1900 [14:06<24:41,  1.24s/it]
+
+
Evaluating eval...:  37%|███▋      | 705/1900 [14:08<24:19,  1.22s/it]
+
+
Evaluating eval...:  37%|███▋      | 706/1900 [14:09<24:07,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 707/1900 [14:10<23:41,  1.19s/it]
+
+
Evaluating eval...:  37%|███▋      | 708/1900 [14:11<24:05,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 709/1900 [14:12<23:52,  1.20s/it]
+
+
Evaluating eval...:  37%|███▋      | 710/1900 [14:14<23:55,  1.21s/it]
+
+
Evaluating eval...:  37%|███▋      | 711/1900 [14:15<24:38,  1.24s/it]
+
+
Evaluating eval...:  37%|███▋      | 712/1900 [14:16<24:42,  1.25s/it]
+
+
Evaluating eval...:  38%|███▊      | 713/1900 [14:17<24:59,  1.26s/it]
+
+
Evaluating eval...:  38%|███▊      | 714/1900 [14:19<24:22,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 715/1900 [14:20<23:59,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 716/1900 [14:21<23:44,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 717/1900 [14:22<23:35,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 718/1900 [14:23<23:49,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 719/1900 [14:25<23:46,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 720/1900 [14:26<23:34,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 721/1900 [14:27<23:48,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 722/1900 [14:28<23:41,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 723/1900 [14:29<23:41,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 724/1900 [14:31<23:43,  1.21s/it]
+
+
Evaluating eval...:  38%|███▊      | 725/1900 [14:32<23:20,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 726/1900 [14:33<23:29,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 727/1900 [14:34<23:15,  1.19s/it]
+
+
Evaluating eval...:  38%|███▊      | 728/1900 [14:35<23:49,  1.22s/it]
+
+
Evaluating eval...:  38%|███▊      | 729/1900 [14:37<23:24,  1.20s/it]
+
+
Evaluating eval...:  38%|███▊      | 730/1900 [14:38<23:53,  1.23s/it]
+
+
Evaluating eval...:  38%|███▊      | 731/1900 [14:39<23:50,  1.22s/it]
+
+
Evaluating eval...:  39%|███▊      | 732/1900 [14:40<23:30,  1.21s/it]
+
+
Evaluating eval...:  39%|███▊      | 733/1900 [14:41<23:25,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 734/1900 [14:43<23:17,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 735/1900 [14:44<23:13,  1.20s/it]
+
+
Evaluating eval...:  39%|███▊      | 736/1900 [14:45<23:06,  1.19s/it]
+
+
Evaluating eval...:  39%|███▉      | 737/1900 [14:46<22:56,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 738/1900 [14:47<23:10,  1.20s/it]
+
+
Evaluating eval...:  39%|███▉      | 739/1900 [14:49<22:52,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 740/1900 [14:50<22:50,  1.18s/it]
+
+
Evaluating eval...:  39%|███▉      | 741/1900 [14:51<23:24,  1.21s/it]
+
+
Evaluating eval...:  39%|███▉      | 742/1900 [14:52<23:21,  1.21s/it]
+
+
Evaluating eval...:  39%|███▉      | 743/1900 [14:53<23:31,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 744/1900 [14:55<23:16,  1.21s/it]
+
+
Evaluating eval...:  39%|███▉      | 745/1900 [14:56<23:42,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 746/1900 [14:57<23:33,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 747/1900 [14:58<23:52,  1.24s/it]
+
+
Evaluating eval...:  39%|███▉      | 748/1900 [15:00<23:21,  1.22s/it]
+
+
Evaluating eval...:  39%|███▉      | 749/1900 [15:01<23:31,  1.23s/it]
+
+
Evaluating eval...:  39%|███▉      | 750/1900 [15:02<23:11,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 751/1900 [15:03<23:23,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 752/1900 [15:05<23:32,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 753/1900 [15:06<23:30,  1.23s/it]
+
+
Evaluating eval...:  40%|███▉      | 754/1900 [15:07<23:02,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 755/1900 [15:08<22:40,  1.19s/it]
+
+
Evaluating eval...:  40%|███▉      | 756/1900 [15:09<23:00,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 757/1900 [15:11<22:59,  1.21s/it]
+
+
Evaluating eval...:  40%|███▉      | 758/1900 [15:12<23:11,  1.22s/it]
+
+
Evaluating eval...:  40%|███▉      | 759/1900 [15:13<23:11,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 760/1900 [15:14<23:25,  1.23s/it]
+
+
Evaluating eval...:  40%|████      | 761/1900 [15:15<23:07,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 762/1900 [15:17<22:38,  1.19s/it]
+
+
Evaluating eval...:  40%|████      | 763/1900 [15:18<22:24,  1.18s/it]
+
+
Evaluating eval...:  40%|████      | 764/1900 [15:19<22:23,  1.18s/it]
+
+
Evaluating eval...:  40%|████      | 765/1900 [15:20<22:41,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 766/1900 [15:21<22:41,  1.20s/it]
+
+
Evaluating eval...:  40%|████      | 767/1900 [15:23<23:01,  1.22s/it]
+
+
Evaluating eval...:  40%|████      | 768/1900 [15:24<23:37,  1.25s/it]
+
+
Evaluating eval...:  40%|████      | 769/1900 [15:25<23:31,  1.25s/it]
+
+
Evaluating eval...:  41%|████      | 770/1900 [15:26<22:59,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 771/1900 [15:28<22:55,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 772/1900 [15:29<23:05,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 773/1900 [15:30<22:50,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 774/1900 [15:31<22:31,  1.20s/it]
+
+
Evaluating eval...:  41%|████      | 775/1900 [15:32<22:52,  1.22s/it]
+
+
Evaluating eval...:  41%|████      | 776/1900 [15:34<22:57,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 777/1900 [15:35<22:59,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 778/1900 [15:36<22:38,  1.21s/it]
+
+
Evaluating eval...:  41%|████      | 779/1900 [15:37<22:23,  1.20s/it]
+
+
Evaluating eval...:  41%|████      | 780/1900 [15:39<23:07,  1.24s/it]
+
+
Evaluating eval...:  41%|████      | 781/1900 [15:40<22:52,  1.23s/it]
+
+
Evaluating eval...:  41%|████      | 782/1900 [15:41<23:23,  1.26s/it]
+
+
Evaluating eval...:  41%|████      | 783/1900 [15:42<23:15,  1.25s/it]
+
+
Evaluating eval...:  41%|████▏     | 784/1900 [15:44<22:56,  1.23s/it]
+
+
Evaluating eval...:  41%|████▏     | 785/1900 [15:45<22:41,  1.22s/it]
+
+
Evaluating eval...:  41%|████▏     | 786/1900 [15:46<22:33,  1.22s/it]
+
+
Evaluating eval...:  41%|████▏     | 787/1900 [15:47<22:50,  1.23s/it]
+
+
Evaluating eval...:  41%|████▏     | 788/1900 [15:48<22:42,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 789/1900 [15:50<22:40,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 790/1900 [15:51<22:32,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 791/1900 [15:52<22:37,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 792/1900 [15:53<22:44,  1.23s/it]
+
+
Evaluating eval...:  42%|████▏     | 793/1900 [15:54<22:30,  1.22s/it]
+
+
Evaluating eval...:  42%|████▏     | 794/1900 [15:56<22:15,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 795/1900 [15:57<22:05,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 796/1900 [15:58<21:47,  1.18s/it]
+
+
Evaluating eval...:  42%|████▏     | 797/1900 [15:59<21:43,  1.18s/it]
+
+
Evaluating eval...:  42%|████▏     | 798/1900 [16:00<21:48,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 799/1900 [16:02<21:46,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 800/1900 [16:03<22:07,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 801/1900 [16:04<22:04,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 802/1900 [16:05<21:41,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 803/1900 [16:06<21:49,  1.19s/it]
+
+
Evaluating eval...:  42%|████▏     | 804/1900 [16:08<21:38,  1.18s/it]
+
+
Evaluating eval...:  42%|████▏     | 805/1900 [16:09<22:06,  1.21s/it]
+
+
Evaluating eval...:  42%|████▏     | 806/1900 [16:10<21:48,  1.20s/it]
+
+
Evaluating eval...:  42%|████▏     | 807/1900 [16:11<21:41,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 808/1900 [16:12<22:16,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 809/1900 [16:14<22:29,  1.24s/it]
+
+
Evaluating eval...:  43%|████▎     | 810/1900 [16:15<22:23,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 811/1900 [16:16<22:06,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 812/1900 [16:17<22:16,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 813/1900 [16:19<21:48,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 814/1900 [16:20<21:44,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 815/1900 [16:21<21:37,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 816/1900 [16:22<21:35,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 817/1900 [16:23<21:24,  1.19s/it]
+
+
Evaluating eval...:  43%|████▎     | 818/1900 [16:24<21:35,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 819/1900 [16:26<21:44,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 820/1900 [16:27<21:49,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 821/1900 [16:28<21:35,  1.20s/it]
+
+
Evaluating eval...:  43%|████▎     | 822/1900 [16:29<21:39,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 823/1900 [16:31<21:59,  1.23s/it]
+
+
Evaluating eval...:  43%|████▎     | 824/1900 [16:32<21:55,  1.22s/it]
+
+
Evaluating eval...:  43%|████▎     | 825/1900 [16:33<21:39,  1.21s/it]
+
+
Evaluating eval...:  43%|████▎     | 826/1900 [16:34<22:00,  1.23s/it]
+
+
Evaluating eval...:  44%|████▎     | 827/1900 [16:35<21:51,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 828/1900 [16:37<21:43,  1.22s/it]
+
+
Evaluating eval...:  44%|████▎     | 829/1900 [16:38<21:24,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 830/1900 [16:39<21:28,  1.20s/it]
+
+
Evaluating eval...:  44%|████▎     | 831/1900 [16:40<21:09,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 832/1900 [16:41<21:25,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 833/1900 [16:43<21:48,  1.23s/it]
+
+
Evaluating eval...:  44%|████▍     | 834/1900 [16:44<21:28,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 835/1900 [16:45<21:49,  1.23s/it]
+
+
Evaluating eval...:  44%|████▍     | 836/1900 [16:46<22:04,  1.24s/it]
+
+
Evaluating eval...:  44%|████▍     | 837/1900 [16:48<21:40,  1.22s/it]
+
+
Evaluating eval...:  44%|████▍     | 838/1900 [16:49<21:11,  1.20s/it]
+
+
Evaluating eval...:  44%|████▍     | 839/1900 [16:50<21:01,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 840/1900 [16:51<21:03,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 841/1900 [16:52<21:28,  1.22s/it]
+
+
Evaluating eval...:  44%|████▍     | 842/1900 [16:54<21:29,  1.22s/it]
+
+
Evaluating eval...:  44%|████▍     | 843/1900 [16:55<21:15,  1.21s/it]
+
+
Evaluating eval...:  44%|████▍     | 844/1900 [16:56<20:59,  1.19s/it]
+
+
Evaluating eval...:  44%|████▍     | 845/1900 [16:57<21:00,  1.19s/it]
+
+
Evaluating eval...:  45%|████▍     | 846/1900 [16:58<21:19,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 847/1900 [17:00<21:00,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 848/1900 [17:01<21:05,  1.20s/it]
+
+
Evaluating eval...:  45%|████▍     | 849/1900 [17:02<21:08,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 850/1900 [17:03<21:24,  1.22s/it]
+
+
Evaluating eval...:  45%|████▍     | 851/1900 [17:04<21:06,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 852/1900 [17:06<21:30,  1.23s/it]
+
+
Evaluating eval...:  45%|████▍     | 853/1900 [17:07<21:07,  1.21s/it]
+
+
Evaluating eval...:  45%|████▍     | 854/1900 [17:08<21:07,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 855/1900 [17:09<21:08,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 856/1900 [17:10<20:53,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 857/1900 [17:12<20:50,  1.20s/it]
+
+
Evaluating eval...:  45%|████▌     | 858/1900 [17:13<21:22,  1.23s/it]
+
+
Evaluating eval...:  45%|████▌     | 859/1900 [17:14<21:16,  1.23s/it]
+
+
Evaluating eval...:  45%|████▌     | 860/1900 [17:15<21:10,  1.22s/it]
+
+
Evaluating eval...:  45%|████▌     | 861/1900 [17:17<21:39,  1.25s/it]
+
+
Evaluating eval...:  45%|████▌     | 862/1900 [17:18<21:31,  1.24s/it]
+
+
Evaluating eval...:  45%|████▌     | 863/1900 [17:19<20:59,  1.21s/it]
+
+
Evaluating eval...:  45%|████▌     | 864/1900 [17:20<20:46,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 865/1900 [17:21<20:27,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 866/1900 [17:23<20:20,  1.18s/it]
+
+
Evaluating eval...:  46%|████▌     | 867/1900 [17:24<20:42,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 868/1900 [17:25<21:15,  1.24s/it]
+
+
Evaluating eval...:  46%|████▌     | 869/1900 [17:26<20:52,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 870/1900 [17:28<20:51,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 871/1900 [17:29<21:01,  1.23s/it]
+
+
Evaluating eval...:  46%|████▌     | 872/1900 [17:30<20:51,  1.22s/it]
+
+
Evaluating eval...:  46%|████▌     | 873/1900 [17:31<20:36,  1.20s/it]
+
+
Evaluating eval...:  46%|████▌     | 874/1900 [17:32<20:58,  1.23s/it]
+
+
Evaluating eval...:  46%|████▌     | 875/1900 [17:34<20:57,  1.23s/it]
+
+
Evaluating eval...:  46%|████▌     | 876/1900 [17:35<20:38,  1.21s/it]
+
+
Evaluating eval...:  46%|████▌     | 877/1900 [17:36<20:18,  1.19s/it]
+
+
Evaluating eval...:  46%|████▌     | 878/1900 [17:37<20:33,  1.21s/it]
+
+
Evaluating eval...:  46%|████▋     | 879/1900 [17:38<20:25,  1.20s/it]
+
+
Evaluating eval...:  46%|████▋     | 880/1900 [17:40<20:16,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 881/1900 [17:41<20:07,  1.18s/it]
+
+
Evaluating eval...:  46%|████▋     | 882/1900 [17:42<20:11,  1.19s/it]
+
+
Evaluating eval...:  46%|████▋     | 883/1900 [17:43<20:31,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 884/1900 [17:44<20:26,  1.21s/it]
+
+
Evaluating eval...:  47%|███��▋     | 885/1900 [17:46<20:14,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 886/1900 [17:47<20:05,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 887/1900 [17:48<20:20,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 888/1900 [17:49<20:21,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 889/1900 [17:50<20:14,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 890/1900 [17:52<20:06,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 891/1900 [17:53<20:22,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 892/1900 [17:54<20:26,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 893/1900 [17:55<20:27,  1.22s/it]
+
+
Evaluating eval...:  47%|████▋     | 894/1900 [17:56<20:08,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 895/1900 [17:58<20:11,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 896/1900 [17:59<20:08,  1.20s/it]
+
+
Evaluating eval...:  47%|████▋     | 897/1900 [18:00<19:58,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 898/1900 [18:01<20:34,  1.23s/it]
+
+
Evaluating eval...:  47%|████▋     | 899/1900 [18:03<20:11,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 900/1900 [18:04<20:08,  1.21s/it]
+
+
Evaluating eval...:  47%|████▋     | 901/1900 [18:05<19:52,  1.19s/it]
+
+
Evaluating eval...:  47%|████▋     | 902/1900 [18:06<20:02,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 903/1900 [18:07<20:13,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 904/1900 [18:09<20:05,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 905/1900 [18:10<19:55,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 906/1900 [18:11<19:46,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 907/1900 [18:12<19:57,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 908/1900 [18:13<19:42,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 909/1900 [18:15<19:43,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 910/1900 [18:16<19:35,  1.19s/it]
+
+
Evaluating eval...:  48%|████▊     | 911/1900 [18:17<19:43,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 912/1900 [18:18<19:44,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 913/1900 [18:19<19:40,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 914/1900 [18:20<19:39,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 915/1900 [18:22<20:11,  1.23s/it]
+
+
Evaluating eval...:  48%|████▊     | 916/1900 [18:23<20:00,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 917/1900 [18:24<19:41,  1.20s/it]
+
+
Evaluating eval...:  48%|████▊     | 918/1900 [18:25<19:47,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 919/1900 [18:27<19:53,  1.22s/it]
+
+
Evaluating eval...:  48%|████▊     | 920/1900 [18:28<19:43,  1.21s/it]
+
+
Evaluating eval...:  48%|████▊     | 921/1900 [18:29<19:31,  1.20s/it]
+
+
Evaluating eval...:  49%|████▊     | 922/1900 [18:30<19:24,  1.19s/it]
+
+
Evaluating eval...:  49%|████▊     | 923/1900 [18:31<19:59,  1.23s/it]
+
+
Evaluating eval...:  49%|████▊     | 924/1900 [18:33<19:34,  1.20s/it]
+
+
Evaluating eval...:  49%|████▊     | 925/1900 [18:34<19:52,  1.22s/it]
+
+
Evaluating eval...:  49%|████▊     | 926/1900 [18:35<19:35,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 927/1900 [18:36<19:20,  1.19s/it]
+
+
Evaluating eval...:  49%|████▉     | 928/1900 [18:37<19:41,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 929/1900 [18:39<19:24,  1.20s/it]
+
+
Evaluating eval...:  49%|████▉     | 930/1900 [18:40<19:11,  1.19s/it]
+
+
Evaluating eval...:  49%|████▉     | 931/1900 [18:41<19:32,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 932/1900 [18:42<19:58,  1.24s/it]
+
+
Evaluating eval...:  49%|████▉     | 933/1900 [18:44<19:48,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 934/1900 [18:45<19:31,  1.21s/it]
+
+
Evaluating eval...:  49%|████▉     | 935/1900 [18:46<19:41,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 936/1900 [18:47<20:02,  1.25s/it]
+
+
Evaluating eval...:  49%|████▉     | 937/1900 [18:48<19:46,  1.23s/it]
+
+
Evaluating eval...:  49%|████▉     | 938/1900 [18:50<19:33,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 939/1900 [18:51<19:31,  1.22s/it]
+
+
Evaluating eval...:  49%|████▉     | 940/1900 [18:52<19:35,  1.22s/it]
+
+
Evaluating eval...:  50%|████▉     | 941/1900 [18:53<19:37,  1.23s/it]
+
+
Evaluating eval...:  50%|████▉     | 942/1900 [18:55<19:51,  1.24s/it]
+
+
Evaluating eval...:  50%|████▉     | 943/1900 [18:56<19:34,  1.23s/it]
+
+
Evaluating eval...:  50%|████▉     | 944/1900 [18:57<19:16,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 945/1900 [18:58<18:57,  1.19s/it]
+
+
Evaluating eval...:  50%|████▉     | 946/1900 [18:59<19:08,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 947/1900 [19:01<19:14,  1.21s/it]
+
+
Evaluating eval...:  50%|████▉     | 948/1900 [19:02<19:03,  1.20s/it]
+
+
Evaluating eval...:  50%|████▉     | 949/1900 [19:03<19:04,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 950/1900 [19:04<19:05,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 951/1900 [19:05<19:20,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 952/1900 [19:07<19:36,  1.24s/it]
+
+
Evaluating eval...:  50%|█████     | 953/1900 [19:08<19:07,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 954/1900 [19:09<18:50,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 955/1900 [19:10<19:15,  1.22s/it]
+
+
Evaluating eval...:  50%|█████     | 956/1900 [19:12<18:59,  1.21s/it]
+
+
Evaluating eval...:  50%|█████     | 957/1900 [19:13<18:49,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 958/1900 [19:14<18:51,  1.20s/it]
+
+
Evaluating eval...:  50%|█████     | 959/1900 [19:15<18:48,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 960/1900 [19:16<18:47,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 961/1900 [19:18<19:19,  1.24s/it]
+
+
Evaluating eval...:  51%|█████     | 962/1900 [19:19<19:08,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 963/1900 [19:20<19:11,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 964/1900 [19:21<19:12,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 965/1900 [19:23<19:06,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 966/1900 [19:24<18:43,  1.20s/it]
+
+
Evaluating eval...:  51%|█████     | 967/1900 [19:25<18:31,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 968/1900 [19:26<18:31,  1.19s/it]
+
+
Evaluating eval...:  51%|█████     | 969/1900 [19:27<18:41,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 970/1900 [19:28<18:51,  1.22s/it]
+
+
Evaluating eval...:  51%|█████     | 971/1900 [19:30<18:40,  1.21s/it]
+
+
Evaluating eval...:  51%|█████     | 972/1900 [19:31<18:58,  1.23s/it]
+
+
Evaluating eval...:  51%|█████     | 973/1900 [19:32<18:44,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 974/1900 [19:33<18:28,  1.20s/it]
+
+
Evaluating eval...:  51%|█████▏    | 975/1900 [19:35<18:55,  1.23s/it]
+
+
Evaluating eval...:  51%|█████▏    | 976/1900 [19:36<19:02,  1.24s/it]
+
+
Evaluating eval...:  51%|█████▏    | 977/1900 [19:37<18:39,  1.21s/it]
+
+
Evaluating eval...:  51%|█████▏    | 978/1900 [19:38<18:48,  1.22s/it]
+
+
Evaluating eval...:  52%|█████▏    | 979/1900 [19:39<18:37,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 980/1900 [19:41<18:32,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 981/1900 [19:42<18:12,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 982/1900 [19:43<17:59,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 983/1900 [19:44<18:13,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 984/1900 [19:45<18:14,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 985/1900 [19:47<18:01,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 986/1900 [19:48<17:55,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 987/1900 [19:49<18:02,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 988/1900 [19:50<17:57,  1.18s/it]
+
+
Evaluating eval...:  52%|█████▏    | 989/1900 [19:51<18:08,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 990/1900 [19:53<18:39,  1.23s/it]
+
+
Evaluating eval...:  52%|█████▏    | 991/1900 [19:54<18:24,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 992/1900 [19:55<18:13,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 993/1900 [19:56<18:11,  1.20s/it]
+
+
Evaluating eval...:  52%|█████▏    | 994/1900 [19:57<18:00,  1.19s/it]
+
+
Evaluating eval...:  52%|█████▏    | 995/1900 [19:59<18:16,  1.21s/it]
+
+
Evaluating eval...:  52%|█████▏    | 996/1900 [20:00<18:04,  1.20s/it]
+
+
Evaluating eval...:  52%|████���▏    | 997/1900 [20:01<18:02,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 998/1900 [20:02<17:57,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 999/1900 [20:03<17:57,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1000/1900 [20:05<17:50,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1001/1900 [20:06<17:49,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1002/1900 [20:07<17:51,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1003/1900 [20:08<17:58,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1004/1900 [20:09<18:01,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1005/1900 [20:11<17:51,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1006/1900 [20:12<17:50,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1007/1900 [20:13<17:41,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1008/1900 [20:14<17:32,  1.18s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1009/1900 [20:15<17:33,  1.18s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1010/1900 [20:16<17:29,  1.18s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1011/1900 [20:18<17:37,  1.19s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1012/1900 [20:19<17:57,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1013/1900 [20:20<17:42,  1.20s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1014/1900 [20:21<18:03,  1.22s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1015/1900 [20:23<17:53,  1.21s/it]
+
+
Evaluating eval...:  53%|█████▎    | 1016/1900 [20:24<18:16,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1017/1900 [20:25<18:12,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1018/1900 [20:26<18:11,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1019/1900 [20:28<18:27,  1.26s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1020/1900 [20:29<18:12,  1.24s/it]
+
+
Evaluating eval...:  54%|█████▎    | 1021/1900 [20:30<18:01,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1022/1900 [20:31<17:56,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1023/1900 [20:32<17:48,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1024/1900 [20:34<17:49,  1.22s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1025/1900 [20:35<17:34,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1026/1900 [20:36<17:40,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1027/1900 [20:37<17:35,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1028/1900 [20:38<17:22,  1.19s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1029/1900 [20:40<17:23,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1030/1900 [20:41<17:16,  1.19s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1031/1900 [20:42<17:45,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1032/1900 [20:43<17:34,  1.21s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1033/1900 [20:44<17:19,  1.20s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1034/1900 [20:46<17:45,  1.23s/it]
+
+
Evaluating eval...:  54%|█████▍    | 1035/1900 [20:47<17:27,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1036/1900 [20:48<17:22,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1037/1900 [20:49<17:26,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1038/1900 [20:51<17:21,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1039/1900 [20:52<17:27,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1040/1900 [20:53<17:17,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1041/1900 [20:54<17:21,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1042/1900 [20:55<17:26,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1043/1900 [20:57<17:13,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▍    | 1044/1900 [20:58<17:09,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1045/1900 [20:59<16:53,  1.19s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1046/1900 [21:00<16:49,  1.18s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1047/1900 [21:01<16:47,  1.18s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1048/1900 [21:03<17:00,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1049/1900 [21:04<17:08,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1050/1900 [21:05<17:20,  1.22s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1051/1900 [21:06<17:05,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1052/1900 [21:07<17:03,  1.21s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1053/1900 [21:09<16:58,  1.20s/it]
+
+
Evaluating eval...:  55%|█████▌    | 1054/1900 [21:10<16:50,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1055/1900 [21:11<16:36,  1.18s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1056/1900 [21:12<16:58,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1057/1900 [21:13<17:25,  1.24s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1058/1900 [21:15<17:19,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1059/1900 [21:16<16:55,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1060/1900 [21:17<16:40,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1061/1900 [21:18<16:46,  1.20s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1062/1900 [21:19<16:34,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1063/1900 [21:21<16:37,  1.19s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1064/1900 [21:22<16:50,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1065/1900 [21:23<17:03,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1066/1900 [21:24<16:47,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1067/1900 [21:26<16:54,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▌    | 1068/1900 [21:27<16:48,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1069/1900 [21:28<16:51,  1.22s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1070/1900 [21:29<16:43,  1.21s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1071/1900 [21:30<16:55,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1072/1900 [21:32<17:00,  1.23s/it]
+
+
Evaluating eval...:  56%|█████▋    | 1073/1900 [21:33<16:41,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1074/1900 [21:34<16:38,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1075/1900 [21:35<16:40,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1076/1900 [21:36<16:47,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1077/1900 [21:38<16:46,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1078/1900 [21:39<16:24,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1079/1900 [21:40<16:37,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1080/1900 [21:41<17:08,  1.25s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1081/1900 [21:43<16:58,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1082/1900 [21:44<16:47,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1083/1900 [21:45<16:48,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1084/1900 [21:46<16:39,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1085/1900 [21:48<16:39,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1086/1900 [21:49<16:42,  1.23s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1087/1900 [21:50<16:29,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1088/1900 [21:51<16:21,  1.21s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1089/1900 [21:52<16:47,  1.24s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1090/1900 [21:54<16:28,  1.22s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1091/1900 [21:55<16:10,  1.20s/it]
+
+
Evaluating eval...:  57%|█████▋    | 1092/1900 [21:56<16:26,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1093/1900 [21:57<16:20,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1094/1900 [21:58<16:15,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1095/1900 [22:00<16:07,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1096/1900 [22:01<15:54,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1097/1900 [22:02<15:44,  1.18s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1098/1900 [22:03<16:00,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1099/1900 [22:04<16:09,  1.21s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1100/1900 [22:06<16:03,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1101/1900 [22:07<15:54,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1102/1900 [22:08<15:49,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1103/1900 [22:09<15:59,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1104/1900 [22:10<15:48,  1.19s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1105/1900 [22:12<16:27,  1.24s/it]
+
+
Evaluating eval...:  58%|███���█▊    | 1106/1900 [22:13<16:31,  1.25s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1107/1900 [22:14<16:25,  1.24s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1108/1900 [22:15<16:08,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1109/1900 [22:17<16:01,  1.22s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1110/1900 [22:18<15:50,  1.20s/it]
+
+
Evaluating eval...:  58%|█████▊    | 1111/1900 [22:19<16:14,  1.24s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1112/1900 [22:20<16:07,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1113/1900 [22:22<16:03,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1114/1900 [22:23<16:01,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1115/1900 [22:24<15:56,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▊    | 1116/1900 [22:25<16:02,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1117/1900 [22:26<15:54,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1118/1900 [22:28<15:41,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1119/1900 [22:29<15:47,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1120/1900 [22:30<15:42,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1121/1900 [22:31<15:45,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1122/1900 [22:32<15:28,  1.19s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1123/1900 [22:34<15:46,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1124/1900 [22:35<15:57,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1125/1900 [22:36<15:42,  1.22s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1126/1900 [22:37<15:36,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1127/1900 [22:38<15:32,  1.21s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1128/1900 [22:40<15:47,  1.23s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1129/1900 [22:41<15:28,  1.20s/it]
+
+
Evaluating eval...:  59%|█████▉    | 1130/1900 [22:42<15:21,  1.20s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1131/1900 [22:43<15:30,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1132/1900 [22:45<15:45,  1.23s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1133/1900 [22:46<15:45,  1.23s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1134/1900 [22:47<15:35,  1.22s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1135/1900 [22:48<16:00,  1.26s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1136/1900 [22:50<15:39,  1.23s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1137/1900 [22:51<15:22,  1.21s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1138/1900 [22:52<15:44,  1.24s/it]
+
+
Evaluating eval...:  60%|█████▉    | 1139/1900 [22:53<15:40,  1.24s/it]
+
+
Evaluating eval...:  60%|██████    | 1140/1900 [22:54<15:39,  1.24s/it]
+
+
Evaluating eval...:  60%|██████    | 1141/1900 [22:56<15:45,  1.25s/it]
+
+
Evaluating eval...:  60%|██████    | 1142/1900 [22:57<15:22,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1143/1900 [22:58<15:09,  1.20s/it]
+
+
Evaluating eval...:  60%|██████    | 1144/1900 [22:59<15:06,  1.20s/it]
+
+
Evaluating eval...:  60%|██████    | 1145/1900 [23:01<15:16,  1.21s/it]
+
+
Evaluating eval...:  60%|██████    | 1146/1900 [23:02<15:16,  1.22s/it]
+
+
Evaluating eval...:  60%|██████    | 1147/1900 [23:03<15:22,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1148/1900 [23:04<15:22,  1.23s/it]
+
+
Evaluating eval...:  60%|██████    | 1149/1900 [23:05<15:05,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1150/1900 [23:07<15:10,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1151/1900 [23:08<15:01,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1152/1900 [23:09<14:54,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1153/1900 [23:10<15:05,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1154/1900 [23:11<15:02,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1155/1900 [23:13<14:55,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1156/1900 [23:14<14:43,  1.19s/it]
+
+
Evaluating eval...:  61%|██████    | 1157/1900 [23:15<14:48,  1.20s/it]
+
+
Evaluating eval...:  61%|██████    | 1158/1900 [23:16<15:11,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1159/1900 [23:17<14:58,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1160/1900 [23:19<14:59,  1.22s/it]
+
+
Evaluating eval...:  61%|██████    | 1161/1900 [23:20<15:07,  1.23s/it]
+
+
Evaluating eval...:  61%|██████    | 1162/1900 [23:21<14:53,  1.21s/it]
+
+
Evaluating eval...:  61%|██████    | 1163/1900 [23:22<14:50,  1.21s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1164/1900 [23:23<14:37,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1165/1900 [23:25<14:34,  1.19s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1166/1900 [23:26<14:45,  1.21s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1167/1900 [23:27<14:52,  1.22s/it]
+
+
Evaluating eval...:  61%|██████▏   | 1168/1900 [23:28<14:51,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1169/1900 [23:30<14:42,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1170/1900 [23:31<14:49,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1171/1900 [23:32<14:50,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1172/1900 [23:33<14:48,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1173/1900 [23:34<14:40,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1174/1900 [23:36<14:27,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1175/1900 [23:37<14:28,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1176/1900 [23:38<14:39,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1177/1900 [23:39<14:26,  1.20s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1178/1900 [23:40<14:16,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1179/1900 [23:42<14:16,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1180/1900 [23:43<14:28,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1181/1900 [23:44<14:17,  1.19s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1182/1900 [23:45<14:28,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1183/1900 [23:46<14:29,  1.21s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1184/1900 [23:48<14:40,  1.23s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1185/1900 [23:49<14:34,  1.22s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1186/1900 [23:50<14:42,  1.24s/it]
+
+
Evaluating eval...:  62%|██████▏   | 1187/1900 [23:51<14:29,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1188/1900 [23:52<14:15,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1189/1900 [23:54<14:11,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1190/1900 [23:55<14:00,  1.18s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1191/1900 [23:56<14:06,  1.19s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1192/1900 [23:57<14:22,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1193/1900 [23:59<14:15,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1194/1900 [24:00<14:27,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1195/1900 [24:01<14:20,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1196/1900 [24:02<14:10,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1197/1900 [24:03<14:15,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1198/1900 [24:05<14:09,  1.21s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1199/1900 [24:06<14:30,  1.24s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1200/1900 [24:07<14:23,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1201/1900 [24:08<14:12,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1202/1900 [24:09<13:59,  1.20s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1203/1900 [24:11<14:09,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1204/1900 [24:12<14:12,  1.23s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1205/1900 [24:13<14:07,  1.22s/it]
+
+
Evaluating eval...:  63%|██████▎   | 1206/1900 [24:14<14:11,  1.23s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1207/1900 [24:16<13:54,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1208/1900 [24:17<13:49,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1209/1900 [24:18<13:39,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1210/1900 [24:19<13:53,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▎   | 1211/1900 [24:20<13:57,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1212/1900 [24:22<13:54,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1213/1900 [24:23<13:48,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1214/1900 [24:24<13:47,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1215/1900 [24:25<13:38,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1216/1900 [24:26<13:46,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1217/1900 [24:28<13:47,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1218/1900 [24:29<13:54,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1219/1900 [24:30<13:48,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1220/1900 [24:31<13:46,  1.22s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1221/1900 [24:32<13:41,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1222/1900 [24:34<13:37,  1.21s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1223/1900 [24:35<13:33,  1.20s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1224/1900 [24:36<13:25,  1.19s/it]
+
+
Evaluating eval...:  64%|██████▍   | 1225/1900 [24:37<13:29,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1226/1900 [24:38<13:31,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1227/1900 [24:40<13:28,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1228/1900 [24:41<13:20,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1229/1900 [24:42<13:15,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1230/1900 [24:43<13:23,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1231/1900 [24:44<13:24,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1232/1900 [24:46<13:19,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1233/1900 [24:47<13:15,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▍   | 1234/1900 [24:48<13:14,  1.19s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1235/1900 [24:49<13:23,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1236/1900 [24:50<13:15,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1237/1900 [24:52<13:17,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1238/1900 [24:53<13:12,  1.20s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1239/1900 [24:54<13:20,  1.21s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1240/1900 [24:55<13:38,  1.24s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1241/1900 [24:57<13:24,  1.22s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1242/1900 [24:58<13:29,  1.23s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1243/1900 [24:59<13:46,  1.26s/it]
+
+
Evaluating eval...:  65%|██████▌   | 1244/1900 [25:00<13:23,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1245/1900 [25:01<13:12,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1246/1900 [25:03<13:20,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1247/1900 [25:04<13:12,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1248/1900 [25:05<13:01,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1249/1900 [25:06<13:11,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1250/1900 [25:08<13:03,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1251/1900 [25:09<12:54,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1252/1900 [25:10<12:55,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1253/1900 [25:11<13:07,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1254/1900 [25:12<13:17,  1.23s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1255/1900 [25:14<13:21,  1.24s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1256/1900 [25:15<13:20,  1.24s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1257/1900 [25:16<13:04,  1.22s/it]
+
+
Evaluating eval...:  66%|██████▌   | 1258/1900 [25:17<13:07,  1.23s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1259/1900 [25:18<12:51,  1.20s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1260/1900 [25:20<12:51,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1261/1900 [25:21<12:50,  1.21s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1262/1900 [25:22<12:39,  1.19s/it]
+
+
Evaluating eval...:  66%|██████▋   | 1263/1900 [25:23<12:42,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1264/1900 [25:24<12:41,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1265/1900 [25:26<12:46,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1266/1900 [25:27<12:59,  1.23s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1267/1900 [25:28<12:51,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1268/1900 [25:29<12:44,  1.21s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1269/1900 [25:31<12:49,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1270/1900 [25:32<12:36,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1271/1900 [25:33<12:45,  1.22s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1272/1900 [25:34<12:31,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1273/1900 [25:35<12:33,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1274/1900 [25:37<12:29,  1.20s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1275/1900 [25:38<12:22,  1.19s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1276/1900 [25:39<12:19,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1277/1900 [25:40<12:17,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1278/1900 [25:41<12:12,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1279/1900 [25:42<12:11,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1280/1900 [25:44<12:12,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1281/1900 [25:45<12:08,  1.18s/it]
+
+
Evaluating eval...:  67%|██████▋   | 1282/1900 [25:46<12:03,  1.17s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1283/1900 [25:47<12:02,  1.17s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1284/1900 [25:48<12:04,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1285/1900 [25:49<12:04,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1286/1900 [25:51<12:07,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1287/1900 [25:52<12:21,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1288/1900 [25:53<12:19,  1.21s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1289/1900 [25:54<12:08,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1290/1900 [25:55<12:06,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1291/1900 [25:57<12:00,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1292/1900 [25:58<12:05,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1293/1900 [25:59<12:03,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1294/1900 [26:00<12:06,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1295/1900 [26:01<12:00,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1296/1900 [26:03<12:01,  1.19s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1297/1900 [26:04<11:51,  1.18s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1298/1900 [26:05<12:00,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1299/1900 [26:06<11:58,  1.20s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1300/1900 [26:08<12:12,  1.22s/it]
+
+
Evaluating eval...:  68%|██████▊   | 1301/1900 [26:09<12:12,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1302/1900 [26:10<12:00,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1303/1900 [26:11<11:58,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1304/1900 [26:12<11:55,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1305/1900 [26:13<11:53,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▊   | 1306/1900 [26:15<12:00,  1.21s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1307/1900 [26:16<11:47,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1308/1900 [26:17<11:44,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1309/1900 [26:18<11:40,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1310/1900 [26:19<11:35,  1.18s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1311/1900 [26:21<11:38,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1312/1900 [26:22<11:36,  1.18s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1313/1900 [26:23<11:40,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1314/1900 [26:24<11:33,  1.18s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1315/1900 [26:25<11:35,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1316/1900 [26:27<11:38,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1317/1900 [26:28<11:34,  1.19s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1318/1900 [26:29<11:48,  1.22s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1319/1900 [26:30<11:39,  1.20s/it]
+
+
Evaluating eval...:  69%|██████▉   | 1320/1900 [26:31<11:27,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1321/1900 [26:33<11:37,  1.20s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1322/1900 [26:34<11:29,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1323/1900 [26:35<11:26,  1.19s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1324/1900 [26:36<11:21,  1.18s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1325/1900 [26:37<11:13,  1.17s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1326/1900 [26:38<11:19,  1.18s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1327/1900 [26:40<11:16,  1.18s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1328/1900 [26:41<11:34,  1.21s/it]
+
+
Evaluating eval...:  70%|██████▉   | 1329/1900 [26:42<11:23,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1330/1900 [26:43<11:27,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1331/1900 [26:44<11:20,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1332/1900 [26:46<11:17,  1.19s/it]
+
+
Evaluating eval...:  70%|███████   | 1333/1900 [26:47<11:18,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1334/1900 [26:48<11:21,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1335/1900 [26:49<11:19,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1336/1900 [26:51<11:18,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1337/1900 [26:52<11:21,  1.21s/it]
+
+
Evaluating eval...:  70%|███████   | 1338/1900 [26:53<11:13,  1.20s/it]
+
+
Evaluating eval...:  70%|███████   | 1339/1900 [26:54<11:08,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1340/1900 [26:55<11:04,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1341/1900 [26:56<10:57,  1.18s/it]
+
+
Evaluating eval...:  71%|███████   | 1342/1900 [26:58<11:03,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1343/1900 [26:59<10:56,  1.18s/it]
+
+
Evaluating eval...:  71%|███████   | 1344/1900 [27:00<10:57,  1.18s/it]
+
+
Evaluating eval...:  71%|███████   | 1345/1900 [27:01<11:02,  1.19s/it]
+
+
Evaluating eval...:  71%|███████   | 1346/1900 [27:03<11:30,  1.25s/it]
+
+
Evaluating eval...:  71%|███████   | 1347/1900 [27:04<11:17,  1.23s/it]
+
+
Evaluating eval...:  71%|███████   | 1348/1900 [27:05<11:06,  1.21s/it]
+
+
Evaluating eval...:  71%|███████   | 1349/1900 [27:06<11:22,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1350/1900 [27:07<11:17,  1.23s/it]
+
+
Evaluating eval...:  71%|███████   | 1351/1900 [27:09<11:22,  1.24s/it]
+
+
Evaluating eval...:  71%|███████   | 1352/1900 [27:10<11:14,  1.23s/it]
+
+
Evaluating eval...:  71%|███████   | 1353/1900 [27:11<11:13,  1.23s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1354/1900 [27:12<11:05,  1.22s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1355/1900 [27:13<10:55,  1.20s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1356/1900 [27:15<11:06,  1.22s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1357/1900 [27:16<10:57,  1.21s/it]
+
+
Evaluating eval...:  71%|███████▏  | 1358/1900 [27:17<10:50,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1359/1900 [27:18<10:49,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1360/1900 [27:19<10:42,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1361/1900 [27:21<10:55,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1362/1900 [27:22<10:42,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1363/1900 [27:23<10:57,  1.22s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1364/1900 [27:24<10:48,  1.21s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1365/1900 [27:26<10:41,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1366/1900 [27:27<10:32,  1.18s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1367/1900 [27:28<10:34,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1368/1900 [27:29<10:38,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1369/1900 [27:30<10:33,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1370/1900 [27:32<10:35,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1371/1900 [27:33<10:33,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1372/1900 [27:34<10:27,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1373/1900 [27:35<10:21,  1.18s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1374/1900 [27:36<10:19,  1.18s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1375/1900 [27:37<10:25,  1.19s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1376/1900 [27:39<10:28,  1.20s/it]
+
+
Evaluating eval...:  72%|███████▏  | 1377/1900 [27:40<10:29,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1378/1900 [27:41<10:19,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1379/1900 [27:42<10:20,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1380/1900 [27:43<10:21,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1381/1900 [27:45<10:28,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1382/1900 [27:46<10:21,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1383/1900 [27:47<10:19,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1384/1900 [27:48<10:15,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1385/1900 [27:49<10:16,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1386/1900 [27:51<10:17,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1387/1900 [27:52<10:08,  1.19s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1388/1900 [27:53<10:05,  1.18s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1389/1900 [27:54<09:58,  1.17s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1390/1900 [27:55<10:17,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1391/1900 [27:57<10:20,  1.22s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1392/1900 [27:58<10:13,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1393/1900 [27:59<10:08,  1.20s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1394/1900 [28:00<10:20,  1.23s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1395/1900 [28:01<10:13,  1.21s/it]
+
+
Evaluating eval...:  73%|███████▎  | 1396/1900 [28:03<10:05,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1397/1900 [28:04<09:58,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1398/1900 [28:05<10:04,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1399/1900 [28:06<09:59,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1400/1900 [28:07<09:54,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▎  | 1401/1900 [28:09<10:07,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1402/1900 [28:10<09:56,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1403/1900 [28:11<09:52,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1404/1900 [28:12<09:46,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1405/1900 [28:13<09:39,  1.17s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1406/1900 [28:15<09:45,  1.18s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1407/1900 [28:16<09:49,  1.19s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1408/1900 [28:17<09:58,  1.22s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1409/1900 [28:18<09:52,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1410/1900 [28:19<09:48,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1411/1900 [28:21<09:48,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1412/1900 [28:22<09:50,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1413/1900 [28:23<09:48,  1.21s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1414/1900 [28:24<09:45,  1.20s/it]
+
+
Evaluating eval...:  74%|███████▍  | 1415/1900 [28:25<09:44,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1416/1900 [28:27<09:39,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1417/1900 [28:28<09:37,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1418/1900 [28:29<09:33,  1.19s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1419/1900 [28:30<09:49,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1420/1900 [28:32<09:51,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1421/1900 [28:33<09:46,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1422/1900 [28:34<09:51,  1.24s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1423/1900 [28:35<09:42,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▍  | 1424/1900 [28:36<09:38,  1.22s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1425/1900 [28:38<09:32,  1.21s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1426/1900 [28:39<09:27,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1427/1900 [28:40<09:26,  1.20s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1428/1900 [28:41<09:53,  1.26s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1429/1900 [28:43<09:46,  1.25s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1430/1900 [28:44<09:36,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1431/1900 [28:45<09:38,  1.23s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1432/1900 [28:47<12:09,  1.56s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1433/1900 [28:49<11:19,  1.45s/it]
+
+
Evaluating eval...:  75%|███████▌  | 1434/1900 [28:50<10:40,  1.38s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1435/1900 [28:51<10:17,  1.33s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1436/1900 [28:52<10:06,  1.31s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1437/1900 [28:53<09:49,  1.27s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1438/1900 [28:55<09:35,  1.25s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1439/1900 [28:56<09:31,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1440/1900 [28:57<09:31,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1441/1900 [28:58<09:22,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1442/1900 [28:59<09:24,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1443/1900 [29:01<09:26,  1.24s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1444/1900 [29:02<09:19,  1.23s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1445/1900 [29:03<09:14,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1446/1900 [29:04<09:15,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1447/1900 [29:06<09:08,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▌  | 1448/1900 [29:07<09:06,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1449/1900 [29:08<09:01,  1.20s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1450/1900 [29:09<09:08,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1451/1900 [29:10<09:08,  1.22s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1452/1900 [29:12<09:00,  1.21s/it]
+
+
Evaluating eval...:  76%|███████▋  | 1453/1900 [29:13<09:04,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1454/1900 [29:14<09:22,  1.26s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1455/1900 [29:15<09:21,  1.26s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1456/1900 [29:17<09:19,  1.26s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1457/1900 [29:18<09:09,  1.24s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1458/1900 [29:19<09:05,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1459/1900 [29:20<08:57,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1460/1900 [29:22<08:50,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1461/1900 [29:23<08:50,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1462/1900 [29:24<08:50,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1463/1900 [29:25<08:47,  1.21s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1464/1900 [29:26<08:51,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1465/1900 [29:28<08:48,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1466/1900 [29:29<08:55,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1467/1900 [29:30<08:48,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1468/1900 [29:31<09:03,  1.26s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1469/1900 [29:33<08:59,  1.25s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1470/1900 [29:34<08:45,  1.22s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1471/1900 [29:35<08:47,  1.23s/it]
+
+
Evaluating eval...:  77%|███████▋  | 1472/1900 [29:36<08:41,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1473/1900 [29:37<08:41,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1474/1900 [29:39<08:37,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1475/1900 [29:40<08:40,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1476/1900 [29:41<08:40,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1477/1900 [29:42<08:39,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1478/1900 [29:44<08:43,  1.24s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1479/1900 [29:45<08:49,  1.26s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1480/1900 [29:46<08:36,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1481/1900 [29:47<08:34,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1482/1900 [29:49<08:29,  1.22s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1483/1900 [29:50<08:21,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1484/1900 [29:51<08:20,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1485/1900 [29:52<08:22,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1486/1900 [29:53<08:19,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1487/1900 [29:55<08:27,  1.23s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1488/1900 [29:56<08:17,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1489/1900 [29:57<08:13,  1.20s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1490/1900 [29:58<08:14,  1.21s/it]
+
+
Evaluating eval...:  78%|███████▊  | 1491/1900 [29:59<08:09,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1492/1900 [30:01<08:18,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1493/1900 [30:02<08:18,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1494/1900 [30:03<08:11,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1495/1900 [30:04<08:10,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▊  | 1496/1900 [30:05<08:02,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1497/1900 [30:07<07:58,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1498/1900 [30:08<08:03,  1.20s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1499/1900 [30:09<08:03,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1500/1900 [30:10<08:02,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1501/1900 [30:11<07:56,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1502/1900 [30:13<07:53,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1503/1900 [30:14<07:51,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1504/1900 [30:15<07:48,  1.18s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1505/1900 [30:16<07:49,  1.19s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1506/1900 [30:17<07:54,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1507/1900 [30:19<07:53,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1508/1900 [30:20<07:52,  1.21s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1509/1900 [30:21<07:56,  1.22s/it]
+
+
Evaluating eval...:  79%|███████▉  | 1510/1900 [30:22<07:50,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1511/1900 [30:23<07:51,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1512/1900 [30:25<07:57,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1513/1900 [30:26<07:59,  1.24s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1514/1900 [30:27<07:53,  1.23s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1515/1900 [30:28<08:01,  1.25s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1516/1900 [30:30<07:54,  1.24s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1517/1900 [30:31<07:45,  1.21s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1518/1900 [30:32<07:37,  1.20s/it]
+
+
Evaluating eval...:  80%|███████▉  | 1519/1900 [30:33<07:30,  1.18s/it]
+
+
Evaluating eval...:  80%|████████  | 1520/1900 [30:34<07:34,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1521/1900 [30:36<07:37,  1.21s/it]
+
+
Evaluating eval...:  80%|████████  | 1522/1900 [30:37<07:31,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1523/1900 [30:38<07:31,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1524/1900 [30:39<07:33,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1525/1900 [30:40<07:31,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1526/1900 [30:42<07:25,  1.19s/it]
+
+
Evaluating eval...:  80%|████████  | 1527/1900 [30:43<07:26,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1528/1900 [30:44<07:26,  1.20s/it]
+
+
Evaluating eval...:  80%|████████  | 1529/1900 [30:45<07:21,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1530/1900 [30:46<07:22,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1531/1900 [30:48<07:23,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1532/1900 [30:49<07:29,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1533/1900 [30:50<07:23,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1534/1900 [30:51<07:25,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1535/1900 [30:52<07:18,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1536/1900 [30:54<07:11,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1537/1900 [30:55<07:15,  1.20s/it]
+
+
Evaluating eval...:  81%|████████  | 1538/1900 [30:56<07:11,  1.19s/it]
+
+
Evaluating eval...:  81%|████████  | 1539/1900 [30:57<07:21,  1.22s/it]
+
+
Evaluating eval...:  81%|████████  | 1540/1900 [30:58<07:16,  1.21s/it]
+
+
Evaluating eval...:  81%|████████  | 1541/1900 [31:00<07:25,  1.24s/it]
+
+
Evaluating eval...:  81%|████████  | 1542/1900 [31:01<07:19,  1.23s/it]
+
+
Evaluating eval...:  81%|████████  | 1543/1900 [31:02<07:18,  1.23s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1544/1900 [31:03<07:17,  1.23s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1545/1900 [31:05<07:11,  1.21s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1546/1900 [31:06<07:10,  1.22s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1547/1900 [31:07<07:17,  1.24s/it]
+
+
Evaluating eval...:  81%|████████▏ | 1548/1900 [31:08<07:08,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1549/1900 [31:09<07:01,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1550/1900 [31:11<07:06,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1551/1900 [31:12<07:03,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1552/1900 [31:13<06:56,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1553/1900 [31:14<06:59,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1554/1900 [31:15<06:57,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1555/1900 [31:17<06:54,  1.20s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1556/1900 [31:18<07:06,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1557/1900 [31:19<07:02,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1558/1900 [31:21<07:08,  1.25s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1559/1900 [31:22<07:07,  1.26s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1560/1900 [31:23<06:56,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1561/1900 [31:24<06:58,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1562/1900 [31:25<07:04,  1.26s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1563/1900 [31:27<06:57,  1.24s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1564/1900 [31:28<06:51,  1.23s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1565/1900 [31:29<06:46,  1.21s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1566/1900 [31:30<06:48,  1.22s/it]
+
+
Evaluating eval...:  82%|████████▏ | 1567/1900 [31:32<06:47,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1568/1900 [31:33<06:58,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1569/1900 [31:34<06:57,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1570/1900 [31:35<06:53,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1571/1900 [31:37<06:47,  1.24s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1572/1900 [31:38<06:49,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1573/1900 [31:39<06:41,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1574/1900 [31:40<06:38,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1575/1900 [31:42<06:38,  1.23s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1576/1900 [31:43<06:32,  1.21s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1577/1900 [31:44<06:35,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1578/1900 [31:45<06:33,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1579/1900 [31:46<06:31,  1.22s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1580/1900 [31:48<06:38,  1.25s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1581/1900 [31:49<06:41,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1582/1900 [31:50<06:41,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1583/1900 [31:51<06:37,  1.26s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1584/1900 [31:53<06:40,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1585/1900 [31:54<06:39,  1.27s/it]
+
+
Evaluating eval...:  83%|████████▎ | 1586/1900 [31:55<06:36,  1.26s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1587/1900 [31:56<06:25,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1588/1900 [31:58<06:18,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1589/1900 [31:59<06:17,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1590/1900 [32:00<06:16,  1.22s/it]
+
+
Evaluating eval...:  84%|████████▎ | 1591/1900 [32:01<06:20,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1592/1900 [32:02<06:13,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1593/1900 [32:04<06:11,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1594/1900 [32:05<06:18,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1595/1900 [32:06<06:18,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1596/1900 [32:07<06:16,  1.24s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1597/1900 [32:09<06:12,  1.23s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1598/1900 [32:10<06:04,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1599/1900 [32:11<05:57,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1600/1900 [32:12<05:53,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1601/1900 [32:13<05:51,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1602/1900 [32:15<05:52,  1.18s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1603/1900 [32:16<05:53,  1.19s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1604/1900 [32:17<05:59,  1.21s/it]
+
+
Evaluating eval...:  84%|████████▍ | 1605/1900 [32:18<05:53,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1606/1900 [32:19<05:51,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1607/1900 [32:21<05:49,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1608/1900 [32:22<05:53,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1609/1900 [32:23<06:01,  1.24s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1610/1900 [32:24<06:01,  1.25s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1611/1900 [32:26<05:54,  1.23s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1612/1900 [32:27<05:46,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1613/1900 [32:28<05:40,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▍ | 1614/1900 [32:29<05:43,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1615/1900 [32:30<05:42,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1616/1900 [32:31<05:38,  1.19s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1617/1900 [32:33<05:42,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1618/1900 [32:34<05:43,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1619/1900 [32:35<05:44,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1620/1900 [32:36<05:42,  1.22s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1621/1900 [32:38<05:38,  1.21s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1622/1900 [32:39<05:33,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1623/1900 [32:40<05:31,  1.20s/it]
+
+
Evaluating eval...:  85%|████████▌ | 1624/1900 [32:41<05:27,  1.19s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1625/1900 [32:42<05:33,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1626/1900 [32:44<05:34,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1627/1900 [32:45<05:36,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1628/1900 [32:46<05:34,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1629/1900 [32:47<05:30,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1630/1900 [32:48<05:28,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1631/1900 [32:50<05:39,  1.26s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1632/1900 [32:51<05:33,  1.25s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1633/1900 [32:52<05:30,  1.24s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1634/1900 [32:53<05:26,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1635/1900 [32:55<05:20,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1636/1900 [32:56<05:20,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1637/1900 [32:57<05:23,  1.23s/it]
+
+
Evaluating eval...:  86%|████████▌ | 1638/1900 [32:58<05:15,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1639/1900 [33:00<05:17,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1640/1900 [33:01<05:16,  1.22s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1641/1900 [33:02<05:12,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1642/1900 [33:03<05:13,  1.21s/it]
+
+
Evaluating eval...:  86%|████████▋ | 1643/1900 [33:04<05:12,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1644/1900 [33:06<05:05,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1645/1900 [33:07<05:00,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1646/1900 [33:08<05:04,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1647/1900 [33:09<05:03,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1648/1900 [33:10<05:03,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1649/1900 [33:11<04:59,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1650/1900 [33:13<05:00,  1.20s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1651/1900 [33:14<04:54,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1652/1900 [33:15<04:53,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1653/1900 [33:16<04:52,  1.18s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1654/1900 [33:17<04:53,  1.19s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1655/1900 [33:19<04:58,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1656/1900 [33:20<04:57,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1657/1900 [33:21<04:55,  1.21s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1658/1900 [33:22<04:54,  1.22s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1659/1900 [33:24<04:59,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1660/1900 [33:25<04:57,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1661/1900 [33:26<04:57,  1.24s/it]
+
+
Evaluating eval...:  87%|████████▋ | 1662/1900 [33:27<04:52,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1663/1900 [33:29<04:47,  1.21s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1664/1900 [33:30<04:49,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1665/1900 [33:31<04:47,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1666/1900 [33:32<04:55,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1667/1900 [33:34<04:52,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1668/1900 [33:35<04:47,  1.24s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1669/1900 [33:36<04:47,  1.24s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1670/1900 [33:37<04:46,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1671/1900 [33:39<04:46,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1672/1900 [33:40<04:43,  1.24s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1673/1900 [33:41<04:49,  1.27s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1674/1900 [33:42<04:45,  1.26s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1675/1900 [33:44<04:40,  1.25s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1676/1900 [33:45<04:35,  1.23s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1677/1900 [33:46<04:31,  1.22s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1678/1900 [33:47<04:26,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1679/1900 [33:48<04:25,  1.20s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1680/1900 [33:49<04:22,  1.19s/it]
+
+
Evaluating eval...:  88%|████████▊ | 1681/1900 [33:51<04:22,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1682/1900 [33:52<04:19,  1.19s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1683/1900 [33:53<04:23,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1684/1900 [33:54<04:20,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1685/1900 [33:55<04:16,  1.19s/it]
+
+
Evaluating eval...:  89%|████████▊ | 1686/1900 [33:57<04:17,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1687/1900 [33:58<04:17,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1688/1900 [33:59<04:17,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1689/1900 [34:00<04:14,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1690/1900 [34:02<04:12,  1.20s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1691/1900 [34:03<04:17,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1692/1900 [34:04<04:13,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1693/1900 [34:05<04:13,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1694/1900 [34:07<04:13,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1695/1900 [34:08<04:10,  1.22s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1696/1900 [34:09<04:06,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1697/1900 [34:10<04:08,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1698/1900 [34:11<04:08,  1.23s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1699/1900 [34:13<04:03,  1.21s/it]
+
+
Evaluating eval...:  89%|████████▉ | 1700/1900 [34:14<04:03,  1.22s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1701/1900 [34:15<04:06,  1.24s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1702/1900 [34:16<04:04,  1.23s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1703/1900 [34:18<04:01,  1.23s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1704/1900 [34:19<03:57,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1705/1900 [34:20<03:53,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1706/1900 [34:21<03:53,  1.20s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1707/1900 [34:22<03:50,  1.19s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1708/1900 [34:24<03:52,  1.21s/it]
+
+
Evaluating eval...:  90%|████████▉ | 1709/1900 [34:25<03:51,  1.21s/it]
+
+
Evaluating eval...:  90%|█████████ | 1710/1900 [34:26<03:48,  1.20s/it]
+
+
Evaluating eval...:  90%|█████████ | 1711/1900 [34:27<03:44,  1.19s/it]
+
+
Evaluating eval...:  90%|█████████ | 1712/1900 [34:28<03:42,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1713/1900 [34:29<03:37,  1.17s/it]
+
+
Evaluating eval...:  90%|█████████ | 1714/1900 [34:30<03:35,  1.16s/it]
+
+
Evaluating eval...:  90%|█████████ | 1715/1900 [34:32<03:38,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1716/1900 [34:33<03:37,  1.18s/it]
+
+
Evaluating eval...:  90%|█████████ | 1717/1900 [34:34<03:43,  1.22s/it]
+
+
Evaluating eval...:  90%|█████████ | 1718/1900 [34:35<03:44,  1.23s/it]
+
+
Evaluating eval...:  90%|█████████ | 1719/1900 [34:37<03:39,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1720/1900 [34:38<03:40,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1721/1900 [34:39<03:37,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1722/1900 [34:40<03:39,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████ | 1723/1900 [34:42<03:35,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1724/1900 [34:43<03:40,  1.25s/it]
+
+
Evaluating eval...:  91%|█████████ | 1725/1900 [34:44<03:36,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1726/1900 [34:45<03:36,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1727/1900 [34:47<03:34,  1.24s/it]
+
+
Evaluating eval...:  91%|█████████ | 1728/1900 [34:48<03:28,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1729/1900 [34:49<03:23,  1.19s/it]
+
+
Evaluating eval...:  91%|█████████ | 1730/1900 [34:50<03:26,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████ | 1731/1900 [34:51<03:24,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1732/1900 [34:53<03:23,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████ | 1733/1900 [34:54<03:26,  1.23s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1734/1900 [34:55<03:22,  1.22s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1735/1900 [34:56<03:20,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1736/1900 [34:57<03:18,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1737/1900 [34:59<03:17,  1.21s/it]
+
+
Evaluating eval...:  91%|█████████▏| 1738/1900 [35:00<03:14,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1739/1900 [35:01<03:16,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1740/1900 [35:02<03:14,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1741/1900 [35:04<03:13,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1742/1900 [35:05<03:09,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1743/1900 [35:06<03:08,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1744/1900 [35:07<03:06,  1.19s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1745/1900 [35:08<03:03,  1.18s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1746/1900 [35:10<03:08,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1747/1900 [35:11<03:05,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1748/1900 [35:12<03:04,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1749/1900 [35:13<03:05,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1750/1900 [35:14<03:04,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1751/1900 [35:16<03:03,  1.23s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1752/1900 [35:17<02:59,  1.21s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1753/1900 [35:18<02:55,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1754/1900 [35:19<02:55,  1.20s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1755/1900 [35:20<02:56,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1756/1900 [35:22<02:55,  1.22s/it]
+
+
Evaluating eval...:  92%|█████████▏| 1757/1900 [35:23<03:01,  1.27s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1758/1900 [35:24<02:56,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1759/1900 [35:25<02:51,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1760/1900 [35:27<02:47,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1761/1900 [35:28<02:45,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1762/1900 [35:29<02:45,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1763/1900 [35:30<02:42,  1.19s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1764/1900 [35:31<02:45,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1765/1900 [35:33<02:46,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1766/1900 [35:34<02:43,  1.22s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1767/1900 [35:35<02:40,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1768/1900 [35:36<02:42,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1769/1900 [35:38<02:40,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1770/1900 [35:39<02:41,  1.24s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1771/1900 [35:40<02:38,  1.23s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1772/1900 [35:41<02:35,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1773/1900 [35:42<02:33,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1774/1900 [35:44<02:30,  1.20s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1775/1900 [35:45<02:31,  1.21s/it]
+
+
Evaluating eval...:  93%|█████████▎| 1776/1900 [35:46<02:28,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1777/1900 [35:47<02:26,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1778/1900 [35:48<02:25,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1779/1900 [35:49<02:22,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1780/1900 [35:51<02:20,  1.17s/it]
+
+
Evaluating eval...:  94%|█████████▎| 1781/1900 [35:52<02:18,  1.16s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1782/1900 [35:53<02:18,  1.18s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1783/1900 [35:54<02:20,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1784/1900 [35:55<02:19,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1785/1900 [35:57<02:17,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1786/1900 [35:58<02:17,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1787/1900 [35:59<02:16,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1788/1900 [36:00<02:14,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1789/1900 [36:01<02:11,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1790/1900 [36:03<02:12,  1.20s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1791/1900 [36:04<02:10,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1792/1900 [36:05<02:08,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1793/1900 [36:06<02:09,  1.21s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1794/1900 [36:07<02:06,  1.19s/it]
+
+
Evaluating eval...:  94%|█████████▍| 1795/1900 [36:09<02:05,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1796/1900 [36:10<02:02,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1797/1900 [36:11<02:02,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1798/1900 [36:12<02:03,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1799/1900 [36:13<02:02,  1.22s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1800/1900 [36:15<02:00,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1801/1900 [36:16<01:57,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1802/1900 [36:17<01:56,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1803/1900 [36:18<01:56,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▍| 1804/1900 [36:19<01:53,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1805/1900 [36:21<01:52,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1806/1900 [36:22<01:51,  1.19s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1807/1900 [36:23<01:49,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1808/1900 [36:24<01:47,  1.17s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1809/1900 [36:25<01:46,  1.17s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1810/1900 [36:26<01:45,  1.18s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1811/1900 [36:28<01:47,  1.21s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1812/1900 [36:29<01:45,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1813/1900 [36:30<01:44,  1.20s/it]
+
+
Evaluating eval...:  95%|█████████▌| 1814/1900 [36:31<01:43,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1815/1900 [36:32<01:40,  1.18s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1816/1900 [36:34<01:41,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1817/1900 [36:35<01:42,  1.23s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1818/1900 [36:36<01:39,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1819/1900 [36:37<01:37,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1820/1900 [36:39<01:36,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1821/1900 [36:40<01:35,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1822/1900 [36:41<01:34,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1823/1900 [36:42<01:32,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1824/1900 [36:43<01:31,  1.20s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1825/1900 [36:45<01:30,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1826/1900 [36:46<01:30,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1827/1900 [36:47<01:29,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▌| 1828/1900 [36:48<01:27,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1829/1900 [36:50<01:28,  1.24s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1830/1900 [36:51<01:25,  1.22s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1831/1900 [36:52<01:23,  1.21s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1832/1900 [36:53<01:21,  1.19s/it]
+
+
Evaluating eval...:  96%|█████████▋| 1833/1900 [36:54<01:19,  1.18s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1834/1900 [36:55<01:19,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1835/1900 [36:57<01:17,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1836/1900 [36:58<01:16,  1.19s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1837/1900 [36:59<01:17,  1.23s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1838/1900 [37:00<01:15,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1839/1900 [37:02<01:13,  1.20s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1840/1900 [37:03<01:12,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1841/1900 [37:04<01:11,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1842/1900 [37:05<01:11,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1843/1900 [37:06<01:08,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1844/1900 [37:08<01:08,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1845/1900 [37:09<01:06,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1846/1900 [37:10<01:05,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1847/1900 [37:11<01:03,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1848/1900 [37:12<01:03,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1849/1900 [37:14<01:02,  1.22s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1850/1900 [37:15<01:00,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1851/1900 [37:16<00:59,  1.21s/it]
+
+
Evaluating eval...:  97%|█████████▋| 1852/1900 [37:17<00:57,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1853/1900 [37:18<00:57,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1854/1900 [37:20<00:55,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1855/1900 [37:21<00:55,  1.23s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1856/1900 [37:22<00:53,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1857/1900 [37:23<00:51,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1858/1900 [37:25<00:50,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1859/1900 [37:26<00:49,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1860/1900 [37:27<00:48,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1861/1900 [37:28<00:46,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1862/1900 [37:29<00:45,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1863/1900 [37:30<00:43,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1864/1900 [37:32<00:42,  1.18s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1865/1900 [37:33<00:41,  1.17s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1866/1900 [37:34<00:40,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1867/1900 [37:35<00:39,  1.19s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1868/1900 [37:36<00:38,  1.20s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1869/1900 [37:38<00:37,  1.22s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1870/1900 [37:39<00:36,  1.21s/it]
+
+
Evaluating eval...:  98%|█████████▊| 1871/1900 [37:40<00:35,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1872/1900 [37:41<00:34,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1873/1900 [37:43<00:32,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1874/1900 [37:44<00:31,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1875/1900 [37:45<00:30,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▊| 1876/1900 [37:46<00:28,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1877/1900 [37:47<00:27,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1878/1900 [37:49<00:26,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1879/1900 [37:50<00:25,  1.20s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1880/1900 [37:51<00:23,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1881/1900 [37:52<00:22,  1.18s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1882/1900 [37:53<00:21,  1.22s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1883/1900 [37:55<00:21,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1884/1900 [37:56<00:19,  1.24s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1885/1900 [37:57<00:18,  1.23s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1886/1900 [37:58<00:16,  1.21s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1887/1900 [37:59<00:15,  1.19s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1888/1900 [38:01<00:14,  1.18s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1889/1900 [38:02<00:13,  1.18s/it]
+
+
Evaluating eval...:  99%|█████████▉| 1890/1900 [38:03<00:11,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1891/1900 [38:04<00:10,  1.17s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1892/1900 [38:05<00:09,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1893/1900 [38:07<00:08,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1894/1900 [38:08<00:07,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1895/1900 [38:09<00:05,  1.19s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1896/1900 [38:10<00:04,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1897/1900 [38:11<00:03,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1898/1900 [38:12<00:02,  1.18s/it]
+
+
Evaluating eval...: 100%|█████████▉| 1899/1900 [38:14<00:01,  1.20s/it]
+
+
Evaluating eval...: 100%|██████████| 1900/1900 [38:15<00:00,  1.29s/it]
Evaluating eval...: 100%|██████████| 1900/1900 [38:15<00:00,  1.21s/it]
+Eval results for step (45000 / 100000 | Eval Loss: 1.0432617664337158 | Eval wer: 26.216460140493147 | Eval wer_ortho: 29.520683144524547 |)
+
                                                                             
Eval results for step (45000 / 100000 | Eval Loss: 1.0432617664337158 | Eval wer: 26.216460140493147 | Eval wer_ortho: 29.520683144524547 |)
+
Train steps ... :  45%|████▌     | 45000/100000 [13:45:25<8:56:08,  1.71it/s]
Train steps ... :  45%|████▌     | 45001/100000 [13:45:25<11641:21:41, 761.99s/it]
Train steps ... :  45%|████▌     | 45002/100000 [13:45:25<8151:28:49, 533.57s/it] 
Train steps ... :  45%|████▌     | 45003/100000 [13:45:26<5708:37:02, 373.68s/it]
Train steps ... :  45%|████▌     | 45004/100000 [13:45:27<3998:38:38, 261.75s/it]
Train steps ... :  45%|████▌     | 45005/100000 [13:45:27<2801:40:21, 183.40s/it]
Train steps ... :  45%|████▌     | 45006/100000 [13:45:28<1963:49:08, 128.55s/it]
Train steps ... :  45%|████▌     | 45007/100000 [13:45:28<1377:18:56, 90.16s/it] 
Train steps ... :  45%|████▌     | 45008/100000 [13:45:29<966:46:19, 63.29s/it] 
Train steps ... :  45%|████▌     | 45009/100000 [13:45:30<679:24:27, 44.48s/it]
Train steps ... :  45%|████▌     | 45010/100000 [13:45:30<478:14:52, 31.31s/it]
Train steps ... :  45%|████▌     | 45011/100000 [13:45:31<337:26:15, 22.09s/it]
Train steps ... :  45%|████▌     | 45012/100000 [13:45:31<238:52:37, 15.64s/it]
Train steps ... :  45%|████▌     | 45013/100000 [13:45:32<169:53:04, 11.12s/it]
Train steps ... :  45%|████▌     | 45014/100000 [13:45:32<121:35:19,  7.96s/it]
Train steps ... :  45%|████▌     | 45015/100000 [13:45:33<87:46:56,  5.75s/it] 
Train steps ... :  45%|████▌     | 45016/100000 [13:45:34<64:06:57,  4.20s/it]
Train steps ... :  45%|████▌     | 45017/100000 [13:45:34<47:33:20,  3.11s/it]
Train steps ... :  45%|████▌     | 45018/100000 [13:45:35<35:58:19,  2.36s/it]
Train steps ... :  45%|████▌     | 45019/100000 [13:45:35<27:51:01,  1.82s/it]
Train steps ... :  45%|████▌     | 45020/100000 [13:45:36<22:10:09,  1.45s/it]
Train steps ... :  45%|████▌     | 45021/100000 [13:45:37<18:11:52,  1.19s/it]
Train steps ... :  45%|████▌     | 45022/100000 [13:45:37<15:24:52,  1.01s/it]
Train steps ... :  45%|████▌     | 45023/100000 [13:45:38<13:27:52,  1.13it/s]
Train steps ... :  45%|████▌     | 45024/100000 [13:45:38<12:06:22,  1.26it/s]
Train steps ... :  45%|████▌     | 45025/100000 [13:45:39<11:09:02,  1.37it/s]Step... (45025 / 100000 | Loss: 0.8431174755096436, Learning Rate: 5.5251256281407036e-05)
+
                                                                              
Step... (45025 / 100000 | Loss: 0.801513671875, Learning Rate: 5.5251256281407036e-05)
+
Train steps ... :  45%|████▌     | 45025/100000 [13:45:39<11:09:02,  1.37it/s]
Train steps ... :  45%|████▌     | 45026/100000 [13:45:39<10:28:48,  1.46it/s]
Train steps ... :  45%|████▌     | 45027/100000 [13:45:40<10:00:24,  1.53it/s]
Train steps ... :  45%|████▌     | 45028/100000 [13:45:41<9:41:09,  1.58it/s] 
Train steps ... :  45%|████▌     | 45029/100000 [13:45:41<9:27:14,  1.62it/s]
Train steps ... :  45%|████▌     | 45030/100000 [13:45:42<9:17:00,  1.64it/s]
Train steps ... :  45%|████▌     | 45031/100000 [13:45:42<9:10:07,  1.67it/s]
Train steps ... :  45%|████▌     | 45032/100000 [13:45:43<9:05:14,  1.68it/s]
Train steps ... :  45%|████▌     | 45033/100000 [13:45:44<9:02:37,  1.69it/s]
Train steps ... :  45%|████▌     | 45034/100000 [13:45:44<8:59:50,  1.70it/s]
Train steps ... :  45%|████▌     | 45035/100000 [13:45:45<8:57:59,  1.70it/s]
Train steps ... :  45%|████▌     | 45036/100000 [13:45:45<8:57:43,  1.70it/s]
Train steps ... :  45%|████▌     | 45037/100000 [13:45:46<8:58:08,  1.70it/s]
Train steps ... :  45%|████▌     | 45038/100000 [13:45:46<8:57:52,  1.70it/s]
Train steps ... :  45%|████▌     | 45039/100000 [13:45:47<8:57:38,  1.70it/s]
Train steps ... :  45%|████▌     | 45040/100000 [13:45:48<8:56:27,  1.71it/s]
Train steps ... :  45%|████▌     | 45041/100000 [13:45:48<8:57:16,  1.70it/s]
Train steps ... :  45%|████▌     | 45042/100000 [13:45:49<8:56:48,  1.71it/s]
Train steps ... :  45%|████▌     | 45043/100000 [13:45:49<8:56:38,  1.71it/s]
Train steps ... :  45%|████▌     | 45044/100000 [13:45:50<8:57:30,  1.70it/s]
Train steps ... :  45%|████▌     | 45045/100000 [13:45:51<8:56:16,  1.71it/s]
Train steps ... :  45%|████▌     | 45046/100000 [13:45:51<8:55:37,  1.71it/s]
Train steps ... :  45%|████▌     | 45047/100000 [13:45:52<8:55:20,  1.71it/s]
Train steps ... :  45%|████▌     | 45048/100000 [13:45:52<8:55:25,  1.71it/s]
Train steps ... :  45%|████▌     | 45049/100000 [13:45:53<8:55:12,  1.71it/s]
Train steps ... :  45%|████▌     | 45050/100000 [13:45:53<8:55:07,  1.71it/s]Step... (45050 / 100000 | Loss: 0.897830605506897, Learning Rate: 5.522613065326634e-05)
+
                                                                             
Step... (45050 / 100000 | Loss: 0.6034043431282043, Learning Rate: 5.522613065326634e-05)
+
Train steps ... :  45%|████▌     | 45050/100000 [13:45:54<8:55:07,  1.71it/s]
Train steps ... :  45%|████▌     | 45051/100000 [13:45:54<8:54:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45052/100000 [13:45:55<8:54:27,  1.71it/s]
Train steps ... :  45%|████▌     | 45053/100000 [13:45:55<8:54:17,  1.71it/s]
Train steps ... :  45%|████▌     | 45054/100000 [13:45:56<8:54:10,  1.71it/s]
Train steps ... :  45%|████▌     | 45055/100000 [13:45:56<8:54:18,  1.71it/s]
Train steps ... :  45%|████▌     | 45056/100000 [13:45:57<8:54:02,  1.71it/s]
Train steps ... :  45%|████▌     | 45057/100000 [13:45:58<8:54:45,  1.71it/s]
Train steps ... :  45%|████▌     | 45058/100000 [13:45:58<8:55:03,  1.71it/s]
Train steps ... :  45%|████▌     | 45059/100000 [13:45:59<8:54:40,  1.71it/s]
Train steps ... :  45%|████▌     | 45060/100000 [13:45:59<8:54:54,  1.71it/s]
Train steps ... :  45%|████▌     | 45061/100000 [13:46:00<8:54:30,  1.71it/s]
Train steps ... :  45%|████▌     | 45062/100000 [13:46:00<8:54:18,  1.71it/s]
Train steps ... :  45%|████▌     | 45063/100000 [13:46:01<8:54:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45064/100000 [13:46:02<8:54:03,  1.71it/s]
Train steps ... :  45%|████▌     | 45065/100000 [13:46:02<8:54:00,  1.71it/s]
Train steps ... :  45%|████▌     | 45066/100000 [13:46:03<8:54:16,  1.71it/s]
Train steps ... :  45%|████▌     | 45067/100000 [13:46:03<8:54:46,  1.71it/s]
Train steps ... :  45%|████▌     | 45068/100000 [13:46:04<8:54:22,  1.71it/s]
Train steps ... :  45%|████▌     | 45069/100000 [13:46:05<8:54:01,  1.71it/s]
Train steps ... :  45%|████▌     | 45070/100000 [13:46:05<8:54:28,  1.71it/s]
Train steps ... :  45%|████▌     | 45071/100000 [13:46:06<8:53:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45072/100000 [13:46:06<8:53:47,  1.72it/s]
Train steps ... :  45%|████▌     | 45073/100000 [13:46:07<8:53:53,  1.71it/s]
Train steps ... :  45%|████▌     | 45074/100000 [13:46:07<8:53:44,  1.72it/s]
Train steps ... :  45%|████▌     | 45075/100000 [13:46:08<8:54:02,  1.71it/s]Step... (45075 / 100000 | Loss: 0.9091838598251343, Learning Rate: 5.520100502512563e-05)
+
                                                                             
Step... (45075 / 100000 | Loss: 0.6468457579612732, Learning Rate: 5.520100502512563e-05)
+
Train steps ... :  45%|████▌     | 45075/100000 [13:46:08<8:54:02,  1.71it/s]
Train steps ... :  45%|████▌     | 45076/100000 [13:46:09<8:54:30,  1.71it/s]
Train steps ... :  45%|████▌     | 45077/100000 [13:46:09<8:54:35,  1.71it/s]
Train steps ... :  45%|████▌     | 45078/100000 [13:46:10<8:54:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45079/100000 [13:46:10<8:54:15,  1.71it/s]
Train steps ... :  45%|████▌     | 45080/100000 [13:46:11<8:54:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45081/100000 [13:46:12<8:54:51,  1.71it/s]
Train steps ... :  45%|████▌     | 45082/100000 [13:46:12<8:54:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45083/100000 [13:46:13<8:54:28,  1.71it/s]
Train steps ... :  45%|████▌     | 45084/100000 [13:46:13<8:54:15,  1.71it/s]
Train steps ... :  45%|████▌     | 45085/100000 [13:46:14<8:54:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45086/100000 [13:46:14<8:54:29,  1.71it/s]
Train steps ... :  45%|████▌     | 45087/100000 [13:46:15<8:54:03,  1.71it/s]
Train steps ... :  45%|████▌     | 45088/100000 [13:46:16<8:54:12,  1.71it/s]
Train steps ... :  45%|████▌     | 45089/100000 [13:46:16<8:54:27,  1.71it/s]
Train steps ... :  45%|████▌     | 45090/100000 [13:46:17<8:54:02,  1.71it/s]
Train steps ... :  45%|████▌     | 45091/100000 [13:46:17<8:54:05,  1.71it/s]
Train steps ... :  45%|████▌     | 45092/100000 [13:46:18<8:53:52,  1.71it/s]
Train steps ... :  45%|████▌     | 45093/100000 [13:46:19<8:53:39,  1.71it/s]
Train steps ... :  45%|████▌     | 45094/100000 [13:46:19<8:54:18,  1.71it/s]
Train steps ... :  45%|████▌     | 45095/100000 [13:46:20<8:53:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45096/100000 [13:46:20<8:53:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45097/100000 [13:46:21<8:53:42,  1.71it/s]
Train steps ... :  45%|████▌     | 45098/100000 [13:46:21<8:55:38,  1.71it/s]
Train steps ... :  45%|████▌     | 45099/100000 [13:46:22<8:55:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45100/100000 [13:46:23<8:56:42,  1.70it/s]Step... (45100 / 100000 | Loss: 0.9609776735305786, Learning Rate: 5.517587939698493e-05)
+
                                                                             
Step... (45100 / 100000 | Loss: 0.7668558359146118, Learning Rate: 5.517587939698493e-05)
+
Train steps ... :  45%|████▌     | 45100/100000 [13:46:23<8:56:42,  1.70it/s]
Train steps ... :  45%|████▌     | 45101/100000 [13:46:23<8:55:52,  1.71it/s]
Train steps ... :  45%|████▌     | 45102/100000 [13:46:24<8:54:41,  1.71it/s]
Train steps ... :  45%|████▌     | 45103/100000 [13:46:24<8:54:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45104/100000 [13:46:25<8:54:31,  1.71it/s]
Train steps ... :  45%|████▌     | 45105/100000 [13:46:26<8:53:50,  1.71it/s]
Train steps ... :  45%|████▌     | 45106/100000 [13:46:26<8:54:01,  1.71it/s]
Train steps ... :  45%|████▌     | 45107/100000 [13:46:27<8:54:30,  1.71it/s]
Train steps ... :  45%|████▌     | 45108/100000 [13:46:27<8:55:01,  1.71it/s]
Train steps ... :  45%|████▌     | 45109/100000 [13:46:28<8:54:10,  1.71it/s]
Train steps ... :  45%|████▌     | 45110/100000 [13:46:29<8:54:24,  1.71it/s]
Train steps ... :  45%|████▌     | 45111/100000 [13:46:29<8:54:42,  1.71it/s]
Train steps ... :  45%|████▌     | 45112/100000 [13:46:30<8:54:55,  1.71it/s]
Train steps ... :  45%|████▌     | 45113/100000 [13:46:30<8:54:22,  1.71it/s]
Train steps ... :  45%|████▌     | 45114/100000 [13:46:31<8:54:29,  1.71it/s]
Train steps ... :  45%|████▌     | 45115/100000 [13:46:31<8:54:40,  1.71it/s]
Train steps ... :  45%|████▌     | 45116/100000 [13:46:32<8:54:53,  1.71it/s]
Train steps ... :  45%|████▌     | 45117/100000 [13:46:33<8:55:13,  1.71it/s]
Train steps ... :  45%|████▌     | 45118/100000 [13:46:33<8:54:20,  1.71it/s]
Train steps ... :  45%|████▌     | 45119/100000 [13:46:34<8:54:39,  1.71it/s]
Train steps ... :  45%|████▌     | 45120/100000 [13:46:34<8:54:16,  1.71it/s]
Train steps ... :  45%|████▌     | 45121/100000 [13:46:35<8:54:03,  1.71it/s]
Train steps ... :  45%|████▌     | 45122/100000 [13:46:36<8:54:48,  1.71it/s]
Train steps ... :  45%|████▌     | 45123/100000 [13:46:36<8:53:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45124/100000 [13:46:37<8:54:10,  1.71it/s]
Train steps ... :  45%|████▌     | 45125/100000 [13:46:37<8:54:33,  1.71it/s]Step... (45125 / 100000 | Loss: 0.6328602433204651, Learning Rate: 5.515075376884422e-05)
+
                                                                             
Step... (45125 / 100000 | Loss: 0.7680855989456177, Learning Rate: 5.515075376884422e-05)
+
Train steps ... :  45%|████▌     | 45125/100000 [13:46:38<8:54:33,  1.71it/s]
Train steps ... :  45%|████▌     | 45126/100000 [13:46:38<8:54:08,  1.71it/s]
Train steps ... :  45%|████▌     | 45127/100000 [13:46:38<8:54:25,  1.71it/s]
Train steps ... :  45%|████▌     | 45128/100000 [13:46:39<8:53:41,  1.71it/s]
Train steps ... :  45%|████▌     | 45129/100000 [13:46:40<8:54:07,  1.71it/s]
Train steps ... :  45%|████▌     | 45130/100000 [13:46:40<8:54:12,  1.71it/s]
Train steps ... :  45%|████▌     | 45131/100000 [13:46:41<8:54:35,  1.71it/s]
Train steps ... :  45%|████▌     | 45132/100000 [13:46:41<8:54:42,  1.71it/s]
Train steps ... :  45%|████▌     | 45133/100000 [13:46:42<8:54:40,  1.71it/s]
Train steps ... :  45%|████▌     | 45134/100000 [13:46:43<8:54:14,  1.71it/s]
Train steps ... :  45%|████▌     | 45135/100000 [13:46:43<8:54:06,  1.71it/s]
Train steps ... :  45%|████▌     | 45136/100000 [13:46:44<8:53:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45137/100000 [13:46:44<8:53:59,  1.71it/s]
Train steps ... :  45%|████▌     | 45138/100000 [13:46:45<8:53:53,  1.71it/s]
Train steps ... :  45%|████▌     | 45139/100000 [13:46:45<8:54:09,  1.71it/s]
Train steps ... :  45%|████▌     | 45140/100000 [13:46:46<8:54:02,  1.71it/s]
Train steps ... :  45%|████▌     | 45141/100000 [13:46:47<8:53:52,  1.71it/s]
Train steps ... :  45%|████▌     | 45142/100000 [13:46:47<8:54:35,  1.71it/s]
Train steps ... :  45%|████▌     | 45143/100000 [13:46:48<8:54:14,  1.71it/s]
Train steps ... :  45%|████▌     | 45144/100000 [13:46:48<8:54:47,  1.71it/s]
Train steps ... :  45%|████▌     | 45145/100000 [13:46:49<8:55:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45146/100000 [13:46:50<8:54:51,  1.71it/s]
Train steps ... :  45%|████▌     | 45147/100000 [13:46:50<8:54:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45148/100000 [13:46:51<8:54:34,  1.71it/s]
Train steps ... :  45%|████▌     | 45149/100000 [13:46:51<8:54:41,  1.71it/s]
Train steps ... :  45%|████▌     | 45150/100000 [13:46:52<8:54:25,  1.71it/s]Step... (45150 / 100000 | Loss: 0.710384726524353, Learning Rate: 5.5125628140703526e-05)
+
                                                                             
Step... (45150 / 100000 | Loss: 1.0133476257324219, Learning Rate: 5.5125628140703526e-05)
+
Train steps ... :  45%|████▌     | 45150/100000 [13:46:52<8:54:25,  1.71it/s]
Train steps ... :  45%|████▌     | 45151/100000 [13:46:52<8:54:11,  1.71it/s]
Train steps ... :  45%|████▌     | 45152/100000 [13:46:53<8:54:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45153/100000 [13:46:54<8:54:59,  1.71it/s]
Train steps ... :  45%|████▌     | 45154/100000 [13:46:54<8:54:00,  1.71it/s]
Train steps ... :  45%|████▌     | 45155/100000 [13:46:55<8:53:33,  1.71it/s]
Train steps ... :  45%|████▌     | 45156/100000 [13:46:55<8:54:08,  1.71it/s]
Train steps ... :  45%|████▌     | 45157/100000 [13:46:56<8:53:31,  1.71it/s]
Train steps ... :  45%|████▌     | 45158/100000 [13:46:57<8:53:00,  1.71it/s]
Train steps ... :  45%|████▌     | 45159/100000 [13:46:57<8:53:20,  1.71it/s]
Train steps ... :  45%|████▌     | 45160/100000 [13:46:58<8:53:40,  1.71it/s]
Train steps ... :  45%|████▌     | 45161/100000 [13:46:58<8:52:40,  1.72it/s]
Train steps ... :  45%|████▌     | 45162/100000 [13:46:59<8:53:34,  1.71it/s]
Train steps ... :  45%|████▌     | 45163/100000 [13:46:59<8:53:15,  1.71it/s]
Train steps ... :  45%|████▌     | 45164/100000 [13:47:00<8:53:08,  1.71it/s]
Train steps ... :  45%|████▌     | 45165/100000 [13:47:01<8:53:53,  1.71it/s]
Train steps ... :  45%|████▌     | 45166/100000 [13:47:01<8:53:28,  1.71it/s]
Train steps ... :  45%|████▌     | 45167/100000 [13:47:02<8:53:46,  1.71it/s]
Train steps ... :  45%|████▌     | 45168/100000 [13:47:02<8:53:52,  1.71it/s]
Train steps ... :  45%|████▌     | 45169/100000 [13:47:03<8:53:54,  1.71it/s]
Train steps ... :  45%|████▌     | 45170/100000 [13:47:04<8:53:57,  1.71it/s]
Train steps ... :  45%|████▌     | 45171/100000 [13:47:04<8:54:22,  1.71it/s]
Train steps ... :  45%|████▌     | 45172/100000 [13:47:05<8:53:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45173/100000 [13:47:05<8:55:10,  1.71it/s]
Train steps ... :  45%|████▌     | 45174/100000 [13:47:06<8:55:46,  1.71it/s]
Train steps ... :  45%|████▌     | 45175/100000 [13:47:06<8:55:09,  1.71it/s]Step... (45175 / 100000 | Loss: 0.7911079525947571, Learning Rate: 5.5100502512562815e-05)
+
                                                                             
Step... (45175 / 100000 | Loss: 0.6868945956230164, Learning Rate: 5.5100502512562815e-05)
+
Train steps ... :  45%|████▌     | 45175/100000 [13:47:07<8:55:09,  1.71it/s]
Train steps ... :  45%|████▌     | 45176/100000 [13:47:07<9:05:51,  1.67it/s]
Train steps ... :  45%|████▌     | 45177/100000 [13:47:08<9:02:16,  1.68it/s]
Train steps ... :  45%|████▌     | 45178/100000 [13:47:08<8:59:17,  1.69it/s]
Train steps ... :  45%|████▌     | 45179/100000 [13:47:09<8:57:31,  1.70it/s]
Train steps ... :  45%|████▌     | 45180/100000 [13:47:09<8:55:47,  1.71it/s]
Train steps ... :  45%|████▌     | 45181/100000 [13:47:10<8:54:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45182/100000 [13:47:11<8:54:11,  1.71it/s]
Train steps ... :  45%|████▌     | 45183/100000 [13:47:11<8:54:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45184/100000 [13:47:12<8:54:42,  1.71it/s]
Train steps ... :  45%|████▌     | 45185/100000 [13:47:12<8:54:14,  1.71it/s]
Train steps ... :  45%|████▌     | 45186/100000 [13:47:13<8:53:43,  1.71it/s]
Train steps ... :  45%|████▌     | 45187/100000 [13:47:14<8:53:16,  1.71it/s]
Train steps ... :  45%|████▌     | 45188/100000 [13:47:14<8:53:40,  1.71it/s]
Train steps ... :  45%|████▌     | 45189/100000 [13:47:15<8:53:38,  1.71it/s]
Train steps ... :  45%|████▌     | 45190/100000 [13:47:15<8:53:22,  1.71it/s]
Train steps ... :  45%|████▌     | 45191/100000 [13:47:16<8:53:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45192/100000 [13:47:16<8:53:28,  1.71it/s]
Train steps ... :  45%|████▌     | 45193/100000 [13:47:17<8:53:14,  1.71it/s]
Train steps ... :  45%|████▌     | 45194/100000 [13:47:18<8:52:48,  1.71it/s]
Train steps ... :  45%|████▌     | 45195/100000 [13:47:18<8:53:28,  1.71it/s]
Train steps ... :  45%|████▌     | 45196/100000 [13:47:19<8:53:39,  1.71it/s]
Train steps ... :  45%|████▌     | 45197/100000 [13:47:19<8:53:45,  1.71it/s]
Train steps ... :  45%|████▌     | 45198/100000 [13:47:20<8:53:45,  1.71it/s]
Train steps ... :  45%|████▌     | 45199/100000 [13:47:21<8:53:22,  1.71it/s]
Train steps ... :  45%|████▌     | 45200/100000 [13:47:21<8:54:15,  1.71it/s]Step... (45200 / 100000 | Loss: 0.9910728931427002, Learning Rate: 5.507537688442211e-05)
+
                                                                             
Step... (45200 / 100000 | Loss: 0.8570641279220581, Learning Rate: 5.507537688442211e-05)
+
Train steps ... :  45%|████▌     | 45200/100000 [13:47:21<8:54:15,  1.71it/s]
Train steps ... :  45%|████▌     | 45201/100000 [13:47:22<8:53:52,  1.71it/s]
Train steps ... :  45%|████▌     | 45202/100000 [13:47:22<8:53:22,  1.71it/s]
Train steps ... :  45%|████▌     | 45203/100000 [13:47:23<8:53:32,  1.71it/s]
Train steps ... :  45%|████▌     | 45204/100000 [13:47:23<8:53:33,  1.71it/s]
Train steps ... :  45%|████▌     | 45205/100000 [13:47:24<8:53:27,  1.71it/s]
Train steps ... :  45%|████▌     | 45206/100000 [13:47:25<8:54:14,  1.71it/s]
Train steps ... :  45%|████▌     | 45207/100000 [13:47:25<8:53:52,  1.71it/s]
Train steps ... :  45%|████▌     | 45208/100000 [13:47:26<8:53:14,  1.71it/s]
Train steps ... :  45%|████▌     | 45209/100000 [13:47:26<8:53:31,  1.71it/s]
Train steps ... :  45%|████▌     | 45210/100000 [13:47:27<8:53:47,  1.71it/s]
Train steps ... :  45%|████▌     | 45211/100000 [13:47:28<8:53:36,  1.71it/s]
Train steps ... :  45%|████▌     | 45212/100000 [13:47:28<8:53:37,  1.71it/s]
Train steps ... :  45%|████▌     | 45213/100000 [13:47:29<8:53:49,  1.71it/s]
Train steps ... :  45%|████▌     | 45214/100000 [13:47:29<8:52:51,  1.71it/s]
Train steps ... :  45%|████▌     | 45215/100000 [13:47:30<8:52:45,  1.71it/s]
Train steps ... :  45%|████▌     | 45216/100000 [13:47:30<8:52:18,  1.72it/s]
Train steps ... :  45%|████▌     | 45217/100000 [13:47:31<8:53:06,  1.71it/s]
Train steps ... :  45%|████▌     | 45218/100000 [13:47:32<8:52:38,  1.71it/s]
Train steps ... :  45%|████▌     | 45219/100000 [13:47:32<8:52:28,  1.71it/s]
Train steps ... :  45%|████▌     | 45220/100000 [13:47:33<8:52:17,  1.72it/s]
Train steps ... :  45%|████▌     | 45221/100000 [13:47:33<8:52:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45222/100000 [13:47:34<8:52:28,  1.71it/s]
Train steps ... :  45%|████▌     | 45223/100000 [13:47:35<8:52:33,  1.71it/s]
Train steps ... :  45%|████▌     | 45224/100000 [13:47:35<8:52:37,  1.71it/s]
Train steps ... :  45%|████▌     | 45225/100000 [13:47:36<8:53:01,  1.71it/s]Step... (45225 / 100000 | Loss: 0.991304337978363, Learning Rate: 5.50502512562814e-05)
+
                                                                             
Step... (45225 / 100000 | Loss: 0.7592988014221191, Learning Rate: 5.50502512562814e-05)
+
Train steps ... :  45%|████▌     | 45225/100000 [13:47:36<8:53:01,  1.71it/s]
Train steps ... :  45%|████▌     | 45226/100000 [13:47:36<8:52:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45227/100000 [13:47:37<8:52:38,  1.71it/s]
Train steps ... :  45%|████▌     | 45228/100000 [13:47:37<8:53:07,  1.71it/s]
Train steps ... :  45%|████▌     | 45229/100000 [13:47:38<8:53:14,  1.71it/s]
Train steps ... :  45%|████▌     | 45230/100000 [13:47:39<8:53:01,  1.71it/s]
Train steps ... :  45%|████▌     | 45231/100000 [13:47:39<8:53:22,  1.71it/s]
Train steps ... :  45%|████▌     | 45232/100000 [13:47:40<8:53:40,  1.71it/s]
Train steps ... :  45%|████▌     | 45233/100000 [13:47:40<8:54:00,  1.71it/s]
Train steps ... :  45%|████▌     | 45234/100000 [13:47:41<8:53:36,  1.71it/s]
Train steps ... :  45%|████▌     | 45235/100000 [13:47:42<8:54:53,  1.71it/s]
Train steps ... :  45%|████▌     | 45236/100000 [13:47:42<8:54:33,  1.71it/s]
Train steps ... :  45%|████▌     | 45237/100000 [13:47:43<8:54:54,  1.71it/s]
Train steps ... :  45%|████▌     | 45238/100000 [13:47:43<8:55:31,  1.70it/s]
Train steps ... :  45%|████▌     | 45239/100000 [13:47:44<8:55:16,  1.71it/s]
Train steps ... :  45%|████▌     | 45240/100000 [13:47:45<8:55:16,  1.71it/s]
Train steps ... :  45%|████▌     | 45241/100000 [13:47:45<8:54:37,  1.71it/s]
Train steps ... :  45%|████▌     | 45242/100000 [13:47:46<8:53:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45243/100000 [13:47:46<8:53:47,  1.71it/s]
Train steps ... :  45%|████▌     | 45244/100000 [13:47:47<8:54:09,  1.71it/s]
Train steps ... :  45%|████▌     | 45245/100000 [13:47:47<8:53:54,  1.71it/s]
Train steps ... :  45%|████▌     | 45246/100000 [13:47:48<8:53:53,  1.71it/s]
Train steps ... :  45%|████▌     | 45247/100000 [13:47:49<8:53:47,  1.71it/s]
Train steps ... :  45%|████▌     | 45248/100000 [13:47:49<8:52:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45249/100000 [13:47:50<8:53:51,  1.71it/s]
Train steps ... :  45%|████▌     | 45250/100000 [13:47:50<8:54:28,  1.71it/s]Step... (45250 / 100000 | Loss: 1.1132992506027222, Learning Rate: 5.5025125628140705e-05)
+
                                                                             
Step... (45250 / 100000 | Loss: 1.064091444015503, Learning Rate: 5.5025125628140705e-05)
+
Train steps ... :  45%|████▌     | 45250/100000 [13:47:51<8:54:28,  1.71it/s]
Train steps ... :  45%|████▌     | 45251/100000 [13:47:51<8:54:34,  1.71it/s]
Train steps ... :  45%|████▌     | 45252/100000 [13:47:52<8:55:55,  1.70it/s]
Train steps ... :  45%|████▌     | 45253/100000 [13:47:52<8:55:05,  1.71it/s]
Train steps ... :  45%|████▌     | 45254/100000 [13:47:53<8:55:35,  1.70it/s]
Train steps ... :  45%|████▌     | 45255/100000 [13:47:53<8:55:45,  1.70it/s]
Train steps ... :  45%|████▌     | 45256/100000 [13:47:54<8:55:18,  1.70it/s]
Train steps ... :  45%|████▌     | 45257/100000 [13:47:54<8:55:09,  1.70it/s]
Train steps ... :  45%|████▌     | 45258/100000 [13:47:55<8:54:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45259/100000 [13:47:56<8:54:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45260/100000 [13:47:56<8:53:51,  1.71it/s]
Train steps ... :  45%|████▌     | 45261/100000 [13:47:57<8:53:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45262/100000 [13:47:57<8:53:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45263/100000 [13:47:58<8:53:39,  1.71it/s]
Train steps ... :  45%|████▌     | 45264/100000 [13:47:59<8:53:48,  1.71it/s]
Train steps ... :  45%|████▌     | 45265/100000 [13:47:59<8:53:28,  1.71it/s]
Train steps ... :  45%|████▌     | 45266/100000 [13:48:00<8:53:06,  1.71it/s]
Train steps ... :  45%|████▌     | 45267/100000 [13:48:00<8:53:29,  1.71it/s]
Train steps ... :  45%|████▌     | 45268/100000 [13:48:01<8:54:24,  1.71it/s]
Train steps ... :  45%|████▌     | 45269/100000 [13:48:01<8:54:09,  1.71it/s]
Train steps ... :  45%|████▌     | 45270/100000 [13:48:02<8:53:54,  1.71it/s]
Train steps ... :  45%|████▌     | 45271/100000 [13:48:03<8:53:04,  1.71it/s]
Train steps ... :  45%|████▌     | 45272/100000 [13:48:03<8:54:13,  1.71it/s]
Train steps ... :  45%|████▌     | 45273/100000 [13:48:04<8:53:40,  1.71it/s]
Train steps ... :  45%|████▌     | 45274/100000 [13:48:04<8:52:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45275/100000 [13:48:05<8:53:06,  1.71it/s]Step... (45275 / 100000 | Loss: 1.1032578945159912, Learning Rate: 5.500000000000001e-05)
+
                                                                             
Step... (45275 / 100000 | Loss: 0.6691926717758179, Learning Rate: 5.500000000000001e-05)
+
Train steps ... :  45%|████▌     | 45275/100000 [13:48:05<8:53:06,  1.71it/s]
Train steps ... :  45%|████▌     | 45276/100000 [13:48:06<8:53:19,  1.71it/s]
Train steps ... :  45%|████▌     | 45277/100000 [13:48:06<8:53:47,  1.71it/s]
Train steps ... :  45%|████▌     | 45278/100000 [13:48:07<8:53:06,  1.71it/s]
Train steps ... :  45%|████▌     | 45279/100000 [13:48:07<8:52:36,  1.71it/s]
Train steps ... :  45%|████▌     | 45280/100000 [13:48:08<8:53:17,  1.71it/s]
Train steps ... :  45%|████▌     | 45281/100000 [13:48:09<8:52:46,  1.71it/s]
Train steps ... :  45%|████▌     | 45282/100000 [13:48:09<8:53:21,  1.71it/s]
Train steps ... :  45%|████▌     | 45283/100000 [13:48:10<8:53:45,  1.71it/s]
Train steps ... :  45%|████▌     | 45284/100000 [13:48:10<8:53:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45285/100000 [13:48:11<8:53:23,  1.71it/s]
Train steps ... :  45%|████▌     | 45286/100000 [13:48:11<8:52:55,  1.71it/s]
Train steps ... :  45%|████▌     | 45287/100000 [13:48:12<8:52:27,  1.71it/s]
Train steps ... :  45%|████▌     | 45288/100000 [13:48:13<8:52:55,  1.71it/s]
Train steps ... :  45%|████▌     | 45289/100000 [13:48:13<8:52:28,  1.71it/s]
Train steps ... :  45%|████▌     | 45290/100000 [13:48:14<8:52:20,  1.71it/s]
Train steps ... :  45%|████▌     | 45291/100000 [13:48:14<8:52:57,  1.71it/s]
Train steps ... :  45%|████▌     | 45292/100000 [13:48:15<8:53:04,  1.71it/s]
Train steps ... :  45%|████▌     | 45293/100000 [13:48:16<8:52:34,  1.71it/s]
Train steps ... :  45%|████▌     | 45294/100000 [13:48:16<8:52:19,  1.71it/s]
Train steps ... :  45%|████▌     | 45295/100000 [13:48:17<8:52:03,  1.71it/s]
Train steps ... :  45%|████▌     | 45296/100000 [13:48:17<8:51:54,  1.71it/s]
Train steps ... :  45%|████▌     | 45297/100000 [13:48:18<8:51:50,  1.71it/s]
Train steps ... :  45%|████▌     | 45298/100000 [13:48:18<8:51:39,  1.71it/s]
Train steps ... :  45%|████▌     | 45299/100000 [13:48:19<8:52:25,  1.71it/s]
Train steps ... :  45%|████▌     | 45300/100000 [13:48:20<8:52:47,  1.71it/s]Step... (45300 / 100000 | Loss: 0.9245506525039673, Learning Rate: 5.49748743718593e-05)
+
                                                                             
Step... (45300 / 100000 | Loss: 0.5940679907798767, Learning Rate: 5.49748743718593e-05)
+
Train steps ... :  45%|████▌     | 45300/100000 [13:48:20<8:52:47,  1.71it/s]
Train steps ... :  45%|████▌     | 45301/100000 [13:48:20<8:53:52,  1.71it/s]
Train steps ... :  45%|████▌     | 45302/100000 [13:48:21<8:53:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45303/100000 [13:48:21<8:53:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45304/100000 [13:48:22<8:52:49,  1.71it/s]
Train steps ... :  45%|████▌     | 45305/100000 [13:48:23<8:52:52,  1.71it/s]
Train steps ... :  45%|████▌     | 45306/100000 [13:48:23<8:53:16,  1.71it/s]
Train steps ... :  45%|████▌     | 45307/100000 [13:48:24<8:52:46,  1.71it/s]
Train steps ... :  45%|████▌     | 45308/100000 [13:48:24<8:53:06,  1.71it/s]
Train steps ... :  45%|████▌     | 45309/100000 [13:48:25<8:52:53,  1.71it/s]
Train steps ... :  45%|████▌     | 45310/100000 [13:48:25<8:52:49,  1.71it/s]
Train steps ... :  45%|████▌     | 45311/100000 [13:48:26<8:52:17,  1.71it/s]
Train steps ... :  45%|████▌     | 45312/100000 [13:48:27<8:52:39,  1.71it/s]
Train steps ... :  45%|████▌     | 45313/100000 [13:48:27<8:52:23,  1.71it/s]
Train steps ... :  45%|████▌     | 45314/100000 [13:48:28<8:53:48,  1.71it/s]
Train steps ... :  45%|████▌     | 45315/100000 [13:48:28<8:53:01,  1.71it/s]
Train steps ... :  45%|████▌     | 45316/100000 [13:48:29<8:53:17,  1.71it/s]
Train steps ... :  45%|████▌     | 45317/100000 [13:48:30<8:53:38,  1.71it/s]
Train steps ... :  45%|████▌     | 45318/100000 [13:48:30<8:53:10,  1.71it/s]
Train steps ... :  45%|████▌     | 45319/100000 [13:48:31<8:52:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45320/100000 [13:48:31<8:53:06,  1.71it/s]
Train steps ... :  45%|████▌     | 45321/100000 [13:48:32<8:52:33,  1.71it/s]
Train steps ... :  45%|████▌     | 45322/100000 [13:48:32<8:52:20,  1.71it/s]
Train steps ... :  45%|████▌     | 45323/100000 [13:48:33<8:52:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45324/100000 [13:48:34<8:53:10,  1.71it/s]
Train steps ... :  45%|████▌     | 45325/100000 [13:48:34<8:53:35,  1.71it/s]Step... (45325 / 100000 | Loss: 0.6305262446403503, Learning Rate: 5.49497487437186e-05)
+
                                                                             
Step... (45325 / 100000 | Loss: 0.7420768737792969, Learning Rate: 5.49497487437186e-05)
+
Train steps ... :  45%|████▌     | 45325/100000 [13:48:35<8:53:35,  1.71it/s]
Train steps ... :  45%|████▌     | 45326/100000 [13:48:35<8:53:05,  1.71it/s]
Train steps ... :  45%|████▌     | 45327/100000 [13:48:35<8:52:29,  1.71it/s]
Train steps ... :  45%|████▌     | 45328/100000 [13:48:36<8:52:20,  1.71it/s]
Train steps ... :  45%|████▌     | 45329/100000 [13:48:37<8:52:27,  1.71it/s]
Train steps ... :  45%|████▌     | 45330/100000 [13:48:37<8:52:41,  1.71it/s]
Train steps ... :  45%|████▌     | 45331/100000 [13:48:38<8:52:12,  1.71it/s]
Train steps ... :  45%|████▌     | 45332/100000 [13:48:38<8:52:31,  1.71it/s]
Train steps ... :  45%|████▌     | 45333/100000 [13:48:39<8:51:49,  1.71it/s]
Train steps ... :  45%|████▌     | 45334/100000 [13:48:39<8:51:29,  1.71it/s]
Train steps ... :  45%|████▌     | 45335/100000 [13:48:40<8:51:25,  1.71it/s]
Train steps ... :  45%|████▌     | 45336/100000 [13:48:41<8:51:09,  1.72it/s]
Train steps ... :  45%|████▌     | 45337/100000 [13:48:41<8:51:48,  1.71it/s]
Train steps ... :  45%|████▌     | 45338/100000 [13:48:42<8:52:29,  1.71it/s]
Train steps ... :  45%|████▌     | 45339/100000 [13:48:42<8:52:39,  1.71it/s]
Train steps ... :  45%|████▌     | 45340/100000 [13:48:43<8:52:10,  1.71it/s]
Train steps ... :  45%|████▌     | 45341/100000 [13:48:44<8:52:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45342/100000 [13:48:44<8:52:05,  1.71it/s]
Train steps ... :  45%|████▌     | 45343/100000 [13:48:45<8:51:30,  1.71it/s]
Train steps ... :  45%|████▌     | 45344/100000 [13:48:45<8:51:41,  1.71it/s]
Train steps ... :  45%|████▌     | 45345/100000 [13:48:46<8:51:24,  1.71it/s]
Train steps ... :  45%|████▌     | 45346/100000 [13:48:46<8:51:40,  1.71it/s]
Train steps ... :  45%|████▌     | 45347/100000 [13:48:47<8:51:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45348/100000 [13:48:48<8:51:49,  1.71it/s]
Train steps ... :  45%|████▌     | 45349/100000 [13:48:48<8:52:01,  1.71it/s]
Train steps ... :  45%|████▌     | 45350/100000 [13:48:49<8:51:31,  1.71it/s]Step... (45350 / 100000 | Loss: 0.6594018936157227, Learning Rate: 5.492462311557789e-05)
+
                                                                             
Step... (45350 / 100000 | Loss: 0.680345356464386, Learning Rate: 5.492462311557789e-05)
+
Train steps ... :  45%|████▌     | 45350/100000 [13:48:49<8:51:31,  1.71it/s]
Train steps ... :  45%|████▌     | 45351/100000 [13:48:49<8:51:38,  1.71it/s]
Train steps ... :  45%|████▌     | 45352/100000 [13:48:50<8:51:53,  1.71it/s]
Train steps ... :  45%|████▌     | 45353/100000 [13:48:51<8:53:24,  1.71it/s]
Train steps ... :  45%|████▌     | 45354/100000 [13:48:51<8:52:41,  1.71it/s]
Train steps ... :  45%|████▌     | 45355/100000 [13:48:52<8:52:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45356/100000 [13:48:52<8:52:19,  1.71it/s]
Train steps ... :  45%|████▌     | 45357/100000 [13:48:53<8:52:19,  1.71it/s]
Train steps ... :  45%|████▌     | 45358/100000 [13:48:53<8:51:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45359/100000 [13:48:54<8:52:37,  1.71it/s]
Train steps ... :  45%|████▌     | 45360/100000 [13:48:55<8:52:15,  1.71it/s]
Train steps ... :  45%|████▌     | 45361/100000 [13:48:55<8:51:52,  1.71it/s]
Train steps ... :  45%|████▌     | 45362/100000 [13:48:56<8:51:30,  1.71it/s]
Train steps ... :  45%|████▌     | 45363/100000 [13:48:56<8:51:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45364/100000 [13:48:57<8:51:29,  1.71it/s]
Train steps ... :  45%|████▌     | 45365/100000 [13:48:58<8:51:35,  1.71it/s]
Train steps ... :  45%|████▌     | 45366/100000 [13:48:58<8:51:49,  1.71it/s]
Train steps ... :  45%|████▌     | 45367/100000 [13:48:59<8:52:49,  1.71it/s]
Train steps ... :  45%|████▌     | 45368/100000 [13:48:59<8:52:22,  1.71it/s]
Train steps ... :  45%|████▌     | 45369/100000 [13:49:00<8:52:23,  1.71it/s]
Train steps ... :  45%|████▌     | 45370/100000 [13:49:01<8:52:19,  1.71it/s]
Train steps ... :  45%|████▌     | 45371/100000 [13:49:01<8:52:12,  1.71it/s]
Train steps ... :  45%|████▌     | 45372/100000 [13:49:02<8:51:49,  1.71it/s]
Train steps ... :  45%|████▌     | 45373/100000 [13:49:02<8:51:22,  1.71it/s]
Train steps ... :  45%|████▌     | 45374/100000 [13:49:03<8:51:57,  1.71it/s]
Train steps ... :  45%|████▌     | 45375/100000 [13:49:03<8:51:15,  1.71it/s]Step... (45375 / 100000 | Loss: 0.7571024298667908, Learning Rate: 5.489949748743719e-05)
+
                                                                             
Step... (45375 / 100000 | Loss: 0.7081456184387207, Learning Rate: 5.489949748743719e-05)
+
Train steps ... :  45%|████▌     | 45375/100000 [13:49:04<8:51:15,  1.71it/s]
Train steps ... :  45%|████▌     | 45376/100000 [13:49:04<8:52:06,  1.71it/s]
Train steps ... :  45%|████▌     | 45377/100000 [13:49:05<8:51:39,  1.71it/s]
Train steps ... :  45%|████▌     | 45378/100000 [13:49:05<8:52:04,  1.71it/s]
Train steps ... :  45%|████▌     | 45379/100000 [13:49:06<8:51:51,  1.71it/s]
Train steps ... :  45%|████▌     | 45380/100000 [13:49:06<8:51:30,  1.71it/s]
Train steps ... :  45%|████▌     | 45381/100000 [13:49:07<8:51:19,  1.71it/s]
Train steps ... :  45%|████▌     | 45382/100000 [13:49:08<8:51:20,  1.71it/s]
Train steps ... :  45%|████▌     | 45383/100000 [13:49:08<8:51:16,  1.71it/s]
Train steps ... :  45%|████▌     | 45384/100000 [13:49:09<8:51:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45385/100000 [13:49:09<8:51:29,  1.71it/s]
Train steps ... :  45%|████▌     | 45386/100000 [13:49:10<8:51:33,  1.71it/s]
Train steps ... :  45%|████▌     | 45387/100000 [13:49:10<8:51:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45388/100000 [13:49:11<8:51:15,  1.71it/s]
Train steps ... :  45%|████▌     | 45389/100000 [13:49:12<8:51:12,  1.71it/s]
Train steps ... :  45%|████▌     | 45390/100000 [13:49:12<8:50:36,  1.72it/s]
Train steps ... :  45%|████▌     | 45391/100000 [13:49:13<8:50:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45392/100000 [13:49:13<8:51:24,  1.71it/s]
Train steps ... :  45%|████▌     | 45393/100000 [13:49:14<8:51:45,  1.71it/s]
Train steps ... :  45%|████▌     | 45394/100000 [13:49:15<8:51:34,  1.71it/s]
Train steps ... :  45%|████▌     | 45395/100000 [13:49:15<8:51:41,  1.71it/s]
Train steps ... :  45%|████▌     | 45396/100000 [13:49:16<8:52:03,  1.71it/s]
Train steps ... :  45%|████▌     | 45397/100000 [13:49:16<8:51:54,  1.71it/s]
Train steps ... :  45%|████▌     | 45398/100000 [13:49:17<8:51:07,  1.71it/s]
Train steps ... :  45%|████▌     | 45399/100000 [13:49:17<8:51:08,  1.71it/s]
Train steps ... :  45%|████▌     | 45400/100000 [13:49:18<8:50:56,  1.71it/s]Step... (45400 / 100000 | Loss: 0.8153809905052185, Learning Rate: 5.487437185929648e-05)
+
                                                                             
Step... (45400 / 100000 | Loss: 0.7117670774459839, Learning Rate: 5.487437185929648e-05)
+
Train steps ... :  45%|████▌     | 45400/100000 [13:49:18<8:50:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45401/100000 [13:49:19<8:51:05,  1.71it/s]
Train steps ... :  45%|████▌     | 45402/100000 [13:49:19<8:51:20,  1.71it/s]
Train steps ... :  45%|████▌     | 45403/100000 [13:49:20<8:50:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45404/100000 [13:49:20<8:51:42,  1.71it/s]
Train steps ... :  45%|████▌     | 45405/100000 [13:49:21<8:51:09,  1.71it/s]
Train steps ... :  45%|████▌     | 45406/100000 [13:49:22<8:51:01,  1.71it/s]
Train steps ... :  45%|████▌     | 45407/100000 [13:49:22<8:51:10,  1.71it/s]
Train steps ... :  45%|████▌     | 45408/100000 [13:49:23<8:51:28,  1.71it/s]
Train steps ... :  45%|████▌     | 45409/100000 [13:49:23<8:50:30,  1.72it/s]
Train steps ... :  45%|████▌     | 45410/100000 [13:49:24<8:50:39,  1.71it/s]
Train steps ... :  45%|████▌     | 45411/100000 [13:49:24<8:51:06,  1.71it/s]
Train steps ... :  45%|████▌     | 45412/100000 [13:49:25<8:51:11,  1.71it/s]
Train steps ... :  45%|████▌     | 45413/100000 [13:49:26<8:51:47,  1.71it/s]
Train steps ... :  45%|████▌     | 45414/100000 [13:49:26<8:51:53,  1.71it/s]
Train steps ... :  45%|████▌     | 45415/100000 [13:49:27<8:51:14,  1.71it/s]
Train steps ... :  45%|████▌     | 45416/100000 [13:49:27<8:51:33,  1.71it/s]
Train steps ... :  45%|████▌     | 45417/100000 [13:49:28<8:51:21,  1.71it/s]
Train steps ... :  45%|████▌     | 45418/100000 [13:49:29<8:51:13,  1.71it/s]
Train steps ... :  45%|████▌     | 45419/100000 [13:49:29<8:50:32,  1.71it/s]
Train steps ... :  45%|████▌     | 45420/100000 [13:49:30<8:50:31,  1.71it/s]
Train steps ... :  45%|████▌     | 45421/100000 [13:49:30<8:50:50,  1.71it/s]
Train steps ... :  45%|████▌     | 45422/100000 [13:49:31<8:50:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45423/100000 [13:49:31<8:50:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45424/100000 [13:49:32<8:51:11,  1.71it/s]
Train steps ... :  45%|████▌     | 45425/100000 [13:49:33<8:51:02,  1.71it/s]Step... (45425 / 100000 | Loss: 0.6266739964485168, Learning Rate: 5.484924623115578e-05)
+
                                                                             
Step... (45425 / 100000 | Loss: 0.6584034562110901, Learning Rate: 5.484924623115578e-05)
+
Train steps ... :  45%|████▌     | 45425/100000 [13:49:33<8:51:02,  1.71it/s]
Train steps ... :  45%|████▌     | 45426/100000 [13:49:33<8:51:21,  1.71it/s]
Train steps ... :  45%|████▌     | 45427/100000 [13:49:34<8:50:59,  1.71it/s]
Train steps ... :  45%|████▌     | 45428/100000 [13:49:34<8:50:49,  1.71it/s]
Train steps ... :  45%|████▌     | 45429/100000 [13:49:35<8:50:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45430/100000 [13:49:36<8:50:34,  1.71it/s]
Train steps ... :  45%|████▌     | 45431/100000 [13:49:36<8:51:14,  1.71it/s]
Train steps ... :  45%|████▌     | 45432/100000 [13:49:37<8:50:45,  1.71it/s]
Train steps ... :  45%|���███▌     | 45433/100000 [13:49:37<8:50:42,  1.71it/s]
Train steps ... :  45%|████▌     | 45434/100000 [13:49:38<8:50:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45435/100000 [13:49:38<8:50:09,  1.72it/s]
Train steps ... :  45%|████▌     | 45436/100000 [13:49:39<8:50:19,  1.71it/s]
Train steps ... :  45%|████▌     | 45437/100000 [13:49:40<8:50:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45438/100000 [13:49:40<8:50:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45439/100000 [13:49:41<8:50:43,  1.71it/s]
Train steps ... :  45%|████▌     | 45440/100000 [13:49:41<8:50:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45441/100000 [13:49:42<8:50:58,  1.71it/s]
Train steps ... :  45%|████▌     | 45442/100000 [13:49:43<8:50:55,  1.71it/s]
Train steps ... :  45%|████▌     | 45443/100000 [13:49:43<8:50:34,  1.71it/s]
Train steps ... :  45%|████▌     | 45444/100000 [13:49:44<8:51:11,  1.71it/s]
Train steps ... :  45%|████▌     | 45445/100000 [13:49:44<8:51:44,  1.71it/s]
Train steps ... :  45%|████▌     | 45446/100000 [13:49:45<8:50:48,  1.71it/s]
Train steps ... :  45%|████▌     | 45447/100000 [13:49:45<8:50:31,  1.71it/s]
Train steps ... :  45%|████▌     | 45448/100000 [13:49:46<8:51:19,  1.71it/s]
Train steps ... :  45%|████▌     | 45449/100000 [13:49:47<8:51:07,  1.71it/s]
Train steps ... :  45%|████▌     | 45450/100000 [13:49:47<8:50:25,  1.71it/s]Step... (45450 / 100000 | Loss: 0.903544545173645, Learning Rate: 5.4824120603015085e-05)
+
                                                                             
Step... (45450 / 100000 | Loss: 0.9710702896118164, Learning Rate: 5.4824120603015085e-05)
+
Train steps ... :  45%|████▌     | 45450/100000 [13:49:48<8:50:25,  1.71it/s]
Train steps ... :  45%|████▌     | 45451/100000 [13:49:48<8:50:30,  1.71it/s]
Train steps ... :  45%|████▌     | 45452/100000 [13:49:48<8:51:25,  1.71it/s]
Train steps ... :  45%|████▌     | 45453/100000 [13:49:49<8:51:30,  1.71it/s]
Train steps ... :  45%|████▌     | 45454/100000 [13:49:50<8:52:08,  1.71it/s]
Train steps ... :  45%|████▌     | 45455/100000 [13:49:50<8:51:16,  1.71it/s]
Train steps ... :  45%|████▌     | 45456/100000 [13:49:51<8:51:15,  1.71it/s]
Train steps ... :  45%|████▌     | 45457/100000 [13:49:51<8:50:47,  1.71it/s]
Train steps ... :  45%|████▌     | 45458/100000 [13:49:52<8:50:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45459/100000 [13:49:52<8:50:16,  1.71it/s]
Train steps ... :  45%|████▌     | 45460/100000 [13:49:53<8:50:26,  1.71it/s]
Train steps ... :  45%|████▌     | 45461/100000 [13:49:54<8:50:31,  1.71it/s]
Train steps ... :  45%|████▌     | 45462/100000 [13:49:54<8:51:06,  1.71it/s]
Train steps ... :  45%|████▌     | 45463/100000 [13:49:55<8:50:49,  1.71it/s]
Train steps ... :  45%|████▌     | 45464/100000 [13:49:55<8:52:08,  1.71it/s]
Train steps ... :  45%|████▌     | 45465/100000 [13:49:56<8:50:52,  1.71it/s]
Train steps ... :  45%|████▌     | 45466/100000 [13:49:57<8:50:56,  1.71it/s]
Train steps ... :  45%|████▌     | 45467/100000 [13:49:57<8:51:31,  1.71it/s]
Train steps ... :  45%|████▌     | 45468/100000 [13:49:58<8:51:32,  1.71it/s]
Train steps ... :  45%|████▌     | 45469/100000 [13:49:58<8:51:35,  1.71it/s]
Train steps ... :  45%|████▌     | 45470/100000 [13:49:59<8:51:07,  1.71it/s]
Train steps ... :  45%|████▌     | 45471/100000 [13:49:59<8:50:37,  1.71it/s]
Train steps ... :  45%|████▌     | 45472/100000 [13:50:00<8:50:27,  1.71it/s]
Train steps ... :  45%|████▌     | 45473/100000 [13:50:01<8:50:27,  1.71it/s]
Train steps ... :  45%|████▌     | 45474/100000 [13:50:01<8:50:35,  1.71it/s]
Train steps ... :  45%|████▌     | 45475/100000 [13:50:02<8:50:21,  1.71it/s]Step... (45475 / 100000 | Loss: 1.1424251794815063, Learning Rate: 5.4798994974874375e-05)
+
                                                                             
Step... (45475 / 100000 | Loss: 1.1360896825790405, Learning Rate: 5.4798994974874375e-05)
+
Train steps ... :  45%|████▌     | 45475/100000 [13:50:02<8:50:21,  1.71it/s]
Train steps ... :  45%|████▌     | 45476/100000 [13:50:02<8:51:38,  1.71it/s]
Train steps ... :  45%|████▌     | 45477/100000 [13:50:03<8:51:38,  1.71it/s]
Train steps ... :  45%|████▌     | 45478/100000 [13:50:04<8:51:30,  1.71it/s]
Train steps ... :  45%|████▌     | 45479/100000 [13:50:04<8:50:52,  1.71it/s]
Train steps ... :  45%|████▌     | 45480/100000 [13:50:05<8:50:34,  1.71it/s]
Train steps ... :  45%|████▌     | 45481/100000 [13:50:05<8:50:52,  1.71it/s]
Train steps ... :  45%|████▌     | 45482/100000 [13:50:06<8:51:13,  1.71it/s]
Train steps ... :  45%|████▌     | 45483/100000 [13:50:06<8:50:50,  1.71it/s]
Train steps ... :  45%|████▌     | 45484/100000 [13:50:07<8:50:29,  1.71it/s]
Train steps ... :  45%|████▌     | 45485/100000 [13:50:08<8:50:33,  1.71it/s]
Train steps ... :  45%|████▌     | 45486/100000 [13:50:08<8:50:42,  1.71it/s]
Train steps ... :  45%|████▌     | 45487/100000 [13:50:09<8:51:35,  1.71it/s]
Train steps ... :  45%|████▌     | 45488/100000 [13:50:09<8:51:18,  1.71it/s]
Train steps ... :  45%|████▌     | 45489/100000 [13:50:10<8:51:08,  1.71it/s]
Train steps ... :  45%|████▌     | 45490/100000 [13:50:11<8:52:00,  1.71it/s]
Train steps ... :  45%|████▌     | 45491/100000 [13:50:11<8:51:11,  1.71it/s]
Train steps ... :  45%|████▌     | 45492/100000 [13:50:12<8:51:08,  1.71it/s]
Train steps ... :  45%|████▌     | 45493/100000 [13:50:12<8:51:07,  1.71it/s]
Train steps ... :  45%|████▌     | 45494/100000 [13:50:13<8:51:53,  1.71it/s]
Train steps ... :  45%|████▌     | 45495/100000 [13:50:14<8:51:05,  1.71it/s]
Train steps ... :  45%|████▌     | 45496/100000 [13:50:14<8:50:40,  1.71it/s]
Train steps ... :  45%|████▌     | 45497/100000 [13:50:15<8:50:36,  1.71it/s]
Train steps ... :  45%|████▌     | 45498/100000 [13:50:15<8:51:00,  1.71it/s]
Train steps ... :  45%|████▌     | 45499/100000 [13:50:16<8:50:58,  1.71it/s]
Train steps ... :  46%|████▌     | 45500/100000 [13:50:16<8:51:13,  1.71it/s]Step... (45500 / 100000 | Loss: 0.9597792029380798, Learning Rate: 5.477386934673368e-05)
+
                                                                             
Step... (45500 / 100000 | Loss: 0.7170549631118774, Learning Rate: 5.477386934673368e-05)
+
Train steps ... :  46%|████▌     | 45500/100000 [13:50:17<8:51:13,  1.71it/s]
Train steps ... :  46%|████▌     | 45501/100000 [13:50:17<8:51:37,  1.71it/s]
Train steps ... :  46%|████▌     | 45502/100000 [13:50:18<8:51:04,  1.71it/s]
Train steps ... :  46%|████▌     | 45503/100000 [13:50:18<8:50:32,  1.71it/s]
Train steps ... :  46%|████▌     | 45504/100000 [13:50:19<8:50:08,  1.71it/s]
Train steps ... :  46%|████▌     | 45505/100000 [13:50:19<8:50:24,  1.71it/s]
Train steps ... :  46%|████▌     | 45506/100000 [13:50:20<8:50:55,  1.71it/s]
Train steps ... :  46%|████▌     | 45507/100000 [13:50:21<8:51:33,  1.71it/s]
Train steps ... :  46%|████▌     | 45508/100000 [13:50:21<8:50:57,  1.71it/s]
Train steps ... :  46%|████▌     | 45509/100000 [13:50:22<8:50:27,  1.71it/s]
Train steps ... :  46%|████▌     | 45510/100000 [13:50:22<8:50:40,  1.71it/s]
Train steps ... :  46%|████▌     | 45511/100000 [13:50:23<8:50:35,  1.71it/s]
Train steps ... :  46%|████▌     | 45512/100000 [13:50:23<8:50:27,  1.71it/s]
Train steps ... :  46%|████▌     | 45513/100000 [13:50:24<8:50:07,  1.71it/s]
Train steps ... :  46%|████▌     | 45514/100000 [13:50:25<8:50:27,  1.71it/s]
Train steps ... :  46%|████▌     | 45515/100000 [13:50:25<8:50:13,  1.71it/s]
Train steps ... :  46%|████▌     | 45516/100000 [13:50:26<8:50:28,  1.71it/s]
Train steps ... :  46%|████▌     | 45517/100000 [13:50:26<8:50:23,  1.71it/s]
Train steps ... :  46%|████▌     | 45518/100000 [13:50:27<8:49:58,  1.71it/s]
Train steps ... :  46%|████▌     | 45519/100000 [13:50:28<8:49:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45520/100000 [13:50:28<8:49:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45521/100000 [13:50:29<8:49:40,  1.71it/s]
Train steps ... :  46%|████▌     | 45522/100000 [13:50:29<8:49:23,  1.72it/s]
Train steps ... :  46%|████▌     | 45523/100000 [13:50:30<8:49:25,  1.71it/s]
Train steps ... :  46%|████▌     | 45524/100000 [13:50:30<8:50:06,  1.71it/s]
Train steps ... :  46%|████▌     | 45525/100000 [13:50:31<8:49:47,  1.71it/s]Step... (45525 / 100000 | Loss: 0.7897374629974365, Learning Rate: 5.474874371859297e-05)
+
                                                                             
Step... (45525 / 100000 | Loss: 0.8761387467384338, Learning Rate: 5.474874371859297e-05)
+
Train steps ... :  46%|████▌     | 45525/100000 [13:50:31<8:49:47,  1.71it/s]
Train steps ... :  46%|████▌     | 45526/100000 [13:50:32<8:49:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45527/100000 [13:50:32<8:49:32,  1.71it/s]
Train steps ... :  46%|████▌     | 45528/100000 [13:50:33<8:49:21,  1.72it/s]
Train steps ... :  46%|████▌     | 45529/100000 [13:50:33<8:50:10,  1.71it/s]
Train steps ... :  46%|████▌     | 45530/100000 [13:50:34<8:50:04,  1.71it/s]
Train steps ... :  46%|████▌     | 45531/100000 [13:50:35<8:50:21,  1.71it/s]
Train steps ... :  46%|████▌     | 45532/100000 [13:50:35<8:50:27,  1.71it/s]
Train steps ... :  46%|████▌     | 45533/100000 [13:50:36<8:50:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45534/100000 [13:50:36<8:50:37,  1.71it/s]
Train steps ... :  46%|████▌     | 45535/100000 [13:50:37<8:50:28,  1.71it/s]
Train steps ... :  46%|████▌     | 45536/100000 [13:50:37<8:51:06,  1.71it/s]
Train steps ... :  46%|████▌     | 45537/100000 [13:50:38<8:51:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45538/100000 [13:50:39<8:51:26,  1.71it/s]
Train steps ... :  46%|████▌     | 45539/100000 [13:50:39<8:51:23,  1.71it/s]
Train steps ... :  46%|████▌     | 45540/100000 [13:50:40<8:50:37,  1.71it/s]
Train steps ... :  46%|████▌     | 45541/100000 [13:50:40<8:50:30,  1.71it/s]
Train steps ... :  46%|████▌     | 45542/100000 [13:50:41<8:51:30,  1.71it/s]
Train steps ... :  46%|████▌     | 45543/100000 [13:50:42<8:51:00,  1.71it/s]
Train steps ... :  46%|████▌     | 45544/100000 [13:50:42<8:50:20,  1.71it/s]
Train steps ... :  46%|████▌     | 45545/100000 [13:50:43<8:49:53,  1.71it/s]
Train steps ... :  46%|████▌     | 45546/100000 [13:50:43<8:51:23,  1.71it/s]
Train steps ... :  46%|████▌     | 45547/100000 [13:50:44<8:52:17,  1.70it/s]
Train steps ... :  46%|████▌     | 45548/100000 [13:50:44<8:53:13,  1.70it/s]
Train steps ... :  46%|████▌     | 45549/100000 [13:50:45<8:53:08,  1.70it/s]
Train steps ... :  46%|████▌     | 45550/100000 [13:50:46<8:52:00,  1.71it/s]Step... (45550 / 100000 | Loss: 0.7034029960632324, Learning Rate: 5.4723618090452265e-05)
+
                                                                             
Step... (45550 / 100000 | Loss: 0.8170942068099976, Learning Rate: 5.4723618090452265e-05)
+
Train steps ... :  46%|████▌     | 45550/100000 [13:50:46<8:52:00,  1.71it/s]
Train steps ... :  46%|████▌     | 45551/100000 [13:50:46<8:51:02,  1.71it/s]
Train steps ... :  46%|████▌     | 45552/100000 [13:50:47<8:51:16,  1.71it/s]
Train steps ... :  46%|████▌     | 45553/100000 [13:50:47<8:50:51,  1.71it/s]
Train steps ... :  46%|████▌     | 45554/100000 [13:50:48<8:51:10,  1.71it/s]
Train steps ... :  46%|████▌     | 45555/100000 [13:50:49<8:51:06,  1.71it/s]
Train steps ... :  46%|████▌     | 45556/100000 [13:50:49<8:51:12,  1.71it/s]
Train steps ... :  46%|████▌     | 45557/100000 [13:50:50<8:50:31,  1.71it/s]
Train steps ... :  46%|████▌     | 45558/100000 [13:50:50<8:51:35,  1.71it/s]
Train steps ... :  46%|████▌     | 45559/100000 [13:50:51<8:51:00,  1.71it/s]
Train steps ... :  46%|████▌     | 45560/100000 [13:50:52<8:50:34,  1.71it/s]
Train steps ... :  46%|████▌     | 45561/100000 [13:50:52<8:50:38,  1.71it/s]
Train steps ... :  46%|████▌     | 45562/100000 [13:50:53<8:50:49,  1.71it/s]
Train steps ... :  46%|████▌     | 45563/100000 [13:50:53<8:52:24,  1.70it/s]
Train steps ... :  46%|████▌     | 45564/100000 [13:50:54<8:49:31,  1.71it/s]
Train steps ... :  46%|████▌     | 45565/100000 [13:50:54<8:51:23,  1.71it/s]
Train steps ... :  46%|████▌     | 45566/100000 [13:50:55<8:50:31,  1.71it/s]
Train steps ... :  46%|████▌     | 45567/100000 [13:50:56<8:51:01,  1.71it/s]
Train steps ... :  46%|████▌     | 45568/100000 [13:50:56<8:50:42,  1.71it/s]
Train steps ... :  46%|████▌     | 45569/100000 [13:50:57<8:50:31,  1.71it/s]
Train steps ... :  46%|████▌     | 45570/100000 [13:50:57<8:50:02,  1.71it/s]
Train steps ... :  46%|████▌     | 45571/100000 [13:50:58<8:49:36,  1.71it/s]
Train steps ... :  46%|████▌     | 45572/100000 [13:50:59<8:49:50,  1.71it/s]
Train steps ... :  46%|████▌     | 45573/100000 [13:50:59<8:50:26,  1.71it/s]
Train steps ... :  46%|████▌     | 45574/100000 [13:51:00<8:49:26,  1.71it/s]
Train steps ... :  46%|████▌     | 45575/100000 [13:51:00<8:51:26,  1.71it/s]Step... (45575 / 100000 | Loss: 0.7461258172988892, Learning Rate: 5.4698492462311555e-05)
+
                                                                             
Step... (45575 / 100000 | Loss: 0.9458906650543213, Learning Rate: 5.4698492462311555e-05)
+
Train steps ... :  46%|████▌     | 45575/100000 [13:51:01<8:51:26,  1.71it/s]
Train steps ... :  46%|████▌     | 45576/100000 [13:51:01<8:49:48,  1.71it/s]
Train steps ... :  46%|████▌     | 45577/100000 [13:51:01<8:49:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45578/100000 [13:51:02<8:51:05,  1.71it/s]
Train steps ... :  46%|████▌     | 45579/100000 [13:51:03<8:51:07,  1.71it/s]
Train steps ... :  46%|████▌     | 45580/100000 [13:51:03<8:51:41,  1.71it/s]
Train steps ... :  46%|████▌     | 45581/100000 [13:51:04<8:52:10,  1.70it/s]
Train steps ... :  46%|████▌     | 45582/100000 [13:51:04<8:51:51,  1.71it/s]
Train steps ... :  46%|████▌     | 45583/100000 [13:51:05<8:51:30,  1.71it/s]
Train steps ... :  46%|████▌     | 45584/100000 [13:51:06<8:51:19,  1.71it/s]
Train steps ... :  46%|████▌     | 45585/100000 [13:51:06<8:51:07,  1.71it/s]
Train steps ... :  46%|████▌     | 45586/100000 [13:51:07<8:50:34,  1.71it/s]
Train steps ... :  46%|████▌     | 45587/100000 [13:51:07<8:49:48,  1.71it/s]
Train steps ... :  46%|████▌     | 45588/100000 [13:51:08<8:49:14,  1.71it/s]
Train steps ... :  46%|████▌     | 45589/100000 [13:51:08<8:49:47,  1.71it/s]
Train steps ... :  46%|████▌     | 45590/100000 [13:51:09<8:50:20,  1.71it/s]
Train steps ... :  46%|████▌     | 45591/100000 [13:51:10<8:50:08,  1.71it/s]
Train steps ... :  46%|████▌     | 45592/100000 [13:51:10<8:49:54,  1.71it/s]
Train steps ... :  46%|████▌     | 45593/100000 [13:51:11<8:49:29,  1.71it/s]
Train steps ... :  46%|████▌     | 45594/100000 [13:51:11<8:49:03,  1.71it/s]
Train steps ... :  46%|████▌     | 45595/100000 [13:51:12<8:49:25,  1.71it/s]
Train steps ... :  46%|████▌     | 45596/100000 [13:51:13<8:48:43,  1.71it/s]
Train steps ... :  46%|████▌     | 45597/100000 [13:51:13<8:48:58,  1.71it/s]
Train steps ... :  46%|████▌     | 45598/100000 [13:51:14<8:49:06,  1.71it/s]
Train steps ... :  46%|████▌     | 45599/100000 [13:51:14<8:50:00,  1.71it/s]
Train steps ... :  46%|████▌     | 45600/100000 [13:51:15<8:51:05,  1.71it/s]Step... (45600 / 100000 | Loss: 0.6650649905204773, Learning Rate: 5.467336683417086e-05)
+
                                                                             
Step... (45600 / 100000 | Loss: 0.7753400802612305, Learning Rate: 5.467336683417086e-05)
+
Train steps ... :  46%|████▌     | 45600/100000 [13:51:15<8:51:05,  1.71it/s]
Train steps ... :  46%|████▌     | 45601/100000 [13:51:15<8:51:01,  1.71it/s]
Train steps ... :  46%|████▌     | 45602/100000 [13:51:16<8:49:37,  1.71it/s]
Train steps ... :  46%|████▌     | 45603/100000 [13:51:17<8:52:03,  1.70it/s]
Train steps ... :  46%|████▌     | 45604/100000 [13:51:17<8:51:03,  1.71it/s]
Train steps ... :  46%|████▌     | 45605/100000 [13:51:18<8:50:58,  1.71it/s]
Train steps ... :  46%|████▌     | 45606/100000 [13:51:18<8:50:49,  1.71it/s]
Train steps ... :  46%|████▌     | 45607/100000 [13:51:19<8:51:29,  1.71it/s]
Train steps ... :  46%|████▌     | 45608/100000 [13:51:20<8:52:23,  1.70it/s]
Train steps ... :  46%|████▌     | 45609/100000 [13:51:20<8:51:08,  1.71it/s]
Train steps ... :  46%|████▌     | 45610/100000 [13:51:21<8:50:42,  1.71it/s]
Train steps ... :  46%|████▌     | 45611/100000 [13:51:21<8:51:14,  1.71it/s]
Train steps ... :  46%|████▌     | 45612/100000 [13:51:22<8:50:12,  1.71it/s]
Train steps ... :  46%|████▌     | 45613/100000 [13:51:23<8:50:21,  1.71it/s]
Train steps ... :  46%|████▌     | 45614/100000 [13:51:23<8:51:00,  1.71it/s]
Train steps ... :  46%|████▌     | 45615/100000 [13:51:24<8:51:37,  1.71it/s]
Train steps ... :  46%|████▌     | 45616/100000 [13:51:24<8:50:42,  1.71it/s]
Train steps ... :  46%|████▌     | 45617/100000 [13:51:25<8:50:48,  1.71it/s]
Train steps ... :  46%|████▌     | 45618/100000 [13:51:25<8:50:28,  1.71it/s]
Train steps ... :  46%|████▌     | 45619/100000 [13:51:26<8:51:11,  1.71it/s]
Train steps ... :  46%|████▌     | 45620/100000 [13:51:27<8:51:00,  1.71it/s]
Train steps ... :  46%|████▌     | 45621/100000 [13:51:27<8:50:40,  1.71it/s]
Train steps ... :  46%|████▌     | 45622/100000 [13:51:28<8:50:47,  1.71it/s]
Train steps ... :  46%|████▌     | 45623/100000 [13:51:28<8:49:45,  1.71it/s]
Train steps ... :  46%|████▌     | 45624/100000 [13:51:29<8:50:32,  1.71it/s]
Train steps ... :  46%|████▌     | 45625/100000 [13:51:30<8:50:54,  1.71it/s]Step... (45625 / 100000 | Loss: 0.8633893728256226, Learning Rate: 5.464824120603015e-05)
+
                                                                             
Step... (45625 / 100000 | Loss: 0.9771831035614014, Learning Rate: 5.464824120603015e-05)
+
Train steps ... :  46%|████▌     | 45625/100000 [13:51:30<8:50:54,  1.71it/s]
Train steps ... :  46%|████▌     | 45626/100000 [13:51:30<8:50:23,  1.71it/s]
Train steps ... :  46%|████▌     | 45627/100000 [13:51:31<8:51:25,  1.71it/s]
Train steps ... :  46%|████▌     | 45628/100000 [13:51:31<8:49:41,  1.71it/s]
Train steps ... :  46%|████▌     | 45629/100000 [13:51:32<8:50:03,  1.71it/s]
Train steps ... :  46%|████▌     | 45630/100000 [13:51:32<8:51:16,  1.71it/s]
Train steps ... :  46%|████▌     | 45631/100000 [13:51:33<8:50:33,  1.71it/s]
Train steps ... :  46%|████▌     | 45632/100000 [13:51:34<8:49:28,  1.71it/s]
Train steps ... :  46%|████▌     | 45633/100000 [13:51:34<8:49:27,  1.71it/s]
Train steps ... :  46%|████▌     | 45634/100000 [13:51:35<8:51:05,  1.71it/s]
Train steps ... :  46%|████▌     | 45635/100000 [13:51:35<8:48:54,  1.71it/s]
Train steps ... :  46%|████▌     | 45636/100000 [13:51:36<8:49:08,  1.71it/s]
Train steps ... :  46%|████▌     | 45637/100000 [13:51:37<8:49:27,  1.71it/s]
Train steps ... :  46%|████▌     | 45638/100000 [13:51:37<8:48:56,  1.71it/s]
Train steps ... :  46%|████▌     | 45639/100000 [13:51:38<8:48:38,  1.71it/s]
Train steps ... :  46%|████▌     | 45640/100000 [13:51:38<8:48:47,  1.71it/s]
Train steps ... :  46%|████▌     | 45641/100000 [13:51:39<8:48:35,  1.71it/s]
Train steps ... :  46%|████▌     | 45642/100000 [13:51:39<8:48:47,  1.71it/s]
Train steps ... :  46%|████▌     | 45643/100000 [13:51:40<8:48:47,  1.71it/s]
Train steps ... :  46%|████▌     | 45644/100000 [13:51:41<8:48:41,  1.71it/s]
Train steps ... :  46%|████▌     | 45645/100000 [13:51:41<8:48:50,  1.71it/s]
Train steps ... :  46%|████▌     | 45646/100000 [13:51:42<8:49:29,  1.71it/s]
Train steps ... :  46%|████▌     | 45647/100000 [13:51:42<8:50:14,  1.71it/s]
Train steps ... :  46%|████▌     | 45648/100000 [13:51:43<8:49:45,  1.71it/s]
Train steps ... :  46%|████▌     | 45649/100000 [13:51:44<8:49:38,  1.71it/s]
Train steps ... :  46%|████▌     | 45650/100000 [13:51:44<8:49:52,  1.71it/s]Step... (45650 / 100000 | Loss: 0.7660540342330933, Learning Rate: 5.462311557788945e-05)
+
                                                                             
Step... (45650 / 100000 | Loss: 0.6420441269874573, Learning Rate: 5.462311557788945e-05)
+
Train steps ... :  46%|████▌     | 45650/100000 [13:51:44<8:49:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45651/100000 [13:51:45<8:49:49,  1.71it/s]
Train steps ... :  46%|████▌     | 45652/100000 [13:51:45<8:49:22,  1.71it/s]
Train steps ... :  46%|████▌     | 45653/100000 [13:51:46<8:49:31,  1.71it/s]
Train steps ... :  46%|████▌     | 45654/100000 [13:51:46<8:49:04,  1.71it/s]
Train steps ... :  46%|████▌     | 45655/100000 [13:51:47<8:49:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45656/100000 [13:51:48<8:49:48,  1.71it/s]
Train steps ... :  46%|████▌     | 45657/100000 [13:51:48<8:49:20,  1.71it/s]
Train steps ... :  46%|████▌     | 45658/100000 [13:51:49<8:49:07,  1.71it/s]
Train steps ... :  46%|████▌     | 45659/100000 [13:51:49<8:49:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45660/100000 [13:51:50<8:49:09,  1.71it/s]
Train steps ... :  46%|████▌     | 45661/100000 [13:51:51<8:48:45,  1.71it/s]
Train steps ... :  46%|████▌     | 45662/100000 [13:51:51<8:49:14,  1.71it/s]
Train steps ... :  46%|████▌     | 45663/100000 [13:51:52<8:48:53,  1.71it/s]
Train steps ... :  46%|████▌     | 45664/100000 [13:51:52<8:48:53,  1.71it/s]
Train steps ... :  46%|████▌     | 45665/100000 [13:51:53<8:49:09,  1.71it/s]
Train steps ... :  46%|████▌     | 45666/100000 [13:51:54<8:49:01,  1.71it/s]
Train steps ... :  46%|████▌     | 45667/100000 [13:51:54<8:48:28,  1.71it/s]
Train steps ... :  46%|████▌     | 45668/100000 [13:51:55<8:48:25,  1.71it/s]
Train steps ... :  46%|████▌     | 45669/100000 [13:51:55<8:48:19,  1.71it/s]
Train steps ... :  46%|████▌     | 45670/100000 [13:51:56<8:49:30,  1.71it/s]
Train steps ... :  46%|████▌     | 45671/100000 [13:51:56<8:49:30,  1.71it/s]
Train steps ... :  46%|████▌     | 45672/100000 [13:51:57<8:49:03,  1.71it/s]
Train steps ... :  46%|████▌     | 45673/100000 [13:51:58<8:49:24,  1.71it/s]
Train steps ... :  46%|████▌     | 45674/100000 [13:51:58<8:48:42,  1.71it/s]
Train steps ... :  46%|████▌     | 45675/100000 [13:51:59<8:49:20,  1.71it/s]Step... (45675 / 100000 | Loss: 0.801050066947937, Learning Rate: 5.459798994974875e-05)
+
                                                                             
Step... (45675 / 100000 | Loss: 0.6637969017028809, Learning Rate: 5.459798994974875e-05)
+
Train steps ... :  46%|████▌     | 45675/100000 [13:51:59<8:49:20,  1.71it/s]
Train steps ... :  46%|████▌     | 45676/100000 [13:51:59<8:49:35,  1.71it/s]
Train steps ... :  46%|████▌     | 45677/100000 [13:52:00<8:49:51,  1.71it/s]
Train steps ... :  46%|████▌     | 45678/100000 [13:52:01<8:49:36,  1.71it/s]
Train steps ... :  46%|████▌     | 45679/100000 [13:52:01<8:49:29,  1.71it/s]
Train steps ... :  46%|████▌     | 45680/100000 [13:52:02<8:50:14,  1.71it/s]
Train steps ... :  46%|████▌     | 45681/100000 [13:52:02<8:49:44,  1.71it/s]
Train steps ... :  46%|████▌     | 45682/100000 [13:52:03<8:48:54,  1.71it/s]
Train steps ... :  46%|████▌     | 45683/100000 [13:52:03<8:48:50,  1.71it/s]
Train steps ... :  46%|████▌     | 45684/100000 [13:52:04<8:48:45,  1.71it/s]
Train steps ... :  46%|████▌     | 45685/100000 [13:52:05<8:49:19,  1.71it/s]
Train steps ... :  46%|████▌     | 45686/100000 [13:52:05<8:49:36,  1.71it/s]
Train steps ... :  46%|████▌     | 45687/100000 [13:52:06<8:49:02,  1.71it/s]
Train steps ... :  46%|████▌     | 45688/100000 [13:52:06<8:49:19,  1.71it/s]
Train steps ... :  46%|████▌     | 45689/100000 [13:52:07<8:49:23,  1.71it/s]
Train steps ... :  46%|████▌     | 45690/100000 [13:52:08<8:49:14,  1.71it/s]
Train steps ... :  46%|████▌     | 45691/100000 [13:52:08<8:48:40,  1.71it/s]
Train steps ... :  46%|████▌     | 45692/100000 [13:52:09<8:48:25,  1.71it/s]
Train steps ... :  46%|████▌     | 45693/100000 [13:52:09<8:48:47,  1.71it/s]
Train steps ... :  46%|████▌     | 45694/100000 [13:52:10<8:48:50,  1.71it/s]
Train steps ... :  46%|████▌     | 45695/100000 [13:52:10<8:48:17,  1.71it/s]
Train steps ... :  46%|████▌     | 45696/100000 [13:52:11<8:49:20,  1.71it/s]
Train steps ... :  46%|████▌     | 45697/100000 [13:52:12<8:48:19,  1.71it/s]
Train steps ... :  46%|████▌     | 45698/100000 [13:52:12<8:48:14,  1.71it/s]
Train steps ... :  46%|████▌     | 45699/100000 [13:52:13<8:47:57,  1.71it/s]
Train steps ... :  46%|████▌     | 45700/100000 [13:52:13<8:48:04,  1.71it/s]Step... (45700 / 100000 | Loss: 0.8044782280921936, Learning Rate: 5.4572864321608045e-05)
+
                                                                             
Step... (45700 / 100000 | Loss: 1.1016919612884521, Learning Rate: 5.4572864321608045e-05)
+
Train steps ... :  46%|████▌     | 45700/100000 [13:52:14<8:48:04,  1.71it/s]
Train steps ... :  46%|████▌     | 45701/100000 [13:52:14<8:48:04,  1.71it/s]
Train steps ... :  46%|████▌     | 45702/100000 [13:52:15<8:47:57,  1.71it/s]
Train steps ... :  46%|████▌     | 45703/100000 [13:52:15<8:48:51,  1.71it/s]
Train steps ... :  46%|████▌     | 45704/100000 [13:52:16<8:48:20,  1.71it/s]
Train steps ... :  46%|████▌     | 45705/100000 [13:52:16<8:48:33,  1.71it/s]
Train steps ... :  46%|████▌     | 45706/100000 [13:52:17<8:49:02,  1.71it/s]
Train steps ... :  46%|████▌     | 45707/100000 [13:52:17<8:49:55,  1.71it/s]
Train steps ... :  46%|████▌     | 45708/100000 [13:52:18<8:48:43,  1.71it/s]
Train steps ... :  46%|████▌     | 45709/100000 [13:52:19<8:49:04,  1.71it/s]
Train steps ... :  46%|████▌     | 45710/100000 [13:52:19<8:49:24,  1.71it/s]
Train steps ... :  46%|████▌     | 45711/100000 [13:52:20<8:49:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45712/100000 [13:52:20<8:48:49,  1.71it/s]
Train steps ... :  46%|████▌     | 45713/100000 [13:52:21<8:48:40,  1.71it/s]
Train steps ... :  46%|████▌     | 45714/100000 [13:52:22<8:48:19,  1.71it/s]
Train steps ... :  46%|████▌     | 45715/100000 [13:52:22<8:48:37,  1.71it/s]
Train steps ... :  46%|████▌     | 45716/100000 [13:52:23<8:49:10,  1.71it/s]
Train steps ... :  46%|████▌     | 45717/100000 [13:52:23<8:48:32,  1.71it/s]
Train steps ... :  46%|████▌     | 45718/100000 [13:52:24<8:48:16,  1.71it/s]
Train steps ... :  46%|████▌     | 45719/100000 [13:52:24<8:48:18,  1.71it/s]
Train steps ... :  46%|████▌     | 45720/100000 [13:52:25<8:48:44,  1.71it/s]
Train steps ... :  46%|████▌     | 45721/100000 [13:52:26<8:48:16,  1.71it/s]
Train steps ... :  46%|████▌     | 45722/100000 [13:52:26<8:48:17,  1.71it/s]
Train steps ... :  46%|████▌     | 45723/100000 [13:52:27<8:48:40,  1.71it/s]
Train steps ... :  46%|████▌     | 45724/100000 [13:52:27<8:48:13,  1.71it/s]
Train steps ... :  46%|████▌     | 45725/100000 [13:52:28<8:48:01,  1.71it/s]Step... (45725 / 100000 | Loss: 1.0251669883728027, Learning Rate: 5.454773869346734e-05)
+
                                                                             
Step... (45725 / 100000 | Loss: 0.9223005771636963, Learning Rate: 5.454773869346734e-05)
+
Train steps ... :  46%|████▌     | 45725/100000 [13:52:28<8:48:01,  1.71it/s]
Train steps ... :  46%|████▌     | 45726/100000 [13:52:29<8:48:06,  1.71it/s]
Train steps ... :  46%|████▌     | 45727/100000 [13:52:29<8:48:07,  1.71it/s]
Train steps ... :  46%|████▌     | 45728/100000 [13:52:30<8:48:12,  1.71it/s]
Train steps ... :  46%|████▌     | 45729/100000 [13:52:30<8:48:22,  1.71it/s]
Train steps ... :  46%|████▌     | 45730/100000 [13:52:31<8:48:16,  1.71it/s]
Train steps ... :  46%|████▌     | 45731/100000 [13:52:31<8:48:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45732/100000 [13:52:32<8:48:33,  1.71it/s]
Train steps ... :  46%|████▌     | 45733/100000 [13:52:33<8:48:44,  1.71it/s]
Train steps ... :  46%|████▌     | 45734/100000 [13:52:33<8:48:28,  1.71it/s]
Train steps ... :  46%|████▌     | 45735/100000 [13:52:34<8:48:23,  1.71it/s]
Train steps ... :  46%|████▌     | 45736/100000 [13:52:34<8:48:16,  1.71it/s]
Train steps ... :  46%|████▌     | 45737/100000 [13:52:35<8:48:17,  1.71it/s]
Train steps ... :  46%|████▌     | 45738/100000 [13:52:36<8:50:00,  1.71it/s]
Train steps ... :  46%|████▌     | 45739/100000 [13:52:36<8:49:27,  1.71it/s]
Train steps ... :  46%|████▌     | 45740/100000 [13:52:37<8:49:12,  1.71it/s]
Train steps ... :  46%|████▌     | 45741/100000 [13:52:37<8:48:57,  1.71it/s]
Train steps ... :  46%|████▌     | 45742/100000 [13:52:38<8:48:56,  1.71it/s]
Train steps ... :  46%|████▌     | 45743/100000 [13:52:39<8:49:08,  1.71it/s]
Train steps ... :  46%|████▌     | 45744/100000 [13:52:39<8:48:49,  1.71it/s]
Train steps ... :  46%|████▌     | 45745/100000 [13:52:40<8:48:43,  1.71it/s]
Train steps ... :  46%|████▌     | 45746/100000 [13:52:40<8:48:41,  1.71it/s]
Train steps ... :  46%|████▌     | 45747/100000 [13:52:41<8:49:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45748/100000 [13:52:41<8:48:12,  1.71it/s]
Train steps ... :  46%|████▌     | 45749/100000 [13:52:42<8:47:39,  1.71it/s]
Train steps ... :  46%|████▌     | 45750/100000 [13:52:43<8:48:19,  1.71it/s]Step... (45750 / 100000 | Loss: 0.8355756998062134, Learning Rate: 5.452261306532663e-05)
+
                                                                             
Step... (45750 / 100000 | Loss: 0.5889488458633423, Learning Rate: 5.452261306532663e-05)
+
Train steps ... :  46%|████▌     | 45750/100000 [13:52:43<8:48:19,  1.71it/s]
Train steps ... :  46%|████▌     | 45751/100000 [13:52:43<8:48:30,  1.71it/s]
Train steps ... :  46%|████▌     | 45752/100000 [13:52:44<8:48:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45753/100000 [13:52:44<8:48:32,  1.71it/s]
Train steps ... :  46%|████▌     | 45754/100000 [13:52:45<8:48:41,  1.71it/s]
Train steps ... :  46%|████▌     | 45755/100000 [13:52:46<8:48:13,  1.71it/s]
Train steps ... :  46%|████▌     | 45756/100000 [13:52:46<8:48:57,  1.71it/s]
Train steps ... :  46%|████▌     | 45757/100000 [13:52:47<8:48:12,  1.71it/s]
Train steps ... :  46%|████▌     | 45758/100000 [13:52:47<8:49:27,  1.71it/s]
Train steps ... :  46%|████▌     | 45759/100000 [13:52:48<8:48:17,  1.71it/s]
Train steps ... :  46%|████▌     | 45760/100000 [13:52:48<8:48:00,  1.71it/s]
Train steps ... :  46%|████▌     | 45761/100000 [13:52:49<8:49:34,  1.71it/s]
Train steps ... :  46%|████▌     | 45762/100000 [13:52:50<8:49:48,  1.71it/s]
Train steps ... :  46%|████▌     | 45763/100000 [13:52:50<8:49:44,  1.71it/s]
Train steps ... :  46%|████▌     | 45764/100000 [13:52:51<8:48:29,  1.71it/s]
Train steps ... :  46%|████▌     | 45765/100000 [13:52:51<8:48:38,  1.71it/s]
Train steps ... :  46%|████▌     | 45766/100000 [13:52:52<8:48:20,  1.71it/s]
Train steps ... :  46%|████▌     | 45767/100000 [13:52:53<8:48:38,  1.71it/s]
Train steps ... :  46%|████▌     | 45768/100000 [13:52:53<8:48:07,  1.71it/s]
Train steps ... :  46%|████▌     | 45769/100000 [13:52:54<8:47:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45770/100000 [13:52:54<8:48:39,  1.71it/s]
Train steps ... :  46%|████▌     | 45771/100000 [13:52:55<8:47:55,  1.71it/s]
Train steps ... :  46%|████▌     | 45772/100000 [13:52:55<8:48:16,  1.71it/s]
Train steps ... :  46%|████▌     | 45773/100000 [13:52:56<8:48:10,  1.71it/s]
Train steps ... :  46%|████▌     | 45774/100000 [13:52:57<8:48:02,  1.71it/s]
Train steps ... :  46%|████▌     | 45775/100000 [13:52:57<8:47:54,  1.71it/s]Step... (45775 / 100000 | Loss: 0.7857372760772705, Learning Rate: 5.4497487437185934e-05)
+
                                                                             
Step... (45775 / 100000 | Loss: 0.9943984746932983, Learning Rate: 5.4497487437185934e-05)
+
Train steps ... :  46%|████▌     | 45775/100000 [13:52:58<8:47:54,  1.71it/s]
Train steps ... :  46%|████▌     | 45776/100000 [13:52:58<8:48:37,  1.71it/s]
Train steps ... :  46%|████▌     | 45777/100000 [13:52:58<8:48:07,  1.71it/s]
Train steps ... :  46%|████▌     | 45778/100000 [13:52:59<8:48:17,  1.71it/s]
Train steps ... :  46%|████▌     | 45779/100000 [13:53:00<8:47:54,  1.71it/s]
Train steps ... :  46%|████▌     | 45780/100000 [13:53:00<8:48:47,  1.71it/s]
Train steps ... :  46%|████▌     | 45781/100000 [13:53:01<8:47:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45782/100000 [13:53:01<8:48:53,  1.71it/s]
Train steps ... :  46%|████▌     | 45783/100000 [13:53:02<8:48:51,  1.71it/s]
Train steps ... :  46%|████▌     | 45784/100000 [13:53:02<8:48:36,  1.71it/s]
Train steps ... :  46%|████▌     | 45785/100000 [13:53:03<8:48:08,  1.71it/s]
Train steps ... :  46%|████▌     | 45786/100000 [13:53:04<8:48:04,  1.71it/s]
Train steps ... :  46%|████▌     | 45787/100000 [13:53:04<8:48:27,  1.71it/s]
Train steps ... :  46%|████▌     | 45788/100000 [13:53:05<8:48:48,  1.71it/s]
Train steps ... :  46%|████▌     | 45789/100000 [13:53:05<8:49:27,  1.71it/s]
Train steps ... :  46%|████▌     | 45790/100000 [13:53:06<8:49:39,  1.71it/s]
Train steps ... :  46%|████▌     | 45791/100000 [13:53:07<8:49:58,  1.70it/s]
Train steps ... :  46%|████▌     | 45792/100000 [13:53:07<8:48:09,  1.71it/s]
Train steps ... :  46%|████▌     | 45793/100000 [13:53:08<8:47:50,  1.71it/s]
Train steps ... :  46%|████▌     | 45794/100000 [13:53:08<8:47:51,  1.71it/s]
Train steps ... :  46%|████▌     | 45795/100000 [13:53:09<8:47:31,  1.71it/s]
Train steps ... :  46%|████▌     | 45796/100000 [13:53:09<8:47:10,  1.71it/s]
Train steps ... :  46%|████▌     | 45797/100000 [13:53:10<8:48:37,  1.71it/s]
Train steps ... :  46%|████▌     | 45798/100000 [13:53:11<8:47:36,  1.71it/s]
Train steps ... :  46%|████▌     | 45799/100000 [13:53:11<8:47:26,  1.71it/s]
Train steps ... :  46%|████▌     | 45800/100000 [13:53:12<8:47:15,  1.71it/s]Step... (45800 / 100000 | Loss: 0.759186863899231, Learning Rate: 5.4472361809045224e-05)
+
                                                                             
Step... (45800 / 100000 | Loss: 0.8113440275192261, Learning Rate: 5.4472361809045224e-05)
+
Train steps ... :  46%|████▌     | 45800/100000 [13:53:12<8:47:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45801/100000 [13:53:12<8:47:53,  1.71it/s]
Train steps ... :  46%|████▌     | 45802/100000 [13:53:13<8:48:03,  1.71it/s]
Train steps ... :  46%|████▌     | 45803/100000 [13:53:14<8:48:21,  1.71it/s]
Train steps ... :  46%|████▌     | 45804/100000 [13:53:14<8:48:01,  1.71it/s]
Train steps ... :  46%|████▌     | 45805/100000 [13:53:15<8:48:31,  1.71it/s]
Train steps ... :  46%|████▌     | 45806/100000 [13:53:15<8:48:39,  1.71it/s]
Train steps ... :  46%|████▌     | 45807/100000 [13:53:16<8:48:19,  1.71it/s]
Train steps ... :  46%|████▌     | 45808/100000 [13:53:17<8:49:28,  1.71it/s]
Train steps ... :  46%|████▌     | 45809/100000 [13:53:17<8:48:16,  1.71it/s]
Train steps ... :  46%|████▌     | 45810/100000 [13:53:18<8:49:25,  1.71it/s]
Train steps ... :  46%|████▌     | 45811/100000 [13:53:18<8:47:59,  1.71it/s]
Train steps ... :  46%|████▌     | 45812/100000 [13:53:19<8:47:54,  1.71it/s]
Train steps ... :  46%|████▌     | 45813/100000 [13:53:19<8:48:42,  1.71it/s]
Train steps ... :  46%|████▌     | 45814/100000 [13:53:20<8:49:33,  1.71it/s]
Train steps ... :  46%|████▌     | 45815/100000 [13:53:21<8:48:56,  1.71it/s]
Train steps ... :  46%|████▌     | 45816/100000 [13:53:21<8:49:10,  1.71it/s]
Train steps ... :  46%|████▌     | 45817/100000 [13:53:22<8:49:29,  1.71it/s]
Train steps ... :  46%|████▌     | 45818/100000 [13:53:22<8:49:36,  1.71it/s]
Train steps ... :  46%|████▌     | 45819/100000 [13:53:23<8:49:30,  1.71it/s]
Train steps ... :  46%|████▌     | 45820/100000 [13:53:24<8:49:05,  1.71it/s]
Train steps ... :  46%|████▌     | 45821/100000 [13:53:24<8:48:20,  1.71it/s]
Train steps ... :  46%|████▌     | 45822/100000 [13:53:25<8:49:01,  1.71it/s]
Train steps ... :  46%|████▌     | 45823/100000 [13:53:25<8:49:46,  1.70it/s]
Train steps ... :  46%|████▌     | 45824/100000 [13:53:26<8:47:26,  1.71it/s]
Train steps ... :  46%|████▌     | 45825/100000 [13:53:26<8:48:25,  1.71it/s]Step... (45825 / 100000 | Loss: 0.7318148612976074, Learning Rate: 5.444723618090453e-05)
+
                                                                             
Step... (45825 / 100000 | Loss: 0.7213199734687805, Learning Rate: 5.444723618090453e-05)
+
Train steps ... :  46%|████▌     | 45825/100000 [13:53:27<8:48:25,  1.71it/s]
Train steps ... :  46%|████▌     | 45826/100000 [13:53:27<8:48:21,  1.71it/s]
Train steps ... :  46%|████▌     | 45827/100000 [13:53:28<8:48:07,  1.71it/s]
Train steps ... :  46%|████▌     | 45828/100000 [13:53:28<8:47:25,  1.71it/s]
Train steps ... :  46%|████▌     | 45829/100000 [13:53:29<8:48:02,  1.71it/s]
Train steps ... :  46%|████▌     | 45830/100000 [13:53:29<8:47:55,  1.71it/s]
Train steps ... :  46%|████▌     | 45831/100000 [13:53:30<8:47:26,  1.71it/s]
Train steps ... :  46%|████▌     | 45832/100000 [13:53:31<8:47:54,  1.71it/s]
Train steps ... :  46%|████▌     | 45833/100000 [13:53:31<8:47:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45834/100000 [13:53:32<8:47:14,  1.71it/s]
Train steps ... :  46%|████▌     | 45835/100000 [13:53:32<8:46:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45836/100000 [13:53:33<8:47:24,  1.71it/s]
Train steps ... :  46%|████▌     | 45837/100000 [13:53:33<8:47:49,  1.71it/s]
Train steps ... :  46%|████▌     | 45838/100000 [13:53:34<8:48:19,  1.71it/s]
Train steps ... :  46%|████▌     | 45839/100000 [13:53:35<8:48:02,  1.71it/s]
Train steps ... :  46%|████▌     | 45840/100000 [13:53:35<8:47:49,  1.71it/s]
Train steps ... :  46%|████▌     | 45841/100000 [13:53:36<8:48:43,  1.71it/s]
Train steps ... :  46%|████▌     | 45842/100000 [13:53:36<8:47:10,  1.71it/s]
Train steps ... :  46%|████▌     | 45843/100000 [13:53:37<8:48:12,  1.71it/s]
Train steps ... :  46%|████▌     | 45844/100000 [13:53:38<8:47:02,  1.71it/s]
Train steps ... :  46%|████▌     | 45845/100000 [13:53:38<8:46:36,  1.71it/s]
Train steps ... :  46%|████▌     | 45846/100000 [13:53:39<8:46:39,  1.71it/s]
Train steps ... :  46%|████▌     | 45847/100000 [13:53:39<8:46:39,  1.71it/s]
Train steps ... :  46%|████▌     | 45848/100000 [13:53:40<8:46:41,  1.71it/s]
Train steps ... :  46%|████▌     | 45849/100000 [13:53:40<8:47:10,  1.71it/s]
Train steps ... :  46%|████▌     | 45850/100000 [13:53:41<8:47:01,  1.71it/s]Step... (45850 / 100000 | Loss: 1.1233761310577393, Learning Rate: 5.442211055276382e-05)
+
                                                                             
Step... (45850 / 100000 | Loss: 0.6989608407020569, Learning Rate: 5.442211055276382e-05)
+
Train steps ... :  46%|████▌     | 45850/100000 [13:53:41<8:47:01,  1.71it/s]
Train steps ... :  46%|████▌     | 45851/100000 [13:53:42<8:47:59,  1.71it/s]
Train steps ... :  46%|████▌     | 45852/100000 [13:53:42<8:48:47,  1.71it/s]
Train steps ... :  46%|████▌     | 45853/100000 [13:53:43<8:48:25,  1.71it/s]
Train steps ... :  46%|████▌     | 45854/100000 [13:53:43<8:48:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45855/100000 [13:53:44<8:49:14,  1.71it/s]
Train steps ... :  46%|████▌     | 45856/100000 [13:53:45<8:48:16,  1.71it/s]
Train steps ... :  46%|████▌     | 45857/100000 [13:53:45<8:48:34,  1.71it/s]
Train steps ... :  46%|████▌     | 45858/100000 [13:53:46<8:48:44,  1.71it/s]
Train steps ... :  46%|████▌     | 45859/100000 [13:53:46<8:47:56,  1.71it/s]
Train steps ... :  46%|████▌     | 45860/100000 [13:53:47<8:48:19,  1.71it/s]
Train steps ... :  46%|████▌     | 45861/100000 [13:53:48<8:47:58,  1.71it/s]
Train steps ... :  46%|████▌     | 45862/100000 [13:53:48<8:47:57,  1.71it/s]
Train steps ... :  46%|████▌     | 45863/100000 [13:53:49<8:48:47,  1.71it/s]
Train steps ... :  46%|████▌     | 45864/100000 [13:53:49<8:48:38,  1.71it/s]
Train steps ... :  46%|████▌     | 45865/100000 [13:53:50<8:49:15,  1.70it/s]
Train steps ... :  46%|████▌     | 45866/100000 [13:53:50<8:48:43,  1.71it/s]
Train steps ... :  46%|████▌     | 45867/100000 [13:53:51<8:49:22,  1.70it/s]
Train steps ... :  46%|████▌     | 45868/100000 [13:53:52<8:49:27,  1.70it/s]
Train steps ... :  46%|████▌     | 45869/100000 [13:53:52<8:49:42,  1.70it/s]
Train steps ... :  46%|████▌     | 45870/100000 [13:53:53<8:49:02,  1.71it/s]
Train steps ... :  46%|████▌     | 45871/100000 [13:53:53<8:49:35,  1.70it/s]
Train steps ... :  46%|████▌     | 45872/100000 [13:53:54<8:48:43,  1.71it/s]
Train steps ... :  46%|████▌     | 45873/100000 [13:53:55<8:48:39,  1.71it/s]
Train steps ... :  46%|████▌     | 45874/100000 [13:53:55<8:47:56,  1.71it/s]
Train steps ... :  46%|████▌     | 45875/100000 [13:53:56<8:48:19,  1.71it/s]Step... (45875 / 100000 | Loss: 0.8353147506713867, Learning Rate: 5.439698492462312e-05)
+
                                                                             
Step... (45875 / 100000 | Loss: 0.9065988659858704, Learning Rate: 5.439698492462312e-05)
+
Train steps ... :  46%|████▌     | 45875/100000 [13:53:56<8:48:19,  1.71it/s]
Train steps ... :  46%|████▌     | 45876/100000 [13:53:56<8:48:40,  1.71it/s]
Train steps ... :  46%|████▌     | 45877/100000 [13:53:57<8:47:50,  1.71it/s]
Train steps ... :  46%|████▌     | 45878/100000 [13:53:57<8:47:36,  1.71it/s]
Train steps ... :  46%|████▌     | 45879/100000 [13:53:58<8:47:49,  1.71it/s]
Train steps ... :  46%|████▌     | 45880/100000 [13:53:59<8:48:20,  1.71it/s]
Train steps ... :  46%|████▌     | 45881/100000 [13:53:59<8:49:03,  1.70it/s]
Train steps ... :  46%|████▌     | 45882/100000 [13:54:00<8:47:32,  1.71it/s]
Train steps ... :  46%|████▌     | 45883/100000 [13:54:00<8:47:11,  1.71it/s]
Train steps ... :  46%|████▌     | 45884/100000 [13:54:01<8:48:11,  1.71it/s]
Train steps ... :  46%|████▌     | 45885/100000 [13:54:02<8:47:35,  1.71it/s]
Train steps ... :  46%|████▌     | 45886/100000 [13:54:02<8:46:54,  1.71it/s]
Train steps ... :  46%|████▌     | 45887/100000 [13:54:03<8:46:50,  1.71it/s]
Train steps ... :  46%|████▌     | 45888/100000 [13:54:03<8:48:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45889/100000 [13:54:04<8:47:03,  1.71it/s]
Train steps ... :  46%|████▌     | 45890/100000 [13:54:05<8:48:45,  1.71it/s]
Train steps ... :  46%|████▌     | 45891/100000 [13:54:05<8:49:03,  1.70it/s]
Train steps ... :  46%|████▌     | 45892/100000 [13:54:06<8:48:24,  1.71it/s]
Train steps ... :  46%|████▌     | 45893/100000 [13:54:06<8:47:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45894/100000 [13:54:07<8:46:56,  1.71it/s]
Train steps ... :  46%|████▌     | 45895/100000 [13:54:07<8:47:10,  1.71it/s]
Train steps ... :  46%|████▌     | 45896/100000 [13:54:08<8:47:56,  1.71it/s]
Train steps ... :  46%|████▌     | 45897/100000 [13:54:09<8:47:28,  1.71it/s]
Train steps ... :  46%|████▌     | 45898/100000 [13:54:09<8:46:59,  1.71it/s]
Train steps ... :  46%|████▌     | 45899/100000 [13:54:10<8:47:08,  1.71it/s]
Train steps ... :  46%|████▌     | 45900/100000 [13:54:10<8:46:50,  1.71it/s]Step... (45900 / 100000 | Loss: 0.635620653629303, Learning Rate: 5.437185929648242e-05)
+
                                                                             
Step... (45900 / 100000 | Loss: 0.891944408416748, Learning Rate: 5.437185929648242e-05)
+
Train steps ... :  46%|████▌     | 45900/100000 [13:54:11<8:46:50,  1.71it/s]
Train steps ... :  46%|████▌     | 45901/100000 [13:54:11<8:47:22,  1.71it/s]
Train steps ... :  46%|████▌     | 45902/100000 [13:54:12<8:47:00,  1.71it/s]
Train steps ... :  46%|████▌     | 45903/100000 [13:54:12<8:47:01,  1.71it/s]
Train steps ... :  46%|████▌     | 45904/100000 [13:54:13<8:47:26,  1.71it/s]
Train steps ... :  46%|████▌     | 45905/100000 [13:54:13<8:47:01,  1.71it/s]
Train steps ... :  46%|████▌     | 45906/100000 [13:54:14<8:47:28,  1.71it/s]
Train steps ... :  46%|████▌     | 45907/100000 [13:54:14<8:47:06,  1.71it/s]
Train steps ... :  46%|████▌     | 45908/100000 [13:54:15<8:47:41,  1.71it/s]
Train steps ... :  46%|████▌     | 45909/100000 [13:54:16<8:47:16,  1.71it/s]
Train steps ... :  46%|████▌     | 45910/100000 [13:54:16<8:47:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45911/100000 [13:54:17<8:48:20,  1.71it/s]
Train steps ... :  46%|████▌     | 45912/100000 [13:54:17<8:47:59,  1.71it/s]
Train steps ... :  46%|████▌     | 45913/100000 [13:54:18<8:48:13,  1.71it/s]
Train steps ... :  46%|████▌     | 45914/100000 [13:54:19<8:48:10,  1.71it/s]
Train steps ... :  46%|████▌     | 45915/100000 [13:54:19<8:49:00,  1.70it/s]
Train steps ... :  46%|████▌     | 45916/100000 [13:54:20<8:47:22,  1.71it/s]
Train steps ... :  46%|████▌     | 45917/100000 [13:54:20<8:47:21,  1.71it/s]
Train steps ... :  46%|████▌     | 45918/100000 [13:54:21<8:47:05,  1.71it/s]
Train steps ... :  46%|████▌     | 45919/100000 [13:54:21<8:47:00,  1.71it/s]
Train steps ... :  46%|████▌     | 45920/100000 [13:54:22<8:47:55,  1.71it/s]
Train steps ... :  46%|████▌     | 45921/100000 [13:54:23<8:49:19,  1.70it/s]
Train steps ... :  46%|████▌     | 45922/100000 [13:54:23<8:49:55,  1.70it/s]
Train steps ... :  46%|████▌     | 45923/100000 [13:54:24<8:50:12,  1.70it/s]
Train steps ... :  46%|████▌     | 45924/100000 [13:54:24<8:48:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45925/100000 [13:54:25<8:49:16,  1.70it/s]Step... (45925 / 100000 | Loss: 0.7677075862884521, Learning Rate: 5.434673366834171e-05)
+
                                                                             
Step... (45925 / 100000 | Loss: 0.8539193868637085, Learning Rate: 5.434673366834171e-05)
+
Train steps ... :  46%|████▌     | 45925/100000 [13:54:25<8:49:16,  1.70it/s]
Train steps ... :  46%|████▌     | 45926/100000 [13:54:26<8:48:51,  1.70it/s]
Train steps ... :  46%|████▌     | 45927/100000 [13:54:26<8:48:23,  1.71it/s]
Train steps ... :  46%|████▌     | 45928/100000 [13:54:27<8:47:07,  1.71it/s]
Train steps ... :  46%|████▌     | 45929/100000 [13:54:27<8:47:39,  1.71it/s]
Train steps ... :  46%|████▌     | 45930/100000 [13:54:28<8:47:20,  1.71it/s]
Train steps ... :  46%|████▌     | 45931/100000 [13:54:29<8:47:05,  1.71it/s]
Train steps ... :  46%|████▌     | 45932/100000 [13:54:29<8:47:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45933/100000 [13:54:30<8:47:28,  1.71it/s]
Train steps ... :  46%|████▌     | 45934/100000 [13:54:30<8:46:53,  1.71it/s]
Train steps ... :  46%|████▌     | 45935/100000 [13:54:31<8:47:50,  1.71it/s]
Train steps ... :  46%|████▌     | 45936/100000 [13:54:31<8:47:41,  1.71it/s]
Train steps ... :  46%|████▌     | 45937/100000 [13:54:32<8:47:35,  1.71it/s]
Train steps ... :  46%|████▌     | 45938/100000 [13:54:33<8:47:25,  1.71it/s]
Train steps ... :  46%|████▌     | 45939/100000 [13:54:33<8:47:35,  1.71it/s]
Train steps ... :  46%|████▌     | 45940/100000 [13:54:34<8:48:09,  1.71it/s]
Train steps ... :  46%|████▌     | 45941/100000 [13:54:34<8:47:30,  1.71it/s]
Train steps ... :  46%|████▌     | 45942/100000 [13:54:35<8:47:59,  1.71it/s]
Train steps ... :  46%|████▌     | 45943/100000 [13:54:36<8:48:41,  1.70it/s]
Train steps ... :  46%|████▌     | 45944/100000 [13:54:36<8:46:54,  1.71it/s]
Train steps ... :  46%|████▌     | 45945/100000 [13:54:37<8:48:00,  1.71it/s]
Train steps ... :  46%|████▌     | 45946/100000 [13:54:37<8:46:34,  1.71it/s]
Train steps ... :  46%|████▌     | 45947/100000 [13:54:38<8:46:46,  1.71it/s]
Train steps ... :  46%|████▌     | 45948/100000 [13:54:38<8:47:29,  1.71it/s]
Train steps ... :  46%|████▌     | 45949/100000 [13:54:39<8:47:20,  1.71it/s]
Train steps ... :  46%|████▌     | 45950/100000 [13:54:40<8:46:52,  1.71it/s]Step... (45950 / 100000 | Loss: 0.7776073217391968, Learning Rate: 5.432160804020101e-05)
+
                                                                             
Step... (45950 / 100000 | Loss: 1.0858516693115234, Learning Rate: 5.432160804020101e-05)
+
Train steps ... :  46%|████▌     | 45950/100000 [13:54:40<8:46:52,  1.71it/s]
Train steps ... :  46%|████▌     | 45951/100000 [13:54:40<8:48:51,  1.70it/s]
Train steps ... :  46%|████▌     | 45952/100000 [13:54:41<8:47:05,  1.71it/s]
Train steps ... :  46%|████▌     | 45953/100000 [13:54:41<8:46:46,  1.71it/s]
Train steps ... :  46%|████▌     | 45954/100000 [13:54:42<8:47:09,  1.71it/s]
Train steps ... :  46%|████▌     | 45955/100000 [13:54:43<8:47:22,  1.71it/s]
Train steps ... :  46%|████▌     | 45956/100000 [13:54:43<8:47:43,  1.71it/s]
Train steps ... :  46%|████▌     | 45957/100000 [13:54:44<8:47:47,  1.71it/s]
Train steps ... :  46%|████▌     | 45958/100000 [13:54:44<8:47:45,  1.71it/s]
Train steps ... :  46%|████▌     | 45959/100000 [13:54:45<8:46:51,  1.71it/s]
Train steps ... :  46%|████▌     | 45960/100000 [13:54:45<8:47:05,  1.71it/s]
Train steps ... :  46%|████▌     | 45961/100000 [13:54:46<8:47:27,  1.71it/s]
Train steps ... :  46%|████▌     | 45962/100000 [13:54:47<8:46:50,  1.71it/s]
Train steps ... :  46%|████▌     | 45963/100000 [13:54:47<8:47:00,  1.71it/s]
Train steps ... :  46%|████▌     | 45964/100000 [13:54:48<8:46:44,  1.71it/s]
Train steps ... :  46%|████▌     | 45965/100000 [13:54:48<8:46:35,  1.71it/s]
Train steps ... :  46%|████▌     | 45966/100000 [13:54:49<8:46:09,  1.71it/s]
Train steps ... :  46%|████▌     | 45967/100000 [13:54:50<8:46:42,  1.71it/s]
Train steps ... :  46%|████▌     | 45968/100000 [13:54:50<8:47:04,  1.71it/s]
Train steps ... :  46%|████▌     | 45969/100000 [13:54:51<8:47:16,  1.71it/s]
Train steps ... :  46%|████▌     | 45970/100000 [13:54:51<8:47:02,  1.71it/s]
Train steps ... :  46%|████▌     | 45971/100000 [13:54:52<8:46:28,  1.71it/s]
Train steps ... :  46%|████▌     | 45972/100000 [13:54:53<8:46:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45973/100000 [13:54:53<8:47:34,  1.71it/s]
Train steps ... :  46%|████▌     | 45974/100000 [13:54:54<8:47:01,  1.71it/s]
Train steps ... :  46%|████▌     | 45975/100000 [13:54:54<8:46:28,  1.71it/s]Step... (45975 / 100000 | Loss: 0.6855412125587463, Learning Rate: 5.42964824120603e-05)
+
                                                                             
Step... (45975 / 100000 | Loss: 0.8594413995742798, Learning Rate: 5.42964824120603e-05)
+
Train steps ... :  46%|████▌     | 45975/100000 [13:54:55<8:46:28,  1.71it/s]
Train steps ... :  46%|████▌     | 45976/100000 [13:54:55<8:46:26,  1.71it/s]
Train steps ... :  46%|████▌     | 45977/100000 [13:54:55<8:46:02,  1.71it/s]
Train steps ... :  46%|████▌     | 45978/100000 [13:54:56<8:46:48,  1.71it/s]
Train steps ... :  46%|████▌     | 45979/100000 [13:54:57<8:46:49,  1.71it/s]
Train steps ... :  46%|████▌     | 45980/100000 [13:54:57<8:46:06,  1.71it/s]
Train steps ... :  46%|████▌     | 45981/100000 [13:54:58<8:45:53,  1.71it/s]
Train steps ... :  46%|████▌     | 45982/100000 [13:54:58<8:45:43,  1.71it/s]
Train steps ... :  46%|████▌     | 45983/100000 [13:54:59<8:45:24,  1.71it/s]
Train steps ... :  46%|████▌     | 45984/100000 [13:55:00<8:46:15,  1.71it/s]
Train steps ... :  46%|████▌     | 45985/100000 [13:55:00<8:45:37,  1.71it/s]
Train steps ... :  46%|████▌     | 45986/100000 [13:55:01<8:45:50,  1.71it/s]
Train steps ... :  46%|████▌     | 45987/100000 [13:55:01<8:45:23,  1.71it/s]
Train steps ... :  46%|████▌     | 45988/100000 [13:55:02<8:45:18,  1.71it/s]
Train steps ... :  46%|████▌     | 45989/100000 [13:55:02<8:46:12,  1.71it/s]
Train steps ... :  46%|████▌     | 45990/100000 [13:55:03<8:45:40,  1.71it/s]
Train steps ... :  46%|████▌     | 45991/100000 [13:55:04<8:45:42,  1.71it/s]
Train steps ... :  46%|████▌     | 45992/100000 [13:55:04<8:45:13,  1.71it/s]
Train steps ... :  46%|████▌     | 45993/100000 [13:55:05<8:46:02,  1.71it/s]
Train steps ... :  46%|████▌     | 45994/100000 [13:55:05<8:46:13,  1.71it/s]
Train steps ... :  46%|████▌     | 45995/100000 [13:55:06<8:46:17,  1.71it/s]
Train steps ... :  46%|████▌     | 45996/100000 [13:55:07<8:46:19,  1.71it/s]
Train steps ... :  46%|████▌     | 45997/100000 [13:55:07<8:47:09,  1.71it/s]
Train steps ... :  46%|████▌     | 45998/100000 [13:55:08<8:46:09,  1.71it/s]
Train steps ... :  46%|████▌     | 45999/100000 [13:55:08<8:48:10,  1.70it/s]
Train steps ... :  46%|████▌     | 46000/100000 [13:55:09<8:47:50,  1.71it/s]Step... (46000 / 100000 | Loss: 1.358026385307312, Learning Rate: 5.4271356783919604e-05)
+
                                                                             
Step... (46000 / 100000 | Loss: 0.8586626052856445, Learning Rate: 5.4271356783919604e-05)
+
Train steps ... :  46%|████▌     | 46000/100000 [13:55:09<8:47:50,  1.71it/s]
Train steps ... :  46%|████▌     | 46001/100000 [13:55:09<8:47:39,  1.71it/s]
Train steps ... :  46%|████▌     | 46002/100000 [13:55:10<8:47:02,  1.71it/s]
Train steps ... :  46%|████▌     | 46003/100000 [13:55:11<8:47:39,  1.71it/s]
Train steps ... :  46%|████▌     | 46004/100000 [13:55:11<8:47:24,  1.71it/s]
Train steps ... :  46%|████▌     | 46005/100000 [13:55:12<8:46:31,  1.71it/s]
Train steps ... :  46%|████▌     | 46006/100000 [13:55:12<8:46:45,  1.71it/s]
Train steps ... :  46%|████▌     | 46007/100000 [13:55:13<8:46:30,  1.71it/s]
Train steps ... :  46%|████▌     | 46008/100000 [13:55:14<8:45:49,  1.71it/s]
Train steps ... :  46%|████▌     | 46009/100000 [13:55:14<8:45:52,  1.71it/s]
Train steps ... :  46%|████▌     | 46010/100000 [13:55:15<8:46:35,  1.71it/s]
Train steps ... :  46%|████▌     | 46011/100000 [13:55:15<8:48:11,  1.70it/s]
Train steps ... :  46%|████▌     | 46012/100000 [13:55:16<8:47:19,  1.71it/s]
Train steps ... :  46%|████▌     | 46013/100000 [13:55:16<8:47:20,  1.71it/s]
Train steps ... :  46%|████▌     | 46014/100000 [13:55:17<8:46:44,  1.71it/s]
Train steps ... :  46%|████▌     | 46015/100000 [13:55:18<8:46:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46016/100000 [13:55:18<8:45:51,  1.71it/s]
Train steps ... :  46%|████▌     | 46017/100000 [13:55:19<8:46:23,  1.71it/s]
Train steps ... :  46%|████▌     | 46018/100000 [13:55:19<8:46:06,  1.71it/s]
Train steps ... :  46%|████▌     | 46019/100000 [13:55:20<8:46:11,  1.71it/s]
Train steps ... :  46%|████▌     | 46020/100000 [13:55:21<8:46:23,  1.71it/s]
Train steps ... :  46%|████▌     | 46021/100000 [13:55:21<8:46:36,  1.71it/s]
Train steps ... :  46%|████▌     | 46022/100000 [13:55:22<8:46:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46023/100000 [13:55:22<8:46:08,  1.71it/s]
Train steps ... :  46%|████▌     | 46024/100000 [13:55:23<8:45:39,  1.71it/s]
Train steps ... :  46%|████▌     | 46025/100000 [13:55:24<8:45:30,  1.71it/s]Step... (46025 / 100000 | Loss: 0.8343039751052856, Learning Rate: 5.4246231155778894e-05)
+
                                                                             
Step... (46025 / 100000 | Loss: 0.817717432975769, Learning Rate: 5.4246231155778894e-05)
+
Train steps ... :  46%|████▌     | 46025/100000 [13:55:24<8:45:30,  1.71it/s]
Train steps ... :  46%|████▌     | 46026/100000 [13:55:24<8:45:58,  1.71it/s]
Train steps ... :  46%|████▌     | 46027/100000 [13:55:25<8:46:51,  1.71it/s]
Train steps ... :  46%|████▌     | 46028/100000 [13:55:25<8:46:16,  1.71it/s]
Train steps ... :  46%|████▌     | 46029/100000 [13:55:26<8:45:47,  1.71it/s]
Train steps ... :  46%|████▌     | 46030/100000 [13:55:26<8:45:46,  1.71it/s]
Train steps ... :  46%|████▌     | 46031/100000 [13:55:27<8:45:43,  1.71it/s]
Train steps ... :  46%|████▌     | 46032/100000 [13:55:28<8:46:03,  1.71it/s]
Train steps ... :  46%|████▌     | 46033/100000 [13:55:28<8:46:01,  1.71it/s]
Train steps ... :  46%|████▌     | 46034/100000 [13:55:29<8:45:11,  1.71it/s]
Train steps ... :  46%|████▌     | 46035/100000 [13:55:29<8:45:00,  1.71it/s]
Train steps ... :  46%|████▌     | 46036/100000 [13:55:30<8:45:38,  1.71it/s]
Train steps ... :  46%|████▌     | 46037/100000 [13:55:31<8:45:47,  1.71it/s]
Train steps ... :  46%|████▌     | 46038/100000 [13:55:31<8:45:31,  1.71it/s]
Train steps ... :  46%|████▌     | 46039/100000 [13:55:32<8:45:15,  1.71it/s]
Train steps ... :  46%|████▌     | 46040/100000 [13:55:32<8:46:03,  1.71it/s]
Train steps ... :  46%|████▌     | 46041/100000 [13:55:33<8:45:36,  1.71it/s]
Train steps ... :  46%|████▌     | 46042/100000 [13:55:33<8:46:24,  1.71it/s]
Train steps ... :  46%|████▌     | 46043/100000 [13:55:34<8:47:06,  1.71it/s]
Train steps ... :  46%|████▌     | 46044/100000 [13:55:35<8:47:21,  1.71it/s]
Train steps ... :  46%|████▌     | 46045/100000 [13:55:35<8:46:51,  1.71it/s]
Train steps ... :  46%|████▌     | 46046/100000 [13:55:36<8:46:35,  1.71it/s]
Train steps ... :  46%|████▌     | 46047/100000 [13:55:36<8:46:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46048/100000 [13:55:37<8:45:49,  1.71it/s]
Train steps ... :  46%|████▌     | 46049/100000 [13:55:38<8:45:39,  1.71it/s]
Train steps ... :  46%|████▌     | 46050/100000 [13:55:38<8:45:17,  1.71it/s]Step... (46050 / 100000 | Loss: 0.7036786079406738, Learning Rate: 5.42211055276382e-05)
+
                                                                             
Step... (46050 / 100000 | Loss: 0.7495235204696655, Learning Rate: 5.42211055276382e-05)
+
Train steps ... :  46%|████▌     | 46050/100000 [13:55:38<8:45:17,  1.71it/s]
Train steps ... :  46%|████▌     | 46051/100000 [13:55:39<8:46:29,  1.71it/s]
Train steps ... :  46%|████▌     | 46052/100000 [13:55:39<8:46:50,  1.71it/s]
Train steps ... :  46%|████▌     | 46053/100000 [13:55:40<8:46:18,  1.71it/s]
Train steps ... :  46%|████▌     | 46054/100000 [13:55:40<8:46:47,  1.71it/s]
Train steps ... :  46%|████▌     | 46055/100000 [13:55:41<8:46:23,  1.71it/s]
Train steps ... :  46%|████▌     | 46056/100000 [13:55:42<8:45:43,  1.71it/s]
Train steps ... :  46%|████▌     | 46057/100000 [13:55:42<8:45:02,  1.71it/s]
Train steps ... :  46%|████▌     | 46058/100000 [13:55:43<8:45:51,  1.71it/s]
Train steps ... :  46%|████▌     | 46059/100000 [13:55:43<8:45:28,  1.71it/s]
Train steps ... :  46%|████▌     | 46060/100000 [13:55:44<8:45:12,  1.71it/s]
Train steps ... :  46%|████▌     | 46061/100000 [13:55:45<8:44:49,  1.71it/s]
Train steps ... :  46%|████▌     | 46062/100000 [13:55:45<8:44:56,  1.71it/s]
Train steps ... :  46%|████▌     | 46063/100000 [13:55:46<8:45:41,  1.71it/s]
Train steps ... :  46%|████▌     | 46064/100000 [13:55:46<8:45:27,  1.71it/s]
Train steps ... :  46%|████▌     | 46065/100000 [13:55:47<8:46:14,  1.71it/s]
Train steps ... :  46%|████▌     | 46066/100000 [13:55:47<8:45:55,  1.71it/s]
Train steps ... :  46%|████▌     | 46067/100000 [13:55:48<8:45:40,  1.71it/s]
Train steps ... :  46%|████▌     | 46068/100000 [13:55:49<8:45:14,  1.71it/s]
Train steps ... :  46%|████▌     | 46069/100000 [13:55:49<8:44:59,  1.71it/s]
Train steps ... :  46%|████▌     | 46070/100000 [13:55:50<8:45:34,  1.71it/s]
Train steps ... :  46%|████▌     | 46071/100000 [13:55:50<8:45:13,  1.71it/s]
Train steps ... :  46%|████▌     | 46072/100000 [13:55:51<8:45:35,  1.71it/s]
Train steps ... :  46%|████▌     | 46073/100000 [13:55:52<8:45:24,  1.71it/s]
Train steps ... :  46%|████▌     | 46074/100000 [13:55:52<8:45:40,  1.71it/s]
Train steps ... :  46%|████▌     | 46075/100000 [13:55:53<8:45:14,  1.71it/s]Step... (46075 / 100000 | Loss: 0.8178790211677551, Learning Rate: 5.4195979899497494e-05)
+
                                                                             
Step... (46075 / 100000 | Loss: 0.773693323135376, Learning Rate: 5.4195979899497494e-05)
+
Train steps ... :  46%|████▌     | 46075/100000 [13:55:53<8:45:14,  1.71it/s]
Train steps ... :  46%|████▌     | 46076/100000 [13:55:53<8:45:24,  1.71it/s]
Train steps ... :  46%|████▌     | 46077/100000 [13:55:54<8:45:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46078/100000 [13:55:55<8:44:57,  1.71it/s]
Train steps ... :  46%|████▌     | 46079/100000 [13:55:55<8:44:58,  1.71it/s]
Train steps ... :  46%|████▌     | 46080/100000 [13:55:56<8:44:43,  1.71it/s]
Train steps ... :  46%|████▌     | 46081/100000 [13:55:56<8:44:29,  1.71it/s]
Train steps ... :  46%|████▌     | 46082/100000 [13:55:57<8:45:08,  1.71it/s]
Train steps ... :  46%|████▌     | 46083/100000 [13:55:57<8:44:53,  1.71it/s]
Train steps ... :  46%|████▌     | 46084/100000 [13:55:58<8:45:24,  1.71it/s]
Train steps ... :  46%|████▌     | 46085/100000 [13:55:59<8:45:49,  1.71it/s]
Train steps ... :  46%|████▌     | 46086/100000 [13:55:59<8:45:18,  1.71it/s]
Train steps ... :  46%|████▌     | 46087/100000 [13:56:00<8:44:46,  1.71it/s]
Train steps ... :  46%|████▌     | 46088/100000 [13:56:00<8:44:50,  1.71it/s]
Train steps ... :  46%|████▌     | 46089/100000 [13:56:01<8:45:10,  1.71it/s]
Train steps ... :  46%|████▌     | 46090/100000 [13:56:02<8:45:12,  1.71it/s]
Train steps ... :  46%|████▌     | 46091/100000 [13:56:02<8:45:56,  1.71it/s]
Train steps ... :  46%|████▌     | 46092/100000 [13:56:03<8:45:40,  1.71it/s]
Train steps ... :  46%|████▌     | 46093/100000 [13:56:03<8:44:59,  1.71it/s]
Train steps ... :  46%|████▌     | 46094/100000 [13:56:04<8:45:22,  1.71it/s]
Train steps ... :  46%|████▌     | 46095/100000 [13:56:04<8:45:26,  1.71it/s]
Train steps ... :  46%|████▌     | 46096/100000 [13:56:05<8:45:44,  1.71it/s]
Train steps ... :  46%|████▌     | 46097/100000 [13:56:06<8:45:45,  1.71it/s]
Train steps ... :  46%|████▌     | 46098/100000 [13:56:06<8:46:18,  1.71it/s]
Train steps ... :  46%|████▌     | 46099/100000 [13:56:07<8:45:26,  1.71it/s]
Train steps ... :  46%|████▌     | 46100/100000 [13:56:07<8:45:39,  1.71it/s]Step... (46100 / 100000 | Loss: 0.794342577457428, Learning Rate: 5.4170854271356784e-05)
+
                                                                             
Step... (46100 / 100000 | Loss: 0.6516252756118774, Learning Rate: 5.4170854271356784e-05)
+
Train steps ... :  46%|████▌     | 46100/100000 [13:56:08<8:45:39,  1.71it/s]
Train steps ... :  46%|████▌     | 46101/100000 [13:56:08<8:46:28,  1.71it/s]
Train steps ... :  46%|████▌     | 46102/100000 [13:56:09<8:45:54,  1.71it/s]
Train steps ... :  46%|████▌     | 46103/100000 [13:56:09<8:45:25,  1.71it/s]
Train steps ... :  46%|████▌     | 46104/100000 [13:56:10<8:45:04,  1.71it/s]
Train steps ... :  46%|████▌     | 46105/100000 [13:56:10<8:45:08,  1.71it/s]
Train steps ... :  46%|████▌     | 46106/100000 [13:56:11<8:44:42,  1.71it/s]
Train steps ... :  46%|████▌     | 46107/100000 [13:56:11<8:44:27,  1.71it/s]
Train steps ... :  46%|████▌     | 46108/100000 [13:56:12<8:44:16,  1.71it/s]
Train steps ... :  46%|████▌     | 46109/100000 [13:56:13<8:44:17,  1.71it/s]
Train steps ... :  46%|████▌     | 46110/100000 [13:56:13<8:44:19,  1.71it/s]
Train steps ... :  46%|████▌     | 46111/100000 [13:56:14<8:45:16,  1.71it/s]
Train steps ... :  46%|████▌     | 46112/100000 [13:56:14<8:45:08,  1.71it/s]
Train steps ... :  46%|████▌     | 46113/100000 [13:56:15<8:45:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46114/100000 [13:56:16<8:45:32,  1.71it/s]
Train steps ... :  46%|████▌     | 46115/100000 [13:56:16<8:46:02,  1.71it/s]
Train steps ... :  46%|████▌     | 46116/100000 [13:56:17<8:45:54,  1.71it/s]
Train steps ... :  46%|████▌     | 46117/100000 [13:56:17<8:47:35,  1.70it/s]
Train steps ... :  46%|████▌     | 46118/100000 [13:56:18<8:45:40,  1.71it/s]
Train steps ... :  46%|████▌     | 46119/100000 [13:56:18<8:46:26,  1.71it/s]
Train steps ... :  46%|████▌     | 46120/100000 [13:56:19<8:45:20,  1.71it/s]
Train steps ... :  46%|████▌     | 46121/100000 [13:56:20<8:45:14,  1.71it/s]
Train steps ... :  46%|████▌     | 46122/100000 [13:56:20<8:45:54,  1.71it/s]
Train steps ... :  46%|████▌     | 46123/100000 [13:56:21<8:46:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46124/100000 [13:56:21<8:46:23,  1.71it/s]
Train steps ... :  46%|████▌     | 46125/100000 [13:56:22<8:46:01,  1.71it/s]Step... (46125 / 100000 | Loss: 0.7594452500343323, Learning Rate: 5.414572864321609e-05)
+
                                                                             
Step... (46125 / 100000 | Loss: 0.7401221990585327, Learning Rate: 5.414572864321609e-05)
+
Train steps ... :  46%|████▌     | 46125/100000 [13:56:22<8:46:01,  1.71it/s]
Train steps ... :  46%|████▌     | 46126/100000 [13:56:23<8:46:37,  1.71it/s]
Train steps ... :  46%|████▌     | 46127/100000 [13:56:23<8:46:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46128/100000 [13:56:24<8:45:50,  1.71it/s]
Train steps ... :  46%|████▌     | 46129/100000 [13:56:24<8:45:32,  1.71it/s]
Train steps ... :  46%|████▌     | 46130/100000 [13:56:25<8:45:20,  1.71it/s]
Train steps ... :  46%|████▌     | 46131/100000 [13:56:26<8:46:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46132/100000 [13:56:26<8:45:24,  1.71it/s]
Train steps ... :  46%|████▌     | 46133/100000 [13:56:27<8:45:21,  1.71it/s]
Train steps ... :  46%|████▌     | 46134/100000 [13:56:27<8:44:56,  1.71it/s]
Train steps ... :  46%|████▌     | 46135/100000 [13:56:28<8:44:24,  1.71it/s]
Train steps ... :  46%|████▌     | 46136/100000 [13:56:28<8:45:09,  1.71it/s]
Train steps ... :  46%|████▌     | 46137/100000 [13:56:29<8:45:31,  1.71it/s]
Train steps ... :  46%|████▌     | 46138/100000 [13:56:30<8:45:04,  1.71it/s]
Train steps ... :  46%|████▌     | 46139/100000 [13:56:30<8:44:28,  1.71it/s]
Train steps ... :  46%|████▌     | 46140/100000 [13:56:31<8:44:42,  1.71it/s]
Train steps ... :  46%|████▌     | 46141/100000 [13:56:31<8:45:00,  1.71it/s]
Train steps ... :  46%|████▌     | 46142/100000 [13:56:32<8:44:38,  1.71it/s]
Train steps ... :  46%|████▌     | 46143/100000 [13:56:33<8:44:24,  1.71it/s]
Train steps ... :  46%|████▌     | 46144/100000 [13:56:33<8:44:44,  1.71it/s]
Train steps ... :  46%|████▌     | 46145/100000 [13:56:34<8:44:59,  1.71it/s]
Train steps ... :  46%|████▌     | 46146/100000 [13:56:34<8:44:58,  1.71it/s]
Train steps ... :  46%|████▌     | 46147/100000 [13:56:35<8:44:30,  1.71it/s]
Train steps ... :  46%|████▌     | 46148/100000 [13:56:35<8:44:36,  1.71it/s]
Train steps ... :  46%|████▌     | 46149/100000 [13:56:36<8:44:24,  1.71it/s]
Train steps ... :  46%|████▌     | 46150/100000 [13:56:37<8:44:44,  1.71it/s]Step... (46150 / 100000 | Loss: 0.9473596811294556, Learning Rate: 5.412060301507538e-05)
+
                                                                             
Step... (46150 / 100000 | Loss: 0.7737410664558411, Learning Rate: 5.412060301507538e-05)
+
Train steps ... :  46%|████▌     | 46150/100000 [13:56:37<8:44:44,  1.71it/s]
Train steps ... :  46%|████▌     | 46151/100000 [13:56:37<8:44:57,  1.71it/s]
Train steps ... :  46%|████▌     | 46152/100000 [13:56:38<8:44:43,  1.71it/s]
Train steps ... :  46%|████▌     | 46153/100000 [13:56:38<8:44:46,  1.71it/s]
Train steps ... :  46%|████▌     | 46154/100000 [13:56:39<8:44:28,  1.71it/s]
Train steps ... :  46%|████▌     | 46155/100000 [13:56:40<8:44:31,  1.71it/s]
Train steps ... :  46%|████▌     | 46156/100000 [13:56:40<8:44:34,  1.71it/s]
Train steps ... :  46%|████▌     | 46157/100000 [13:56:41<8:45:07,  1.71it/s]
Train steps ... :  46%|████▌     | 46158/100000 [13:56:41<8:45:24,  1.71it/s]
Train steps ... :  46%|████▌     | 46159/100000 [13:56:42<8:45:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46160/100000 [13:56:42<8:45:06,  1.71it/s]
Train steps ... :  46%|████▌     | 46161/100000 [13:56:43<8:44:34,  1.71it/s]
Train steps ... :  46%|████▌     | 46162/100000 [13:56:44<8:44:12,  1.71it/s]
Train steps ... :  46%|████▌     | 46163/100000 [13:56:44<8:44:47,  1.71it/s]
Train steps ... :  46%|████▌     | 46164/100000 [13:56:45<8:44:39,  1.71it/s]
Train steps ... :  46%|████▌     | 46165/100000 [13:56:45<8:44:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46166/100000 [13:56:46<8:44:19,  1.71it/s]
Train steps ... :  46%|████▌     | 46167/100000 [13:56:47<8:45:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46168/100000 [13:56:47<8:44:41,  1.71it/s]
Train steps ... :  46%|████▌     | 46169/100000 [13:56:48<8:44:20,  1.71it/s]
Train steps ... :  46%|████▌     | 46170/100000 [13:56:48<8:44:25,  1.71it/s]
Train steps ... :  46%|████▌     | 46171/100000 [13:56:49<8:43:40,  1.71it/s]
Train steps ... :  46%|████▌     | 46172/100000 [13:56:49<8:44:17,  1.71it/s]
Train steps ... :  46%|████▌     | 46173/100000 [13:56:50<8:44:23,  1.71it/s]
Train steps ... :  46%|████▌     | 46174/100000 [13:56:51<8:44:35,  1.71it/s]
Train steps ... :  46%|████▌     | 46175/100000 [13:56:51<8:44:07,  1.71it/s]Step... (46175 / 100000 | Loss: 1.6252645254135132, Learning Rate: 5.409547738693468e-05)
+
                                                                             
Step... (46175 / 100000 | Loss: 0.8885961771011353, Learning Rate: 5.409547738693468e-05)
+
Train steps ... :  46%|████▌     | 46175/100000 [13:56:52<8:44:07,  1.71it/s]
Train steps ... :  46%|████▌     | 46176/100000 [13:56:52<8:44:32,  1.71it/s]
Train steps ... :  46%|████▌     | 46177/100000 [13:56:52<8:44:56,  1.71it/s]
Train steps ... :  46%|████▌     | 46178/100000 [13:56:53<8:44:28,  1.71it/s]
Train steps ... :  46%|████▌     | 46179/100000 [13:56:54<8:44:28,  1.71it/s]
Train steps ... :  46%|████▌     | 46180/100000 [13:56:54<8:44:21,  1.71it/s]
Train steps ... :  46%|████▌     | 46181/100000 [13:56:55<8:44:28,  1.71it/s]
Train steps ... :  46%|████▌     | 46182/100000 [13:56:55<8:45:02,  1.71it/s]
Train steps ... :  46%|████▌     | 46183/100000 [13:56:56<8:45:08,  1.71it/s]
Train steps ... :  46%|████▌     | 46184/100000 [13:56:57<8:44:25,  1.71it/s]
Train steps ... :  46%|████▌     | 46185/100000 [13:56:57<8:44:46,  1.71it/s]
Train steps ... :  46%|████▌     | 46186/100000 [13:56:58<8:44:24,  1.71it/s]
Train steps ... :  46%|████▌     | 46187/100000 [13:56:58<8:44:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46188/100000 [13:56:59<8:43:56,  1.71it/s]
Train steps ... :  46%|████▌     | 46189/100000 [13:56:59<8:43:34,  1.71it/s]
Train steps ... :  46%|████▌     | 46190/100000 [13:57:00<8:44:08,  1.71it/s]
Train steps ... :  46%|████▌     | 46191/100000 [13:57:01<8:43:55,  1.71it/s]
Train steps ... :  46%|████▌     | 46192/100000 [13:57:01<8:43:48,  1.71it/s]
Train steps ... :  46%|████▌     | 46193/100000 [13:57:02<8:43:35,  1.71it/s]
Train steps ... :  46%|████▌     | 46194/100000 [13:57:02<8:43:48,  1.71it/s]
Train steps ... :  46%|████▌     | 46195/100000 [13:57:03<8:43:54,  1.71it/s]
Train steps ... :  46%|████▌     | 46196/100000 [13:57:04<8:43:39,  1.71it/s]
Train steps ... :  46%|████▌     | 46197/100000 [13:57:04<8:43:50,  1.71it/s]
Train steps ... :  46%|████▌     | 46198/100000 [13:57:05<8:44:15,  1.71it/s]
Train steps ... :  46%|████▌     | 46199/100000 [13:57:05<8:44:35,  1.71it/s]
Train steps ... :  46%|████▌     | 46200/100000 [13:57:06<8:44:29,  1.71it/s]Step... (46200 / 100000 | Loss: 0.5709806680679321, Learning Rate: 5.407035175879397e-05)
+
                                                                             
Step... (46200 / 100000 | Loss: 0.8650346398353577, Learning Rate: 5.407035175879397e-05)
+
Train steps ... :  46%|████▌     | 46200/100000 [13:57:06<8:44:29,  1.71it/s]
Train steps ... :  46%|████▌     | 46201/100000 [13:57:06<8:44:46,  1.71it/s]
Train steps ... :  46%|████▌     | 46202/100000 [13:57:07<8:44:22,  1.71it/s]
Train steps ... :  46%|████▌     | 46203/100000 [13:57:08<8:43:58,  1.71it/s]
Train steps ... :  46%|████▌     | 46204/100000 [13:57:08<8:43:44,  1.71it/s]
Train steps ... :  46%|████▌     | 46205/100000 [13:57:09<8:43:47,  1.71it/s]
Train steps ... :  46%|████▌     | 46206/100000 [13:57:09<8:43:46,  1.71it/s]
Train steps ... :  46%|████▌     | 46207/100000 [13:57:10<8:43:46,  1.71it/s]
Train steps ... :  46%|████▌     | 46208/100000 [13:57:11<8:44:20,  1.71it/s]
Train steps ... :  46%|████▌     | 46209/100000 [13:57:11<8:43:47,  1.71it/s]
Train steps ... :  46%|████▌     | 46210/100000 [13:57:12<8:43:40,  1.71it/s]
Train steps ... :  46%|████▌     | 46211/100000 [13:57:12<8:44:01,  1.71it/s]
Train steps ... :  46%|████▌     | 46212/100000 [13:57:13<8:44:42,  1.71it/s]
Train steps ... :  46%|████▌     | 46213/100000 [13:57:13<8:44:31,  1.71it/s]
Train steps ... :  46%|████▌     | 46214/100000 [13:57:14<8:44:05,  1.71it/s]
Train steps ... :  46%|████▌     | 46215/100000 [13:57:15<8:43:52,  1.71it/s]
Train steps ... :  46%|████▌     | 46216/100000 [13:57:15<8:44:17,  1.71it/s]
Train steps ... :  46%|████▌     | 46217/100000 [13:57:16<8:43:53,  1.71it/s]
Train steps ... :  46%|████▌     | 46218/100000 [13:57:16<8:43:44,  1.71it/s]
Train steps ... :  46%|████▌     | 46219/100000 [13:57:17<8:43:35,  1.71it/s]
Train steps ... :  46%|████▌     | 46220/100000 [13:57:18<8:43:15,  1.71it/s]
Train steps ... :  46%|████▌     | 46221/100000 [13:57:18<8:44:01,  1.71it/s]
Train steps ... :  46%|████▌     | 46222/100000 [13:57:19<8:43:34,  1.71it/s]
Train steps ... :  46%|████▌     | 46223/100000 [13:57:19<8:43:34,  1.71it/s]
Train steps ... :  46%|████▌     | 46224/100000 [13:57:20<8:43:24,  1.71it/s]
Train steps ... :  46%|████▌     | 46225/100000 [13:57:20<8:43:41,  1.71it/s]Step... (46225 / 100000 | Loss: 1.0389902591705322, Learning Rate: 5.4045226130653274e-05)
+
                                                                             
Step... (46225 / 100000 | Loss: 1.0158634185791016, Learning Rate: 5.4045226130653274e-05)
+
Train steps ... :  46%|████▌     | 46225/100000 [13:57:21<8:43:41,  1.71it/s]
Train steps ... :  46%|████▌     | 46226/100000 [13:57:21<8:44:25,  1.71it/s]
Train steps ... :  46%|████▌     | 46227/100000 [13:57:22<8:43:42,  1.71it/s]
Train steps ... :  46%|████▌     | 46228/100000 [13:57:22<8:43:23,  1.71it/s]
Train steps ... :  46%|████▌     | 46229/100000 [13:57:23<8:43:14,  1.71it/s]
Train steps ... :  46%|████▌     | 46230/100000 [13:57:23<8:43:39,  1.71it/s]
Train steps ... :  46%|████▌     | 46231/100000 [13:57:24<8:43:48,  1.71it/s]
Train steps ... :  46%|████▌     | 46232/100000 [13:57:25<8:43:39,  1.71it/s]
Train steps ... :  46%|████▌     | 46233/100000 [13:57:25<8:43:39,  1.71it/s]
Train steps ... :  46%|████▌     | 46234/100000 [13:57:26<8:43:53,  1.71it/s]
Train steps ... :  46%|████▌     | 46235/100000 [13:57:26<8:44:01,  1.71it/s]
Train steps ... :  46%|████▌     | 46236/100000 [13:57:27<8:43:34,  1.71it/s]
Train steps ... :  46%|████▌     | 46237/100000 [13:57:27<8:44:13,  1.71it/s]
Train steps ... :  46%|████▌     | 46238/100000 [13:57:28<8:43:35,  1.71it/s]
Train steps ... :  46%|████▌     | 46239/100000 [13:57:29<8:43:16,  1.71it/s]
Train steps ... :  46%|████▌     | 46240/100000 [13:57:29<8:42:53,  1.71it/s]
Train steps ... :  46%|████▌     | 46241/100000 [13:57:30<8:42:31,  1.71it/s]
Train steps ... :  46%|████▌     | 46242/100000 [13:57:30<8:42:50,  1.71it/s]
Train steps ... :  46%|████▌     | 46243/100000 [13:57:31<8:42:52,  1.71it/s]
Train steps ... :  46%|████▌     | 46244/100000 [13:57:32<8:42:50,  1.71it/s]
Train steps ... :  46%|████▌     | 46245/100000 [13:57:32<8:43:35,  1.71it/s]
Train steps ... :  46%|████▌     | 46246/100000 [13:57:33<8:43:27,  1.71it/s]
Train steps ... :  46%|████▌     | 46247/100000 [13:57:33<8:43:42,  1.71it/s]
Train steps ... :  46%|████▌     | 46248/100000 [13:57:34<8:43:35,  1.71it/s]
Train steps ... :  46%|████▌     | 46249/100000 [13:57:34<8:43:41,  1.71it/s]
Train steps ... :  46%|████▋     | 46250/100000 [13:57:35<8:43:44,  1.71it/s]Step... (46250 / 100000 | Loss: 0.8380456566810608, Learning Rate: 5.4020100502512563e-05)
+
                                                                             
Step... (46250 / 100000 | Loss: 1.0061901807785034, Learning Rate: 5.4020100502512563e-05)
+
Train steps ... :  46%|████▋     | 46250/100000 [13:57:35<8:43:44,  1.71it/s]
Train steps ... :  46%|████▋     | 46251/100000 [13:57:36<8:44:28,  1.71it/s]
Train steps ... :  46%|████▋     | 46252/100000 [13:57:36<8:44:04,  1.71it/s]
Train steps ... :  46%|████▋     | 46253/100000 [13:57:37<8:43:43,  1.71it/s]
Train steps ... :  46%|████▋     | 46254/100000 [13:57:37<8:43:48,  1.71it/s]
Train steps ... :  46%|████▋     | 46255/100000 [13:57:38<8:43:48,  1.71it/s]
Train steps ... :  46%|████▋     | 46256/100000 [13:57:39<8:43:38,  1.71it/s]
Train steps ... :  46%|████▋     | 46257/100000 [13:57:39<8:43:36,  1.71it/s]
Train steps ... :  46%|████▋     | 46258/100000 [13:57:40<8:43:53,  1.71it/s]
Train steps ... :  46%|████▋     | 46259/100000 [13:57:40<8:44:09,  1.71it/s]
Train steps ... :  46%|████▋     | 46260/100000 [13:57:41<8:45:11,  1.71it/s]
Train steps ... :  46%|████▋     | 46261/100000 [13:57:42<8:44:23,  1.71it/s]
Train steps ... :  46%|████▋     | 46262/100000 [13:57:42<8:43:56,  1.71it/s]
Train steps ... :  46%|████▋     | 46263/100000 [13:57:43<8:43:42,  1.71it/s]
Train steps ... :  46%|████▋     | 46264/100000 [13:57:43<8:43:26,  1.71it/s]
Train steps ... :  46%|████▋     | 46265/100000 [13:57:44<8:43:52,  1.71it/s]
Train steps ... :  46%|████▋     | 46266/100000 [13:57:44<8:44:07,  1.71it/s]
Train steps ... :  46%|████▋     | 46267/100000 [13:57:45<8:43:32,  1.71it/s]
Train steps ... :  46%|████▋     | 46268/100000 [13:57:46<8:44:12,  1.71it/s]
Train steps ... :  46%|████▋     | 46269/100000 [13:57:46<8:43:47,  1.71it/s]
Train steps ... :  46%|████▋     | 46270/100000 [13:57:47<8:43:40,  1.71it/s]
Train steps ... :  46%|████▋     | 46271/100000 [13:57:47<8:44:00,  1.71it/s]
Train steps ... :  46%|████▋     | 46272/100000 [13:57:48<8:44:10,  1.71it/s]
Train steps ... :  46%|████▋     | 46273/100000 [13:57:49<8:44:02,  1.71it/s]
Train steps ... :  46%|████▋     | 46274/100000 [13:57:49<8:43:26,  1.71it/s]
Train steps ... :  46%|████▋     | 46275/100000 [13:57:50<8:43:08,  1.71it/s]Step... (46275 / 100000 | Loss: 0.8925217390060425, Learning Rate: 5.399497487437186e-05)
+
                                                                             
Step... (46275 / 100000 | Loss: 1.115161418914795, Learning Rate: 5.399497487437186e-05)
+
Train steps ... :  46%|████▋     | 46275/100000 [13:57:50<8:43:08,  1.71it/s]
Train steps ... :  46%|████▋     | 46276/100000 [13:57:50<8:44:20,  1.71it/s]
Train steps ... :  46%|████▋     | 46277/100000 [13:57:51<8:44:11,  1.71it/s]
Train steps ... :  46%|████▋     | 46278/100000 [13:57:51<8:43:51,  1.71it/s]
Train steps ... :  46%|████▋     | 46279/100000 [13:57:52<8:43:36,  1.71it/s]
Train steps ... :  46%|████▋     | 46280/100000 [13:57:53<8:43:31,  1.71it/s]
Train steps ... :  46%|████▋     | 46281/100000 [13:57:53<8:43:14,  1.71it/s]
Train steps ... :  46%|████▋     | 46282/100000 [13:57:54<8:44:05,  1.71it/s]
Train steps ... :  46%|████▋     | 46283/100000 [13:57:54<8:44:07,  1.71it/s]
Train steps ... :  46%|████▋     | 46284/100000 [13:57:55<8:43:39,  1.71it/s]
Train steps ... :  46%|████▋     | 46285/100000 [13:57:56<8:45:14,  1.70it/s]
Train steps ... :  46%|████▋     | 46286/100000 [13:57:56<8:44:18,  1.71it/s]
Train steps ... :  46%|███��▋     | 46287/100000 [13:57:57<8:44:15,  1.71it/s]
Train steps ... :  46%|████▋     | 46288/100000 [13:57:57<8:43:53,  1.71it/s]
Train steps ... :  46%|████▋     | 46289/100000 [13:57:58<8:43:31,  1.71it/s]
Train steps ... :  46%|████▋     | 46290/100000 [13:57:58<8:43:50,  1.71it/s]
Train steps ... :  46%|████▋     | 46291/100000 [13:57:59<8:44:04,  1.71it/s]
Train steps ... :  46%|████▋     | 46292/100000 [13:58:00<8:43:52,  1.71it/s]
Train steps ... :  46%|████▋     | 46293/100000 [13:58:00<8:43:35,  1.71it/s]
Train steps ... :  46%|████▋     | 46294/100000 [13:58:01<8:42:53,  1.71it/s]
Train steps ... :  46%|████▋     | 46295/100000 [13:58:01<8:42:34,  1.71it/s]
Train steps ... :  46%|████▋     | 46296/100000 [13:58:02<8:42:39,  1.71it/s]
Train steps ... :  46%|████▋     | 46297/100000 [13:58:03<8:43:19,  1.71it/s]
Train steps ... :  46%|████▋     | 46298/100000 [13:58:03<8:43:43,  1.71it/s]
Train steps ... :  46%|████▋     | 46299/100000 [13:58:04<8:43:12,  1.71it/s]
Train steps ... :  46%|████▋     | 46300/100000 [13:58:04<8:43:27,  1.71it/s]Step... (46300 / 100000 | Loss: 0.7063658237457275, Learning Rate: 5.3969849246231163e-05)
+
                                                                             
Step... (46300 / 100000 | Loss: 0.9699430465698242, Learning Rate: 5.3969849246231163e-05)
+
Train steps ... :  46%|████▋     | 46300/100000 [13:58:05<8:43:27,  1.71it/s]
Train steps ... :  46%|████▋     | 46301/100000 [13:58:05<8:43:14,  1.71it/s]
Train steps ... :  46%|████▋     | 46302/100000 [13:58:05<8:43:51,  1.71it/s]
Train steps ... :  46%|████▋     | 46303/100000 [13:58:06<8:43:34,  1.71it/s]
Train steps ... :  46%|████▋     | 46304/100000 [13:58:07<8:43:32,  1.71it/s]
Train steps ... :  46%|████▋     | 46305/100000 [13:58:07<8:43:14,  1.71it/s]
Train steps ... :  46%|████▋     | 46306/100000 [13:58:08<8:43:51,  1.71it/s]
Train steps ... :  46%|████▋     | 46307/100000 [13:58:08<8:43:10,  1.71it/s]
Train steps ... :  46%|████▋     | 46308/100000 [13:58:09<8:43:32,  1.71it/s]
Train steps ... :  46%|████▋     | 46309/100000 [13:58:10<8:43:19,  1.71it/s]
Train steps ... :  46%|████▋     | 46310/100000 [13:58:10<8:43:28,  1.71it/s]
Train steps ... :  46%|████▋     | 46311/100000 [13:58:11<8:44:09,  1.71it/s]
Train steps ... :  46%|████▋     | 46312/100000 [13:58:11<8:43:33,  1.71it/s]
Train steps ... :  46%|████▋     | 46313/100000 [13:58:12<8:43:14,  1.71it/s]
Train steps ... :  46%|████▋     | 46314/100000 [13:58:13<8:43:37,  1.71it/s]
Train steps ... :  46%|████▋     | 46315/100000 [13:58:13<8:43:03,  1.71it/s]
Train steps ... :  46%|████▋     | 46316/100000 [13:58:14<8:43:10,  1.71it/s]
Train steps ... :  46%|████▋     | 46317/100000 [13:58:14<8:43:00,  1.71it/s]
Train steps ... :  46%|████▋     | 46318/100000 [13:58:15<8:42:42,  1.71it/s]
Train steps ... :  46%|████▋     | 46319/100000 [13:58:15<8:43:46,  1.71it/s]
Train steps ... :  46%|████▋     | 46320/100000 [13:58:16<8:43:35,  1.71it/s]
Train steps ... :  46%|████▋     | 46321/100000 [13:58:17<8:44:08,  1.71it/s]
Train steps ... :  46%|████▋     | 46322/100000 [13:58:17<8:43:19,  1.71it/s]
Train steps ... :  46%|████▋     | 46323/100000 [13:58:18<8:43:34,  1.71it/s]
Train steps ... :  46%|████▋     | 46324/100000 [13:58:18<8:43:59,  1.71it/s]
Train steps ... :  46%|████▋     | 46325/100000 [13:58:19<8:43:01,  1.71it/s]Step... (46325 / 100000 | Loss: 0.7687044143676758, Learning Rate: 5.394472361809045e-05)
+
                                                                             
Step... (46325 / 100000 | Loss: 1.3899246454238892, Learning Rate: 5.394472361809045e-05)
+
Train steps ... :  46%|████▋     | 46325/100000 [13:58:19<8:43:01,  1.71it/s]
Train steps ... :  46%|████▋     | 46326/100000 [13:58:20<8:43:45,  1.71it/s]
Train steps ... :  46%|████▋     | 46327/100000 [13:58:20<8:43:19,  1.71it/s]
Train steps ... :  46%|████▋     | 46328/100000 [13:58:21<8:43:10,  1.71it/s]
Train steps ... :  46%|████▋     | 46329/100000 [13:58:21<8:42:50,  1.71it/s]
Train steps ... :  46%|████▋     | 46330/100000 [13:58:22<8:43:19,  1.71it/s]
Train steps ... :  46%|████▋     | 46331/100000 [13:58:22<8:42:44,  1.71it/s]
Train steps ... :  46%|████▋     | 46332/100000 [13:58:23<8:43:11,  1.71it/s]
Train steps ... :  46%|████▋     | 46333/100000 [13:58:24<8:43:53,  1.71it/s]
Train steps ... :  46%|████▋     | 46334/100000 [13:58:24<8:43:20,  1.71it/s]
Train steps ... :  46%|████▋     | 46335/100000 [13:58:25<8:44:20,  1.71it/s]
Train steps ... :  46%|████▋     | 46336/100000 [13:58:25<8:43:57,  1.71it/s]
Train steps ... :  46%|████▋     | 46337/100000 [13:58:26<8:43:37,  1.71it/s]
Train steps ... :  46%|████▋     | 46338/100000 [13:58:27<8:43:29,  1.71it/s]
Train steps ... :  46%|████▋     | 46339/100000 [13:58:27<8:43:20,  1.71it/s]
Train steps ... :  46%|████▋     | 46340/100000 [13:58:28<8:42:57,  1.71it/s]
Train steps ... :  46%|████▋     | 46341/100000 [13:58:28<8:42:42,  1.71it/s]
Train steps ... :  46%|████▋     | 46342/100000 [13:58:29<8:42:38,  1.71it/s]
Train steps ... :  46%|████▋     | 46343/100000 [13:58:29<8:42:28,  1.71it/s]
Train steps ... :  46%|████▋     | 46344/100000 [13:58:30<8:42:14,  1.71it/s]
Train steps ... :  46%|████▋     | 46345/100000 [13:58:31<8:41:59,  1.71it/s]
Train steps ... :  46%|████▋     | 46346/100000 [13:58:31<8:42:46,  1.71it/s]
Train steps ... :  46%|████▋     | 46347/100000 [13:58:32<8:42:41,  1.71it/s]
Train steps ... :  46%|████▋     | 46348/100000 [13:58:32<8:43:08,  1.71it/s]
Train steps ... :  46%|████▋     | 46349/100000 [13:58:33<8:42:38,  1.71it/s]
Train steps ... :  46%|████▋     | 46350/100000 [13:58:34<8:43:25,  1.71it/s]Step... (46350 / 100000 | Loss: 0.9246060848236084, Learning Rate: 5.391959798994976e-05)
+
                                                                             
Step... (46350 / 100000 | Loss: 0.8520466089248657, Learning Rate: 5.391959798994976e-05)
+
Train steps ... :  46%|████▋     | 46350/100000 [13:58:34<8:43:25,  1.71it/s]
Train steps ... :  46%|████▋     | 46351/100000 [13:58:34<8:43:07,  1.71it/s]
Train steps ... :  46%|████▋     | 46352/100000 [13:58:35<8:43:28,  1.71it/s]
Train steps ... :  46%|████▋     | 46353/100000 [13:58:35<8:43:32,  1.71it/s]
Train steps ... :  46%|████▋     | 46354/100000 [13:58:36<8:43:02,  1.71it/s]
Train steps ... :  46%|████▋     | 46355/100000 [13:58:36<8:42:28,  1.71it/s]
Train steps ... :  46%|████▋     | 46356/100000 [13:58:37<8:43:01,  1.71it/s]
Train steps ... :  46%|████▋     | 46357/100000 [13:58:38<8:42:42,  1.71it/s]
Train steps ... :  46%|████▋     | 46358/100000 [13:58:38<8:43:01,  1.71it/s]
Train steps ... :  46%|████▋     | 46359/100000 [13:58:39<8:42:57,  1.71it/s]
Train steps ... :  46%|████▋     | 46360/100000 [13:58:39<8:43:08,  1.71it/s]
Train steps ... :  46%|████▋     | 46361/100000 [13:58:40<8:43:03,  1.71it/s]
Train steps ... :  46%|████▋     | 46362/100000 [13:58:41<8:42:39,  1.71it/s]
Train steps ... :  46%|████▋     | 46363/100000 [13:58:41<8:42:40,  1.71it/s]
Train steps ... :  46%|████▋     | 46364/100000 [13:58:42<8:42:11,  1.71it/s]
Train steps ... :  46%|████▋     | 46365/100000 [13:58:42<8:41:56,  1.71it/s]
Train steps ... :  46%|████▋     | 46366/100000 [13:58:43<8:42:31,  1.71it/s]
Train steps ... :  46%|████▋     | 46367/100000 [13:58:44<8:43:02,  1.71it/s]
Train steps ... :  46%|████▋     | 46368/100000 [13:58:44<8:42:51,  1.71it/s]
Train steps ... :  46%|████▋     | 46369/100000 [13:58:45<8:44:01,  1.71it/s]
Train steps ... :  46%|████▋     | 46370/100000 [13:58:45<8:43:22,  1.71it/s]
Train steps ... :  46%|████▋     | 46371/100000 [13:58:46<8:43:15,  1.71it/s]
Train steps ... :  46%|████▋     | 46372/100000 [13:58:46<8:42:28,  1.71it/s]
Train steps ... :  46%|████▋     | 46373/100000 [13:58:47<8:43:01,  1.71it/s]
Train steps ... :  46%|████▋     | 46374/100000 [13:58:48<8:43:18,  1.71it/s]
Train steps ... :  46%|████▋     | 46375/100000 [13:58:48<8:42:35,  1.71it/s]Step... (46375 / 100000 | Loss: 0.7010402679443359, Learning Rate: 5.3894472361809046e-05)
+
                                                                             
Step... (46375 / 100000 | Loss: 1.1177603006362915, Learning Rate: 5.3894472361809046e-05)
+
Train steps ... :  46%|████▋     | 46375/100000 [13:58:49<8:42:35,  1.71it/s]
Train steps ... :  46%|████▋     | 46376/100000 [13:58:49<8:42:55,  1.71it/s]
Train steps ... :  46%|████▋     | 46377/100000 [13:58:49<8:42:40,  1.71it/s]
Train steps ... :  46%|████▋     | 46378/100000 [13:58:50<8:42:37,  1.71it/s]
Train steps ... :  46%|████▋     | 46379/100000 [13:58:51<8:42:25,  1.71it/s]
Train steps ... :  46%|████▋     | 46380/100000 [13:58:51<8:42:58,  1.71it/s]
Train steps ... :  46%|████▋     | 46381/100000 [13:58:52<8:42:31,  1.71it/s]
Train steps ... :  46%|████▋     | 46382/100000 [13:58:52<8:42:02,  1.71it/s]
Train steps ... :  46%|████▋     | 46383/100000 [13:58:53<8:42:23,  1.71it/s]
Train steps ... :  46%|████▋     | 46384/100000 [13:58:53<8:42:16,  1.71it/s]
Train steps ... :  46%|████▋     | 46385/100000 [13:58:54<8:43:02,  1.71it/s]
Train steps ... :  46%|████▋     | 46386/100000 [13:58:55<8:42:13,  1.71it/s]
Train steps ... :  46%|████▋     | 46387/100000 [13:58:55<8:42:32,  1.71it/s]
Train steps ... :  46%|████▋     | 46388/100000 [13:58:56<8:42:11,  1.71it/s]
Train steps ... :  46%|████▋     | 46389/100000 [13:58:56<8:42:17,  1.71it/s]
Train steps ... :  46%|████▋     | 46390/100000 [13:58:57<8:42:25,  1.71it/s]
Train steps ... :  46%|████▋     | 46391/100000 [13:58:58<8:42:22,  1.71it/s]
Train steps ... :  46%|████▋     | 46392/100000 [13:58:58<8:41:57,  1.71it/s]
Train steps ... :  46%|████▋     | 46393/100000 [13:58:59<8:42:31,  1.71it/s]
Train steps ... :  46%|████▋     | 46394/100000 [13:58:59<8:42:11,  1.71it/s]
Train steps ... :  46%|████▋     | 46395/100000 [13:59:00<8:42:16,  1.71it/s]
Train steps ... :  46%|████▋     | 46396/100000 [13:59:00<8:41:43,  1.71it/s]
Train steps ... :  46%|████▋     | 46397/100000 [13:59:01<8:42:03,  1.71it/s]
Train steps ... :  46%|████▋     | 46398/100000 [13:59:02<8:41:44,  1.71it/s]
Train steps ... :  46%|████▋     | 46399/100000 [13:59:02<8:41:42,  1.71it/s]
Train steps ... :  46%|████▋     | 46400/100000 [13:59:03<8:41:37,  1.71it/s]Step... (46400 / 100000 | Loss: 0.7001620531082153, Learning Rate: 5.386934673366835e-05)
+
                                                                             
Step... (46400 / 100000 | Loss: 0.5723680257797241, Learning Rate: 5.386934673366835e-05)
+
Train steps ... :  46%|████▋     | 46400/100000 [13:59:03<8:41:37,  1.71it/s]
Train steps ... :  46%|████▋     | 46401/100000 [13:59:03<8:42:15,  1.71it/s]
Train steps ... :  46%|████▋     | 46402/100000 [13:59:04<8:42:31,  1.71it/s]
Train steps ... :  46%|████▋     | 46403/100000 [13:59:05<8:42:17,  1.71it/s]
Train steps ... :  46%|████▋     | 46404/100000 [13:59:05<8:43:02,  1.71it/s]
Train steps ... :  46%|████▋     | 46405/100000 [13:59:06<8:43:51,  1.71it/s]
Train steps ... :  46%|████▋     | 46406/100000 [13:59:06<8:43:33,  1.71it/s]
Train steps ... :  46%|████▋     | 46407/100000 [13:59:07<8:42:41,  1.71it/s]
Train steps ... :  46%|████▋     | 46408/100000 [13:59:07<8:42:34,  1.71it/s]
Train steps ... :  46%|████▋     | 46409/100000 [13:59:08<8:43:05,  1.71it/s]
Train steps ... :  46%|████▋     | 46410/100000 [13:59:09<8:42:25,  1.71it/s]
Train steps ... :  46%|████▋     | 46411/100000 [13:59:09<8:42:11,  1.71it/s]
Train steps ... :  46%|████▋     | 46412/100000 [13:59:10<8:42:11,  1.71it/s]
Train steps ... :  46%|████▋     | 46413/100000 [13:59:10<8:42:13,  1.71it/s]
Train steps ... :  46%|████▋     | 46414/100000 [13:59:11<8:41:51,  1.71it/s]
Train steps ... :  46%|████▋     | 46415/100000 [13:59:12<8:42:01,  1.71it/s]
Train steps ... :  46%|████▋     | 46416/100000 [13:59:12<8:41:47,  1.71it/s]
Train steps ... :  46%|████▋     | 46417/100000 [13:59:13<8:42:23,  1.71it/s]
Train steps ... :  46%|████▋     | 46418/100000 [13:59:13<8:42:09,  1.71it/s]
Train steps ... :  46%|████▋     | 46419/100000 [13:59:14<8:42:25,  1.71it/s]
Train steps ... :  46%|████▋     | 46420/100000 [13:59:15<8:42:06,  1.71it/s]
Train steps ... :  46%|████▋     | 46421/100000 [13:59:15<8:43:04,  1.71it/s]
Train steps ... :  46%|████▋     | 46422/100000 [13:59:16<8:42:41,  1.71it/s]
Train steps ... :  46%|████▋     | 46423/100000 [13:59:16<8:43:04,  1.71it/s]
Train steps ... :  46%|████▋     | 46424/100000 [13:59:17<8:42:59,  1.71it/s]
Train steps ... :  46%|████▋     | 46425/100000 [13:59:17<8:42:16,  1.71it/s]Step... (46425 / 100000 | Loss: 0.800506055355072, Learning Rate: 5.384422110552764e-05)
+
                                                                             
Step... (46425 / 100000 | Loss: 0.9510554075241089, Learning Rate: 5.384422110552764e-05)
+
Train steps ... :  46%|████▋     | 46425/100000 [13:59:18<8:42:16,  1.71it/s]
Train steps ... :  46%|████▋     | 46426/100000 [13:59:18<8:42:23,  1.71it/s]
Train steps ... :  46%|████▋     | 46427/100000 [13:59:19<8:41:54,  1.71it/s]
Train steps ... :  46%|████▋     | 46428/100000 [13:59:19<8:41:52,  1.71it/s]
Train steps ... :  46%|████▋     | 46429/100000 [13:59:20<8:42:06,  1.71it/s]
Train steps ... :  46%|████▋     | 46430/100000 [13:59:20<8:42:02,  1.71it/s]
Train steps ... :  46%|████▋     | 46431/100000 [13:59:21<8:42:09,  1.71it/s]
Train steps ... :  46%|████▋     | 46432/100000 [13:59:22<8:42:55,  1.71it/s]
Train steps ... :  46%|████▋     | 46433/100000 [13:59:22<8:42:46,  1.71it/s]
Train steps ... :  46%|████▋     | 46434/100000 [13:59:23<8:42:33,  1.71it/s]
Train steps ... :  46%|████▋     | 46435/100000 [13:59:23<8:41:58,  1.71it/s]
Train steps ... :  46%|████▋     | 46436/100000 [13:59:24<8:41:33,  1.71it/s]
Train steps ... :  46%|████▋     | 46437/100000 [13:59:24<8:41:16,  1.71it/s]
Train steps ... :  46%|████▋     | 46438/100000 [13:59:25<8:41:38,  1.71it/s]
Train steps ... :  46%|████▋     | 46439/100000 [13:59:26<8:41:37,  1.71it/s]
Train steps ... :  46%|████▋     | 46440/100000 [13:59:26<8:41:44,  1.71it/s]
Train steps ... :  46%|████▋     | 46441/100000 [13:59:27<8:41:38,  1.71it/s]
Train steps ... :  46%|████▋     | 46442/100000 [13:59:27<8:41:15,  1.71it/s]
Train steps ... :  46%|████▋     | 46443/100000 [13:59:28<8:41:55,  1.71it/s]
Train steps ... :  46%|████▋     | 46444/100000 [13:59:29<8:42:03,  1.71it/s]
Train steps ... :  46%|████▋     | 46445/100000 [13:59:29<8:41:45,  1.71it/s]
Train steps ... :  46%|████▋     | 46446/100000 [13:59:30<8:41:35,  1.71it/s]
Train steps ... :  46%|████▋     | 46447/100000 [13:59:30<8:43:01,  1.71it/s]
Train steps ... :  46%|████▋     | 46448/100000 [13:59:31<8:42:37,  1.71it/s]
Train steps ... :  46%|████▋     | 46449/100000 [13:59:31<8:42:43,  1.71it/s]
Train steps ... :  46%|████▋     | 46450/100000 [13:59:32<8:43:15,  1.71it/s]Step... (46450 / 100000 | Loss: 1.1378087997436523, Learning Rate: 5.3819095477386936e-05)
+
                                                                             
Step... (46450 / 100000 | Loss: 0.6939520835876465, Learning Rate: 5.3819095477386936e-05)
+
Train steps ... :  46%|████▋     | 46450/100000 [13:59:32<8:43:15,  1.71it/s]
Train steps ... :  46%|████▋     | 46451/100000 [13:59:33<8:42:37,  1.71it/s]
Train steps ... :  46%|████▋     | 46452/100000 [13:59:33<8:42:16,  1.71it/s]
Train steps ... :  46%|████▋     | 46453/100000 [13:59:34<8:42:00,  1.71it/s]
Train steps ... :  46%|████▋     | 46454/100000 [13:59:34<8:42:09,  1.71it/s]
Train steps ... :  46%|████▋     | 46455/100000 [13:59:35<8:42:38,  1.71it/s]
Train steps ... :  46%|████▋     | 46456/100000 [13:59:36<8:42:25,  1.71it/s]
Train steps ... :  46%|████▋     | 46457/100000 [13:59:36<8:42:17,  1.71it/s]
Train steps ... :  46%|████▋     | 46458/100000 [13:59:37<8:41:58,  1.71it/s]
Train steps ... :  46%|████▋     | 46459/100000 [13:59:37<8:41:36,  1.71it/s]
Train steps ... :  46%|████▋     | 46460/100000 [13:59:38<8:42:18,  1.71it/s]
Train steps ... :  46%|████▋     | 46461/100000 [13:59:38<8:42:43,  1.71it/s]
Train steps ... :  46%|████▋     | 46462/100000 [13:59:39<8:42:12,  1.71it/s]
Train steps ... :  46%|████▋     | 46463/100000 [13:59:40<8:41:38,  1.71it/s]
Train steps ... :  46%|████▋     | 46464/100000 [13:59:40<8:41:59,  1.71it/s]
Train steps ... :  46%|████▋     | 46465/100000 [13:59:41<8:42:30,  1.71it/s]
Train steps ... :  46%|████▋     | 46466/100000 [13:59:41<8:41:54,  1.71it/s]
Train steps ... :  46%|████▋     | 46467/100000 [13:59:42<8:42:30,  1.71it/s]
Train steps ... :  46%|████▋     | 46468/100000 [13:59:43<8:42:07,  1.71it/s]
Train steps ... :  46%|████▋     | 46469/100000 [13:59:43<8:42:26,  1.71it/s]
Train steps ... :  46%|████▋     | 46470/100000 [13:59:44<8:42:29,  1.71it/s]
Train steps ... :  46%|████▋     | 46471/100000 [13:59:44<8:42:09,  1.71it/s]
Train steps ... :  46%|████▋     | 46472/100000 [13:59:45<8:42:01,  1.71it/s]
Train steps ... :  46%|████▋     | 46473/100000 [13:59:46<8:42:01,  1.71it/s]
Train steps ... :  46%|████▋     | 46474/100000 [13:59:46<8:41:55,  1.71it/s]
Train steps ... :  46%|████▋     | 46475/100000 [13:59:47<8:41:45,  1.71it/s]Step... (46475 / 100000 | Loss: 0.843021035194397, Learning Rate: 5.3793969849246226e-05)
+
                                                                             
Step... (46475 / 100000 | Loss: 0.7626298666000366, Learning Rate: 5.3793969849246226e-05)
+
Train steps ... :  46%|████▋     | 46475/100000 [13:59:47<8:41:45,  1.71it/s]
Train steps ... :  46%|████▋     | 46476/100000 [13:59:47<8:41:54,  1.71it/s]
Train steps ... :  46%|████▋     | 46477/100000 [13:59:48<8:41:26,  1.71it/s]
Train steps ... :  46%|████▋     | 46478/100000 [13:59:48<8:41:29,  1.71it/s]
Train steps ... :  46%|████▋     | 46479/100000 [13:59:49<8:42:16,  1.71it/s]
Train steps ... :  46%|████▋     | 46480/100000 [13:59:50<8:41:53,  1.71it/s]
Train steps ... :  46%|████▋     | 46481/100000 [13:59:50<8:41:39,  1.71it/s]
Train steps ... :  46%|████▋     | 46482/100000 [13:59:51<8:41:24,  1.71it/s]
Train steps ... :  46%|████▋     | 46483/100000 [13:59:51<8:41:40,  1.71it/s]
Train steps ... :  46%|████▋     | 46484/100000 [13:59:52<8:42:09,  1.71it/s]
Train steps ... :  46%|████▋     | 46485/100000 [13:59:53<8:41:30,  1.71it/s]
Train steps ... :  46%|████▋     | 46486/100000 [13:59:53<8:41:28,  1.71it/s]
Train steps ... :  46%|████▋     | 46487/100000 [13:59:54<8:41:23,  1.71it/s]
Train steps ... :  46%|█��██▋     | 46488/100000 [13:59:54<8:41:00,  1.71it/s]
Train steps ... :  46%|████▋     | 46489/100000 [13:59:55<8:41:14,  1.71it/s]
Train steps ... :  46%|████▋     | 46490/100000 [13:59:55<8:41:56,  1.71it/s]
Train steps ... :  46%|████▋     | 46491/100000 [13:59:56<8:41:38,  1.71it/s]
Train steps ... :  46%|████▋     | 46492/100000 [13:59:57<8:41:11,  1.71it/s]
Train steps ... :  46%|████▋     | 46493/100000 [13:59:57<8:41:16,  1.71it/s]
Train steps ... :  46%|████▋     | 46494/100000 [13:59:58<8:41:54,  1.71it/s]
Train steps ... :  46%|████▋     | 46495/100000 [13:59:58<8:41:33,  1.71it/s]
Train steps ... :  46%|████▋     | 46496/100000 [13:59:59<8:41:07,  1.71it/s]
Train steps ... :  46%|████▋     | 46497/100000 [14:00:00<8:41:31,  1.71it/s]
Train steps ... :  46%|████▋     | 46498/100000 [14:00:00<8:41:59,  1.71it/s]
Train steps ... :  46%|████▋     | 46499/100000 [14:00:01<8:41:33,  1.71it/s]
Train steps ... :  46%|████▋     | 46500/100000 [14:00:01<8:41:07,  1.71it/s]Step... (46500 / 100000 | Loss: 0.9264671802520752, Learning Rate: 5.376884422110553e-05)
+
                                                                             
Step... (46500 / 100000 | Loss: 0.7603546977043152, Learning Rate: 5.376884422110553e-05)
+
Train steps ... :  46%|████▋     | 46500/100000 [14:00:02<8:41:07,  1.71it/s]
Train steps ... :  47%|████▋     | 46501/100000 [14:00:02<8:41:16,  1.71it/s]
Train steps ... :  47%|████▋     | 46502/100000 [14:00:02<8:41:26,  1.71it/s]
Train steps ... :  47%|████▋     | 46503/100000 [14:00:03<8:41:09,  1.71it/s]
Train steps ... :  47%|████▋     | 46504/100000 [14:00:04<8:40:55,  1.71it/s]
Train steps ... :  47%|████▋     | 46505/100000 [14:00:04<8:41:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46506/100000 [14:00:05<8:40:50,  1.71it/s]
Train steps ... :  47%|████▋     | 46507/100000 [14:00:05<8:41:14,  1.71it/s]
Train steps ... :  47%|████▋     | 46508/100000 [14:00:06<8:41:36,  1.71it/s]
Train steps ... :  47%|████▋     | 46509/100000 [14:00:07<8:41:52,  1.71it/s]
Train steps ... :  47%|████▋     | 46510/100000 [14:00:07<8:41:37,  1.71it/s]
Train steps ... :  47%|████▋     | 46511/100000 [14:00:08<8:41:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46512/100000 [14:00:08<8:42:39,  1.71it/s]
Train steps ... :  47%|████▋     | 46513/100000 [14:00:09<8:41:47,  1.71it/s]
Train steps ... :  47%|████▋     | 46514/100000 [14:00:09<8:41:26,  1.71it/s]
Train steps ... :  47%|████▋     | 46515/100000 [14:00:10<8:41:10,  1.71it/s]
Train steps ... :  47%|████▋     | 46516/100000 [14:00:11<8:40:27,  1.71it/s]
Train steps ... :  47%|████▋     | 46517/100000 [14:00:11<8:40:07,  1.71it/s]
Train steps ... :  47%|████▋     | 46518/100000 [14:00:12<8:40:32,  1.71it/s]
Train steps ... :  47%|████▋     | 46519/100000 [14:00:12<8:41:25,  1.71it/s]
Train steps ... :  47%|████▋     | 46520/100000 [14:00:13<8:40:47,  1.71it/s]
Train steps ... :  47%|████▋     | 46521/100000 [14:00:14<8:41:00,  1.71it/s]
Train steps ... :  47%|████▋     | 46522/100000 [14:00:14<8:41:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46523/100000 [14:00:15<8:41:04,  1.71it/s]
Train steps ... :  47%|████▋     | 46524/100000 [14:00:15<8:40:45,  1.71it/s]
Train steps ... :  47%|████▋     | 46525/100000 [14:00:16<8:40:49,  1.71it/s]Step... (46525 / 100000 | Loss: 0.8297961950302124, Learning Rate: 5.374371859296483e-05)
+
                                                                             
Step... (46525 / 100000 | Loss: 0.8331350088119507, Learning Rate: 5.374371859296483e-05)
+
Train steps ... :  47%|████▋     | 46525/100000 [14:00:16<8:40:49,  1.71it/s]
Train steps ... :  47%|████▋     | 46526/100000 [14:00:17<8:41:25,  1.71it/s]
Train steps ... :  47%|████▋     | 46527/100000 [14:00:17<8:40:46,  1.71it/s]
Train steps ... :  47%|████▋     | 46528/100000 [14:00:18<8:41:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46529/100000 [14:00:18<8:40:53,  1.71it/s]
Train steps ... :  47%|████▋     | 46530/100000 [14:00:19<8:41:27,  1.71it/s]
Train steps ... :  47%|████▋     | 46531/100000 [14:00:19<8:41:12,  1.71it/s]
Train steps ... :  47%|████▋     | 46532/100000 [14:00:20<8:40:57,  1.71it/s]
Train steps ... :  47%|████▋     | 46533/100000 [14:00:21<8:40:29,  1.71it/s]
Train steps ... :  47%|████▋     | 46534/100000 [14:00:21<8:40:26,  1.71it/s]
Train steps ... :  47%|████▋     | 46535/100000 [14:00:22<8:40:19,  1.71it/s]
Train steps ... :  47%|████▋     | 46536/100000 [14:00:22<8:40:43,  1.71it/s]
Train steps ... :  47%|████▋     | 46537/100000 [14:00:23<8:40:44,  1.71it/s]
Train steps ... :  47%|████▋     | 46538/100000 [14:00:24<8:41:16,  1.71it/s]
Train steps ... :  47%|████▋     | 46539/100000 [14:00:24<8:40:56,  1.71it/s]
Train steps ... :  47%|████▋     | 46540/100000 [14:00:25<8:41:24,  1.71it/s]
Train steps ... :  47%|████▋     | 46541/100000 [14:00:25<8:41:30,  1.71it/s]
Train steps ... :  47%|████▋     | 46542/100000 [14:00:26<8:41:14,  1.71it/s]
Train steps ... :  47%|████▋     | 46543/100000 [14:00:26<8:41:58,  1.71it/s]
Train steps ... :  47%|████▋     | 46544/100000 [14:00:27<8:41:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46545/100000 [14:00:28<8:41:07,  1.71it/s]
Train steps ... :  47%|████▋     | 46546/100000 [14:00:28<8:40:50,  1.71it/s]
Train steps ... :  47%|████▋     | 46547/100000 [14:00:29<8:40:41,  1.71it/s]
Train steps ... :  47%|████▋     | 46548/100000 [14:00:29<8:40:44,  1.71it/s]
Train steps ... :  47%|████▋     | 46549/100000 [14:00:30<8:40:35,  1.71it/s]
Train steps ... :  47%|████▋     | 46550/100000 [14:00:31<8:40:22,  1.71it/s]Step... (46550 / 100000 | Loss: 0.7666639685630798, Learning Rate: 5.371859296482412e-05)
+
                                                                             
Step... (46550 / 100000 | Loss: 1.0840448141098022, Learning Rate: 5.371859296482412e-05)
+
Train steps ... :  47%|████▋     | 46550/100000 [14:00:31<8:40:22,  1.71it/s]
Train steps ... :  47%|████▋     | 46551/100000 [14:00:31<8:41:10,  1.71it/s]
Train steps ... :  47%|████▋     | 46552/100000 [14:00:32<8:41:04,  1.71it/s]
Train steps ... :  47%|████▋     | 46553/100000 [14:00:32<8:40:34,  1.71it/s]
Train steps ... :  47%|████▋     | 46554/100000 [14:00:33<8:40:44,  1.71it/s]
Train steps ... :  47%|████▋     | 46555/100000 [14:00:33<8:41:15,  1.71it/s]
Train steps ... :  47%|████▋     | 46556/100000 [14:00:34<8:40:46,  1.71it/s]
Train steps ... :  47%|████▋     | 46557/100000 [14:00:35<8:40:58,  1.71it/s]
Train steps ... :  47%|████▋     | 46558/100000 [14:00:35<8:41:18,  1.71it/s]
Train steps ... :  47%|████▋     | 46559/100000 [14:00:36<8:41:52,  1.71it/s]
Train steps ... :  47%|████▋     | 46560/100000 [14:00:36<8:41:10,  1.71it/s]
Train steps ... :  47%|████▋     | 46561/100000 [14:00:37<8:40:46,  1.71it/s]
Train steps ... :  47%|████▋     | 46562/100000 [14:00:38<8:40:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46563/100000 [14:00:38<8:40:18,  1.71it/s]
Train steps ... :  47%|████▋     | 46564/100000 [14:00:39<8:40:06,  1.71it/s]
Train steps ... :  47%|████▋     | 46565/100000 [14:00:39<8:40:06,  1.71it/s]
Train steps ... :  47%|████▋     | 46566/100000 [14:00:40<8:40:38,  1.71it/s]
Train steps ... :  47%|████▋     | 46567/100000 [14:00:40<8:40:31,  1.71it/s]
Train steps ... :  47%|████▋     | 46568/100000 [14:00:41<8:41:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46569/100000 [14:00:42<8:41:20,  1.71it/s]
Train steps ... :  47%|████▋     | 46570/100000 [14:00:42<8:41:16,  1.71it/s]
Train steps ... :  47%|████▋     | 46571/100000 [14:00:43<8:41:45,  1.71it/s]
Train steps ... :  47%|████▋     | 46572/100000 [14:00:43<8:41:02,  1.71it/s]
Train steps ... :  47%|████▋     | 46573/100000 [14:00:44<8:40:36,  1.71it/s]
Train steps ... :  47%|████▋     | 46574/100000 [14:00:45<8:40:34,  1.71it/s]
Train steps ... :  47%|████▋     | 46575/100000 [14:00:45<8:40:21,  1.71it/s]Step... (46575 / 100000 | Loss: 0.6703322529792786, Learning Rate: 5.3693467336683426e-05)
+
                                                                             
Step... (46575 / 100000 | Loss: 0.6951804161071777, Learning Rate: 5.3693467336683426e-05)
+
Train steps ... :  47%|████▋     | 46575/100000 [14:00:45<8:40:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46576/100000 [14:00:46<8:40:54,  1.71it/s]
Train steps ... :  47%|████▋     | 46577/100000 [14:00:46<8:40:41,  1.71it/s]
Train steps ... :  47%|████▋     | 46578/100000 [14:00:47<8:41:01,  1.71it/s]
Train steps ... :  47%|████▋     | 46579/100000 [14:00:48<8:41:06,  1.71it/s]
Train steps ... :  47%|████▋     | 46580/100000 [14:00:48<8:40:48,  1.71it/s]
Train steps ... :  47%|████▋     | 46581/100000 [14:00:49<8:40:44,  1.71it/s]
Train steps ... :  47%|████▋     | 46582/100000 [14:00:49<8:40:16,  1.71it/s]
Train steps ... :  47%|████▋     | 46583/100000 [14:00:50<8:40:17,  1.71it/s]
Train steps ... :  47%|████▋     | 46584/100000 [14:00:50<8:40:26,  1.71it/s]
Train steps ... :  47%|████▋     | 46585/100000 [14:00:51<8:40:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46586/100000 [14:00:52<8:40:31,  1.71it/s]
Train steps ... :  47%|████▋     | 46587/100000 [14:00:52<8:40:32,  1.71it/s]
Train steps ... :  47%|████▋     | 46588/100000 [14:00:53<8:40:49,  1.71it/s]
Train steps ... :  47%|████▋     | 46589/100000 [14:00:53<8:40:06,  1.71it/s]
Train steps ... :  47%|████▋     | 46590/100000 [14:00:54<8:40:52,  1.71it/s]
Train steps ... :  47%|████▋     | 46591/100000 [14:00:55<8:40:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46592/100000 [14:00:55<8:41:27,  1.71it/s]
Train steps ... :  47%|████▋     | 46593/100000 [14:00:56<8:41:58,  1.71it/s]
Train steps ... :  47%|████▋     | 46594/100000 [14:00:56<8:42:02,  1.71it/s]
Train steps ... :  47%|████▋     | 46595/100000 [14:00:57<8:41:09,  1.71it/s]
Train steps ... :  47%|████▋     | 46596/100000 [14:00:57<8:41:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46597/100000 [14:00:58<8:41:10,  1.71it/s]
Train steps ... :  47%|████▋     | 46598/100000 [14:00:59<8:40:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46599/100000 [14:00:59<8:39:59,  1.71it/s]
Train steps ... :  47%|████▋     | 46600/100000 [14:01:00<8:40:05,  1.71it/s]Step... (46600 / 100000 | Loss: 0.8374233245849609, Learning Rate: 5.3668341708542716e-05)
+
                                                                             
Step... (46600 / 100000 | Loss: 0.7397444248199463, Learning Rate: 5.3668341708542716e-05)
+
Train steps ... :  47%|████▋     | 46600/100000 [14:01:00<8:40:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46601/100000 [14:01:00<8:40:40,  1.71it/s]
Train steps ... :  47%|████▋     | 46602/100000 [14:01:01<8:40:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46603/100000 [14:01:02<8:40:20,  1.71it/s]
Train steps ... :  47%|████▋     | 46604/100000 [14:01:02<8:40:04,  1.71it/s]
Train steps ... :  47%|████▋     | 46605/100000 [14:01:03<8:40:09,  1.71it/s]
Train steps ... :  47%|████▋     | 46606/100000 [14:01:03<8:40:18,  1.71it/s]
Train steps ... :  47%|████▋     | 46607/100000 [14:01:04<8:40:11,  1.71it/s]
Train steps ... :  47%|████▋     | 46608/100000 [14:01:04<8:40:53,  1.71it/s]
Train steps ... :  47%|████▋     | 46609/100000 [14:01:05<8:40:43,  1.71it/s]
Train steps ... :  47%|████▋     | 46610/100000 [14:01:06<8:40:56,  1.71it/s]
Train steps ... :  47%|████▋     | 46611/100000 [14:01:06<8:40:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46612/100000 [14:01:07<8:40:00,  1.71it/s]
Train steps ... :  47%|████▋     | 46613/100000 [14:01:07<8:40:12,  1.71it/s]
Train steps ... :  47%|████▋     | 46614/100000 [14:01:08<8:40:03,  1.71it/s]
Train steps ... :  47%|████▋     | 46615/100000 [14:01:09<8:40:18,  1.71it/s]
Train steps ... :  47%|████▋     | 46616/100000 [14:01:09<8:40:22,  1.71it/s]
Train steps ... :  47%|████▋     | 46617/100000 [14:01:10<8:40:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46618/100000 [14:01:10<8:40:15,  1.71it/s]
Train steps ... :  47%|████▋     | 46619/100000 [14:01:11<8:40:03,  1.71it/s]
Train steps ... :  47%|████▋     | 46620/100000 [14:01:11<8:40:28,  1.71it/s]
Train steps ... :  47%|████▋     | 46621/100000 [14:01:12<8:40:00,  1.71it/s]
Train steps ... :  47%|████▋     | 46622/100000 [14:01:13<8:39:56,  1.71it/s]
Train steps ... :  47%|████▋     | 46623/100000 [14:01:13<8:40:26,  1.71it/s]
Train steps ... :  47%|████▋     | 46624/100000 [14:01:14<8:39:57,  1.71it/s]
Train steps ... :  47%|████▋     | 46625/100000 [14:01:14<8:40:36,  1.71it/s]Step... (46625 / 100000 | Loss: 0.7193863391876221, Learning Rate: 5.364321608040201e-05)
+
                                                                             
Step... (46625 / 100000 | Loss: 0.7371046543121338, Learning Rate: 5.364321608040201e-05)
+
Train steps ... :  47%|████▋     | 46625/100000 [14:01:15<8:40:36,  1.71it/s]
Train steps ... :  47%|████▋     | 46626/100000 [14:01:15<8:40:07,  1.71it/s]
Train steps ... :  47%|████▋     | 46627/100000 [14:01:16<8:40:03,  1.71it/s]
Train steps ... :  47%|████▋     | 46628/100000 [14:01:16<8:39:54,  1.71it/s]
Train steps ... :  47%|████▋     | 46629/100000 [14:01:17<8:40:09,  1.71it/s]
Train steps ... :  47%|████▋     | 46630/100000 [14:01:17<8:40:04,  1.71it/s]
Train steps ... :  47%|████▋     | 46631/100000 [14:01:18<8:39:54,  1.71it/s]
Train steps ... :  47%|████▋     | 46632/100000 [14:01:18<8:39:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46633/100000 [14:01:19<8:40:08,  1.71it/s]
Train steps ... :  47%|████▋     | 46634/100000 [14:01:20<8:41:00,  1.71it/s]
Train steps ... :  47%|████▋     | 46635/100000 [14:01:20<8:40:26,  1.71it/s]
Train steps ... :  47%|████▋     | 46636/100000 [14:01:21<8:39:54,  1.71it/s]
Train steps ... :  47%|████▋     | 46637/100000 [14:01:21<8:39:44,  1.71it/s]
Train steps ... :  47%|████▋     | 46638/100000 [14:01:22<8:39:29,  1.71it/s]
Train steps ... :  47%|████▋     | 46639/100000 [14:01:23<8:40:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46640/100000 [14:01:23<8:40:06,  1.71it/s]
Train steps ... :  47%|████▋     | 46641/100000 [14:01:24<8:40:44,  1.71it/s]
Train steps ... :  47%|████▋     | 46642/100000 [14:01:24<8:40:01,  1.71it/s]
Train steps ... :  47%|████▋     | 46643/100000 [14:01:25<8:39:52,  1.71it/s]
Train steps ... :  47%|████▋     | 46644/100000 [14:01:26<8:40:00,  1.71it/s]
Train steps ... :  47%|████▋     | 46645/100000 [14:01:26<8:40:47,  1.71it/s]
Train steps ... :  47%|████▋     | 46646/100000 [14:01:27<8:40:11,  1.71it/s]
Train steps ... :  47%|████▋     | 46647/100000 [14:01:27<8:40:04,  1.71it/s]
Train steps ... :  47%|████▋     | 46648/100000 [14:01:28<8:40:09,  1.71it/s]
Train steps ... :  47%|████▋     | 46649/100000 [14:01:28<8:40:08,  1.71it/s]
Train steps ... :  47%|████▋     | 46650/100000 [14:01:29<8:39:58,  1.71it/s]Step... (46650 / 100000 | Loss: 1.0455833673477173, Learning Rate: 5.36180904522613e-05)
+
                                                                             
Step... (46650 / 100000 | Loss: 0.914300799369812, Learning Rate: 5.36180904522613e-05)
+
Train steps ... :  47%|████▋     | 46650/100000 [14:01:29<8:39:58,  1.71it/s]
Train steps ... :  47%|████▋     | 46651/100000 [14:01:30<8:40:02,  1.71it/s]
Train steps ... :  47%|████▋     | 46652/100000 [14:01:30<8:39:29,  1.71it/s]
Train steps ... :  47%|████▋     | 46653/100000 [14:01:31<8:39:39,  1.71it/s]
Train steps ... :  47%|████▋     | 46654/100000 [14:01:31<8:40:10,  1.71it/s]
Train steps ... :  47%|████▋     | 46655/100000 [14:01:32<8:40:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46656/100000 [14:01:33<8:39:47,  1.71it/s]
Train steps ... :  47%|████▋     | 46657/100000 [14:01:33<8:39:43,  1.71it/s]
Train steps ... :  47%|████▋     | 46658/100000 [14:01:34<8:39:47,  1.71it/s]
Train steps ... :  47%|████▋     | 46659/100000 [14:01:34<8:40:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46660/100000 [14:01:35<8:40:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46661/100000 [14:01:35<8:40:33,  1.71it/s]
Train steps ... :  47%|████▋     | 46662/100000 [14:01:36<8:39:48,  1.71it/s]
Train steps ... :  47%|████▋     | 46663/100000 [14:01:37<8:39:40,  1.71it/s]
Train steps ... :  47%|████▋     | 46664/100000 [14:01:37<8:39:24,  1.71it/s]
Train steps ... :  47%|████▋     | 46665/100000 [14:01:38<8:40:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46666/100000 [14:01:38<8:41:12,  1.71it/s]
Train steps ... :  47%|████▋     | 46667/100000 [14:01:39<8:40:11,  1.71it/s]
Train steps ... :  47%|████▋     | 46668/100000 [14:01:40<8:40:24,  1.71it/s]
Train steps ... :  47%|████▋     | 46669/100000 [14:01:40<8:39:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46670/100000 [14:01:41<8:39:37,  1.71it/s]
Train steps ... :  47%|████▋     | 46671/100000 [14:01:41<8:39:42,  1.71it/s]
Train steps ... :  47%|████▋     | 46672/100000 [14:01:42<8:39:32,  1.71it/s]
Train steps ... :  47%|████▋     | 46673/100000 [14:01:42<8:39:09,  1.71it/s]
Train steps ... :  47%|████▋     | 46674/100000 [14:01:43<8:39:01,  1.71it/s]
Train steps ... :  47%|████▋     | 46675/100000 [14:01:44<8:38:51,  1.71it/s]Step... (46675 / 100000 | Loss: 0.6435068845748901, Learning Rate: 5.3592964824120606e-05)
+
                                                                             
Step... (46675 / 100000 | Loss: 0.6009932160377502, Learning Rate: 5.3592964824120606e-05)
+
Train steps ... :  47%|████▋     | 46675/100000 [14:01:44<8:38:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46676/100000 [14:01:44<8:39:45,  1.71it/s]
Train steps ... :  47%|████▋     | 46677/100000 [14:01:45<8:39:19,  1.71it/s]
Train steps ... :  47%|████▋     | 46678/100000 [14:01:45<8:39:09,  1.71it/s]
Train steps ... :  47%|████▋     | 46679/100000 [14:01:46<8:40:07,  1.71it/s]
Train steps ... :  47%|████▋     | 46680/100000 [14:01:47<8:39:46,  1.71it/s]
Train steps ... :  47%|████▋     | 46681/100000 [14:01:47<8:39:59,  1.71it/s]
Train steps ... :  47%|████▋     | 46682/100000 [14:01:48<8:39:55,  1.71it/s]
Train steps ... :  47%|████▋     | 46683/100000 [14:01:48<8:40:06,  1.71it/s]
Train steps ... :  47%|████▋     | 46684/100000 [14:01:49<8:39:31,  1.71it/s]
Train steps ... :  47%|████▋     | 46685/100000 [14:01:49<8:39:57,  1.71it/s]
Train steps ... :  47%|████▋     | 46686/100000 [14:01:50<8:39:36,  1.71it/s]
Train steps ... :  47%|████▋     | 46687/100000 [14:01:51<8:39:59,  1.71it/s]
Train steps ... :  47%|████▋     | 46688/100000 [14:01:51<8:39:42,  1.71it/s]
Train steps ... :  47%|��███▋     | 46689/100000 [14:01:52<8:39:56,  1.71it/s]
Train steps ... :  47%|████▋     | 46690/100000 [14:01:52<8:40:36,  1.71it/s]
Train steps ... :  47%|████▋     | 46691/100000 [14:01:53<8:39:59,  1.71it/s]
Train steps ... :  47%|████▋     | 46692/100000 [14:01:54<8:39:22,  1.71it/s]
Train steps ... :  47%|████▋     | 46693/100000 [14:01:54<8:39:47,  1.71it/s]
Train steps ... :  47%|████▋     | 46694/100000 [14:01:55<8:39:31,  1.71it/s]
Train steps ... :  47%|████▋     | 46695/100000 [14:01:55<8:40:19,  1.71it/s]
Train steps ... :  47%|████▋     | 46696/100000 [14:01:56<8:39:46,  1.71it/s]
Train steps ... :  47%|████▋     | 46697/100000 [14:01:57<8:39:07,  1.71it/s]
Train steps ... :  47%|████▋     | 46698/100000 [14:01:57<8:39:00,  1.71it/s]
Train steps ... :  47%|████▋     | 46699/100000 [14:01:58<8:38:52,  1.71it/s]
Train steps ... :  47%|████▋     | 46700/100000 [14:01:58<8:39:09,  1.71it/s]Step... (46700 / 100000 | Loss: 0.7036781311035156, Learning Rate: 5.356783919597991e-05)
+
                                                                             
Step... (46700 / 100000 | Loss: 0.7607567310333252, Learning Rate: 5.356783919597991e-05)
+
Train steps ... :  47%|████▋     | 46700/100000 [14:01:59<8:39:09,  1.71it/s]
Train steps ... :  47%|████▋     | 46701/100000 [14:01:59<8:39:49,  1.71it/s]
Train steps ... :  47%|████▋     | 46702/100000 [14:01:59<8:39:26,  1.71it/s]
Train steps ... :  47%|████▋     | 46703/100000 [14:02:00<8:39:02,  1.71it/s]
Train steps ... :  47%|████▋     | 46704/100000 [14:02:01<8:39:37,  1.71it/s]
Train steps ... :  47%|████▋     | 46705/100000 [14:02:01<8:39:22,  1.71it/s]
Train steps ... :  47%|████▋     | 46706/100000 [14:02:02<8:38:48,  1.71it/s]
Train steps ... :  47%|████▋     | 46707/100000 [14:02:02<8:39:24,  1.71it/s]
Train steps ... :  47%|████▋     | 46708/100000 [14:02:03<8:38:46,  1.71it/s]
Train steps ... :  47%|████▋     | 46709/100000 [14:02:04<8:39:06,  1.71it/s]
Train steps ... :  47%|████▋     | 46710/100000 [14:02:04<8:39:03,  1.71it/s]
Train steps ... :  47%|████▋     | 46711/100000 [14:02:05<8:39:38,  1.71it/s]
Train steps ... :  47%|████▋     | 46712/100000 [14:02:05<8:38:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46713/100000 [14:02:06<8:38:48,  1.71it/s]
Train steps ... :  47%|████▋     | 46714/100000 [14:02:06<8:38:56,  1.71it/s]
Train steps ... :  47%|████▋     | 46715/100000 [14:02:07<8:39:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46716/100000 [14:02:08<8:39:19,  1.71it/s]
Train steps ... :  47%|████▋     | 46717/100000 [14:02:08<8:39:36,  1.71it/s]
Train steps ... :  47%|████▋     | 46718/100000 [14:02:09<8:39:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46719/100000 [14:02:09<8:38:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46720/100000 [14:02:10<8:38:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46721/100000 [14:02:11<8:38:49,  1.71it/s]
Train steps ... :  47%|████▋     | 46722/100000 [14:02:11<8:38:33,  1.71it/s]
Train steps ... :  47%|████▋     | 46723/100000 [14:02:12<8:38:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46724/100000 [14:02:12<8:39:39,  1.71it/s]
Train steps ... :  47%|████▋     | 46725/100000 [14:02:13<8:39:40,  1.71it/s]Step... (46725 / 100000 | Loss: 0.5690608024597168, Learning Rate: 5.35427135678392e-05)
+
                                                                             
Step... (46725 / 100000 | Loss: 1.0680837631225586, Learning Rate: 5.35427135678392e-05)
+
Train steps ... :  47%|████▋     | 46725/100000 [14:02:13<8:39:40,  1.71it/s]
Train steps ... :  47%|████▋     | 46726/100000 [14:02:13<8:39:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46727/100000 [14:02:14<8:39:31,  1.71it/s]
Train steps ... :  47%|████▋     | 46728/100000 [14:02:15<8:39:41,  1.71it/s]
Train steps ... :  47%|████▋     | 46729/100000 [14:02:15<8:40:11,  1.71it/s]
Train steps ... :  47%|████▋     | 46730/100000 [14:02:16<8:40:30,  1.71it/s]
Train steps ... :  47%|████▋     | 46731/100000 [14:02:16<8:40:16,  1.71it/s]
Train steps ... :  47%|████▋     | 46732/100000 [14:02:17<8:39:43,  1.71it/s]
Train steps ... :  47%|████▋     | 46733/100000 [14:02:18<8:39:14,  1.71it/s]
Train steps ... :  47%|████▋     | 46734/100000 [14:02:18<8:39:15,  1.71it/s]
Train steps ... :  47%|████▋     | 46735/100000 [14:02:19<8:38:44,  1.71it/s]
Train steps ... :  47%|████▋     | 46736/100000 [14:02:19<8:39:02,  1.71it/s]
Train steps ... :  47%|████▋     | 46737/100000 [14:02:20<8:38:29,  1.71it/s]
Train steps ... :  47%|████▋     | 46738/100000 [14:02:20<8:38:43,  1.71it/s]
Train steps ... :  47%|████▋     | 46739/100000 [14:02:21<8:38:37,  1.71it/s]
Train steps ... :  47%|████▋     | 46740/100000 [14:02:22<8:38:50,  1.71it/s]
Train steps ... :  47%|████▋     | 46741/100000 [14:02:22<8:39:02,  1.71it/s]
Train steps ... :  47%|████▋     | 46742/100000 [14:02:23<8:38:43,  1.71it/s]
Train steps ... :  47%|████▋     | 46743/100000 [14:02:23<8:38:57,  1.71it/s]
Train steps ... :  47%|████▋     | 46744/100000 [14:02:24<8:38:44,  1.71it/s]
Train steps ... :  47%|████▋     | 46745/100000 [14:02:25<8:39:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46746/100000 [14:02:25<8:38:45,  1.71it/s]
Train steps ... :  47%|████▋     | 46747/100000 [14:02:26<8:39:22,  1.71it/s]
Train steps ... :  47%|████▋     | 46748/100000 [14:02:26<8:39:45,  1.71it/s]
Train steps ... :  47%|████▋     | 46749/100000 [14:02:27<8:39:02,  1.71it/s]
Train steps ... :  47%|████▋     | 46750/100000 [14:02:28<8:38:53,  1.71it/s]Step... (46750 / 100000 | Loss: 0.9093396663665771, Learning Rate: 5.3517587939698496e-05)
+
                                                                             
Step... (46750 / 100000 | Loss: 1.0105712413787842, Learning Rate: 5.3517587939698496e-05)
+
Train steps ... :  47%|████▋     | 46750/100000 [14:02:28<8:38:53,  1.71it/s]
Train steps ... :  47%|████▋     | 46751/100000 [14:02:28<8:39:46,  1.71it/s]
Train steps ... :  47%|████▋     | 46752/100000 [14:02:29<8:39:04,  1.71it/s]
Train steps ... :  47%|████▋     | 46753/100000 [14:02:29<8:39:37,  1.71it/s]
Train steps ... :  47%|████▋     | 46754/100000 [14:02:30<8:38:43,  1.71it/s]
Train steps ... :  47%|████▋     | 46755/100000 [14:02:30<8:39:41,  1.71it/s]
Train steps ... :  47%|████▋     | 46756/100000 [14:02:31<8:38:59,  1.71it/s]
Train steps ... :  47%|████▋     | 46757/100000 [14:02:32<8:38:33,  1.71it/s]
Train steps ... :  47%|████▋     | 46758/100000 [14:02:32<8:39:18,  1.71it/s]
Train steps ... :  47%|████▋     | 46759/100000 [14:02:33<8:39:01,  1.71it/s]
Train steps ... :  47%|████▋     | 46760/100000 [14:02:33<8:38:50,  1.71it/s]
Train steps ... :  47%|████▋     | 46761/100000 [14:02:34<8:39:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46762/100000 [14:02:35<8:39:35,  1.71it/s]
Train steps ... :  47%|████▋     | 46763/100000 [14:02:35<8:39:18,  1.71it/s]
Train steps ... :  47%|████▋     | 46764/100000 [14:02:36<8:39:27,  1.71it/s]
Train steps ... :  47%|████▋     | 46765/100000 [14:02:36<8:38:55,  1.71it/s]
Train steps ... :  47%|████▋     | 46766/100000 [14:02:37<8:38:39,  1.71it/s]
Train steps ... :  47%|████▋     | 46767/100000 [14:02:37<8:38:52,  1.71it/s]
Train steps ... :  47%|████▋     | 46768/100000 [14:02:38<8:39:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46769/100000 [14:02:39<8:38:42,  1.71it/s]
Train steps ... :  47%|████▋     | 46770/100000 [14:02:39<8:38:52,  1.71it/s]
Train steps ... :  47%|████▋     | 46771/100000 [14:02:40<8:38:45,  1.71it/s]
Train steps ... :  47%|████▋     | 46772/100000 [14:02:40<8:39:08,  1.71it/s]
Train steps ... :  47%|████▋     | 46773/100000 [14:02:41<8:39:32,  1.71it/s]
Train steps ... :  47%|████▋     | 46774/100000 [14:02:42<8:39:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46775/100000 [14:02:42<8:38:59,  1.71it/s]Step... (46775 / 100000 | Loss: 0.93714839220047, Learning Rate: 5.349246231155779e-05)
+
                                                                             
Step... (46775 / 100000 | Loss: 0.7963144779205322, Learning Rate: 5.349246231155779e-05)
+
Train steps ... :  47%|████▋     | 46775/100000 [14:02:42<8:38:59,  1.71it/s]
Train steps ... :  47%|████▋     | 46776/100000 [14:02:43<8:39:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46777/100000 [14:02:43<8:38:41,  1.71it/s]
Train steps ... :  47%|████▋     | 46778/100000 [14:02:44<8:38:41,  1.71it/s]
Train steps ... :  47%|████▋     | 46779/100000 [14:02:44<8:38:33,  1.71it/s]
Train steps ... :  47%|████▋     | 46780/100000 [14:02:45<8:38:16,  1.71it/s]
Train steps ... :  47%|████▋     | 46781/100000 [14:02:46<8:38:33,  1.71it/s]
Train steps ... :  47%|████▋     | 46782/100000 [14:02:46<8:38:15,  1.71it/s]
Train steps ... :  47%|████▋     | 46783/100000 [14:02:47<8:38:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46784/100000 [14:02:47<8:38:54,  1.71it/s]
Train steps ... :  47%|████▋     | 46785/100000 [14:02:48<8:38:35,  1.71it/s]
Train steps ... :  47%|████▋     | 46786/100000 [14:02:49<8:39:22,  1.71it/s]
Train steps ... :  47%|████▋     | 46787/100000 [14:02:49<8:38:39,  1.71it/s]
Train steps ... :  47%|████▋     | 46788/100000 [14:02:50<8:38:47,  1.71it/s]
Train steps ... :  47%|████▋     | 46789/100000 [14:02:50<8:39:20,  1.71it/s]
Train steps ... :  47%|████▋     | 46790/100000 [14:02:51<8:38:32,  1.71it/s]
Train steps ... :  47%|████▋     | 46791/100000 [14:02:51<8:39:07,  1.71it/s]
Train steps ... :  47%|████▋     | 46792/100000 [14:02:52<8:38:15,  1.71it/s]
Train steps ... :  47%|████▋     | 46793/100000 [14:02:53<8:38:44,  1.71it/s]
Train steps ... :  47%|████▋     | 46794/100000 [14:02:53<8:39:02,  1.71it/s]
Train steps ... :  47%|████▋     | 46795/100000 [14:02:54<8:38:30,  1.71it/s]
Train steps ... :  47%|████▋     | 46796/100000 [14:02:54<8:38:29,  1.71it/s]
Train steps ... :  47%|████▋     | 46797/100000 [14:02:55<8:38:58,  1.71it/s]
Train steps ... :  47%|████▋     | 46798/100000 [14:02:56<8:39:00,  1.71it/s]
Train steps ... :  47%|████▋     | 46799/100000 [14:02:56<8:38:43,  1.71it/s]
Train steps ... :  47%|████▋     | 46800/100000 [14:02:57<8:38:27,  1.71it/s]Step... (46800 / 100000 | Loss: 0.8916724920272827, Learning Rate: 5.346733668341709e-05)
+
                                                                             
Step... (46800 / 100000 | Loss: 0.5475828051567078, Learning Rate: 5.346733668341709e-05)
+
Train steps ... :  47%|████▋     | 46800/100000 [14:02:57<8:38:27,  1.71it/s]
Train steps ... :  47%|████▋     | 46801/100000 [14:02:57<8:38:38,  1.71it/s]
Train steps ... :  47%|████▋     | 46802/100000 [14:02:58<8:38:23,  1.71it/s]
Train steps ... :  47%|████▋     | 46803/100000 [14:02:59<8:38:22,  1.71it/s]
Train steps ... :  47%|████▋     | 46804/100000 [14:02:59<8:38:10,  1.71it/s]
Train steps ... :  47%|████▋     | 46805/100000 [14:03:00<8:38:06,  1.71it/s]
Train steps ... :  47%|████▋     | 46806/100000 [14:03:00<8:38:02,  1.71it/s]
Train steps ... :  47%|████▋     | 46807/100000 [14:03:01<8:38:04,  1.71it/s]
Train steps ... :  47%|████▋     | 46808/100000 [14:03:01<8:37:53,  1.71it/s]
Train steps ... :  47%|████▋     | 46809/100000 [14:03:02<8:38:46,  1.71it/s]
Train steps ... :  47%|████▋     | 46810/100000 [14:03:03<8:38:28,  1.71it/s]
Train steps ... :  47%|████▋     | 46811/100000 [14:03:03<8:37:52,  1.71it/s]
Train steps ... :  47%|████▋     | 46812/100000 [14:03:04<8:38:36,  1.71it/s]
Train steps ... :  47%|████▋     | 46813/100000 [14:03:04<8:38:32,  1.71it/s]
Train steps ... :  47%|████▋     | 46814/100000 [14:03:05<8:39:23,  1.71it/s]
Train steps ... :  47%|████▋     | 46815/100000 [14:03:06<8:39:07,  1.71it/s]
Train steps ... :  47%|████▋     | 46816/100000 [14:03:06<8:39:09,  1.71it/s]
Train steps ... :  47%|████▋     | 46817/100000 [14:03:07<8:38:06,  1.71it/s]
Train steps ... :  47%|████▋     | 46818/100000 [14:03:07<8:38:17,  1.71it/s]
Train steps ... :  47%|████▋     | 46819/100000 [14:03:08<8:38:07,  1.71it/s]
Train steps ... :  47%|████▋     | 46820/100000 [14:03:08<8:38:40,  1.71it/s]
Train steps ... :  47%|████▋     | 46821/100000 [14:03:09<8:38:03,  1.71it/s]
Train steps ... :  47%|████▋     | 46822/100000 [14:03:10<8:38:37,  1.71it/s]
Train steps ... :  47%|████▋     | 46823/100000 [14:03:10<8:38:54,  1.71it/s]
Train steps ... :  47%|████▋     | 46824/100000 [14:03:11<8:38:50,  1.71it/s]
Train steps ... :  47%|████▋     | 46825/100000 [14:03:11<8:38:45,  1.71it/s]Step... (46825 / 100000 | Loss: 1.196629285812378, Learning Rate: 5.344221105527638e-05)
+
                                                                             
Step... (46825 / 100000 | Loss: 1.0782043933868408, Learning Rate: 5.344221105527638e-05)
+
Train steps ... :  47%|████▋     | 46825/100000 [14:03:12<8:38:45,  1.71it/s]
Train steps ... :  47%|████▋     | 46826/100000 [14:03:12<8:38:34,  1.71it/s]
Train steps ... :  47%|████▋     | 46827/100000 [14:03:13<8:38:24,  1.71it/s]
Train steps ... :  47%|████▋     | 46828/100000 [14:03:13<8:38:06,  1.71it/s]
Train steps ... :  47%|████▋     | 46829/100000 [14:03:14<8:38:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46830/100000 [14:03:14<8:37:35,  1.71it/s]
Train steps ... :  47%|████▋     | 46831/100000 [14:03:15<8:37:27,  1.71it/s]
Train steps ... :  47%|████▋     | 46832/100000 [14:03:15<8:37:08,  1.71it/s]
Train steps ... :  47%|████▋     | 46833/100000 [14:03:16<8:37:46,  1.71it/s]
Train steps ... :  47%|████▋     | 46834/100000 [14:03:17<8:37:37,  1.71it/s]
Train steps ... :  47%|████▋     | 46835/100000 [14:03:17<8:37:35,  1.71it/s]
Train steps ... :  47%|████▋     | 46836/100000 [14:03:18<8:38:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46837/100000 [14:03:18<8:37:39,  1.71it/s]
Train steps ... :  47%|████▋     | 46838/100000 [14:03:19<8:37:43,  1.71it/s]
Train steps ... :  47%|████▋     | 46839/100000 [14:03:20<8:38:18,  1.71it/s]
Train steps ... :  47%|████▋     | 46840/100000 [14:03:20<8:39:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46841/100000 [14:03:21<8:39:18,  1.71it/s]
Train steps ... :  47%|████▋     | 46842/100000 [14:03:21<8:39:23,  1.71it/s]
Train steps ... :  47%|████▋     | 46843/100000 [14:03:22<8:37:57,  1.71it/s]
Train steps ... :  47%|████▋     | 46844/100000 [14:03:22<8:38:39,  1.71it/s]
Train steps ... :  47%|████▋     | 46845/100000 [14:03:23<8:38:38,  1.71it/s]
Train steps ... :  47%|████▋     | 46846/100000 [14:03:24<8:38:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46847/100000 [14:03:24<8:38:14,  1.71it/s]
Train steps ... :  47%|████▋     | 46848/100000 [14:03:25<8:38:01,  1.71it/s]
Train steps ... :  47%|████▋     | 46849/100000 [14:03:25<8:38:08,  1.71it/s]
Train steps ... :  47%|████▋     | 46850/100000 [14:03:26<8:37:31,  1.71it/s]Step... (46850 / 100000 | Loss: 0.7861756086349487, Learning Rate: 5.341708542713568e-05)
+
                                                                             
Step... (46850 / 100000 | Loss: 0.8585013151168823, Learning Rate: 5.341708542713568e-05)
+
Train steps ... :  47%|████▋     | 46850/100000 [14:03:26<8:37:31,  1.71it/s]
Train steps ... :  47%|████▋     | 46851/100000 [14:03:27<8:37:35,  1.71it/s]
Train steps ... :  47%|████▋     | 46852/100000 [14:03:27<8:37:34,  1.71it/s]
Train steps ... :  47%|████▋     | 46853/100000 [14:03:28<8:38:54,  1.71it/s]
Train steps ... :  47%|████▋     | 46854/100000 [14:03:28<8:38:49,  1.71it/s]
Train steps ... :  47%|████▋     | 46855/100000 [14:03:29<8:38:37,  1.71it/s]
Train steps ... :  47%|████▋     | 46856/100000 [14:03:30<8:38:28,  1.71it/s]
Train steps ... :  47%|████▋     | 46857/100000 [14:03:30<8:38:08,  1.71it/s]
Train steps ... :  47%|████▋     | 46858/100000 [14:03:31<8:37:54,  1.71it/s]
Train steps ... :  47%|████▋     | 46859/100000 [14:03:31<8:38:43,  1.71it/s]
Train steps ... :  47%|████▋     | 46860/100000 [14:03:32<8:38:15,  1.71it/s]
Train steps ... :  47%|████▋     | 46861/100000 [14:03:32<8:38:28,  1.71it/s]
Train steps ... :  47%|████▋     | 46862/100000 [14:03:33<8:38:27,  1.71it/s]
Train steps ... :  47%|████▋     | 46863/100000 [14:03:34<8:38:27,  1.71it/s]
Train steps ... :  47%|████▋     | 46864/100000 [14:03:34<8:38:44,  1.71it/s]
Train steps ... :  47%|████▋     | 46865/100000 [14:03:35<8:38:12,  1.71it/s]
Train steps ... :  47%|████▋     | 46866/100000 [14:03:35<8:38:30,  1.71it/s]
Train steps ... :  47%|████▋     | 46867/100000 [14:03:36<8:38:18,  1.71it/s]
Train steps ... :  47%|████▋     | 46868/100000 [14:03:37<8:38:28,  1.71it/s]
Train steps ... :  47%|████▋     | 46869/100000 [14:03:37<8:37:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46870/100000 [14:03:38<8:37:46,  1.71it/s]
Train steps ... :  47%|████▋     | 46871/100000 [14:03:38<8:38:20,  1.71it/s]
Train steps ... :  47%|████▋     | 46872/100000 [14:03:39<8:37:19,  1.71it/s]
Train steps ... :  47%|████▋     | 46873/100000 [14:03:39<8:37:28,  1.71it/s]
Train steps ... :  47%|████▋     | 46874/100000 [14:03:40<8:37:45,  1.71it/s]
Train steps ... :  47%|████▋     | 46875/100000 [14:03:41<8:38:05,  1.71it/s]Step... (46875 / 100000 | Loss: 0.7643203735351562, Learning Rate: 5.339195979899497e-05)
+
                                                                             
Step... (46875 / 100000 | Loss: 0.7484831809997559, Learning Rate: 5.339195979899497e-05)
+
Train steps ... :  47%|████▋     | 46875/100000 [14:03:41<8:38:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46876/100000 [14:03:41<8:38:09,  1.71it/s]
Train steps ... :  47%|████▋     | 46877/100000 [14:03:42<8:37:48,  1.71it/s]
Train steps ... :  47%|████▋     | 46878/100000 [14:03:42<8:38:57,  1.71it/s]
Train steps ... :  47%|████▋     | 46879/100000 [14:03:43<8:38:31,  1.71it/s]
Train steps ... :  47%|████▋     | 46880/100000 [14:03:44<8:38:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46881/100000 [14:03:44<8:37:39,  1.71it/s]
Train steps ... :  47%|████▋     | 46882/100000 [14:03:45<8:38:48,  1.71it/s]
Train steps ... :  47%|████▋     | 46883/100000 [14:03:45<8:38:49,  1.71it/s]
Train steps ... :  47%|████▋     | 46884/100000 [14:03:46<8:38:22,  1.71it/s]
Train steps ... :  47%|████▋     | 46885/100000 [14:03:46<8:37:48,  1.71it/s]
Train steps ... :  47%|████▋     | 46886/100000 [14:03:47<8:38:04,  1.71it/s]
Train steps ... :  47%|████▋     | 46887/100000 [14:03:48<8:38:14,  1.71it/s]
Train steps ... :  47%|████▋     | 46888/100000 [14:03:48<8:37:57,  1.71it/s]
Train steps ... :  47%|████▋     | 46889/100000 [14:03:49<8:37:32,  1.71it/s]
Train steps ... :  47%|█��██▋     | 46890/100000 [14:03:49<8:37:43,  1.71it/s]
Train steps ... :  47%|████▋     | 46891/100000 [14:03:50<8:38:26,  1.71it/s]
Train steps ... :  47%|████▋     | 46892/100000 [14:03:51<8:38:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46893/100000 [14:03:51<8:37:52,  1.71it/s]
Train steps ... :  47%|████▋     | 46894/100000 [14:03:52<8:38:52,  1.71it/s]
Train steps ... :  47%|████▋     | 46895/100000 [14:03:52<8:38:53,  1.71it/s]
Train steps ... :  47%|████▋     | 46896/100000 [14:03:53<8:38:27,  1.71it/s]
Train steps ... :  47%|████▋     | 46897/100000 [14:03:54<8:38:12,  1.71it/s]
Train steps ... :  47%|████▋     | 46898/100000 [14:03:54<8:38:17,  1.71it/s]
Train steps ... :  47%|████▋     | 46899/100000 [14:03:55<8:37:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46900/100000 [14:03:55<8:38:13,  1.71it/s]Step... (46900 / 100000 | Loss: 0.6376140713691711, Learning Rate: 5.3366834170854276e-05)
+
                                                                             
Step... (46900 / 100000 | Loss: 0.9235012531280518, Learning Rate: 5.3366834170854276e-05)
+
Train steps ... :  47%|████▋     | 46900/100000 [14:03:56<8:38:13,  1.71it/s]
Train steps ... :  47%|████▋     | 46901/100000 [14:03:56<8:38:25,  1.71it/s]
Train steps ... :  47%|████▋     | 46902/100000 [14:03:56<8:39:13,  1.70it/s]
Train steps ... :  47%|████▋     | 46903/100000 [14:03:57<8:38:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46904/100000 [14:03:58<8:38:31,  1.71it/s]
Train steps ... :  47%|████▋     | 46905/100000 [14:03:58<8:38:16,  1.71it/s]
Train steps ... :  47%|████▋     | 46906/100000 [14:03:59<8:38:06,  1.71it/s]
Train steps ... :  47%|████▋     | 46907/100000 [14:03:59<8:37:52,  1.71it/s]
Train steps ... :  47%|████▋     | 46908/100000 [14:04:00<8:37:31,  1.71it/s]
Train steps ... :  47%|████▋     | 46909/100000 [14:04:01<8:37:19,  1.71it/s]
Train steps ... :  47%|████▋     | 46910/100000 [14:04:01<8:37:17,  1.71it/s]
Train steps ... :  47%|████▋     | 46911/100000 [14:04:02<8:38:14,  1.71it/s]
Train steps ... :  47%|████▋     | 46912/100000 [14:04:02<8:38:25,  1.71it/s]
Train steps ... :  47%|████▋     | 46913/100000 [14:04:03<8:38:12,  1.71it/s]
Train steps ... :  47%|████▋     | 46914/100000 [14:04:03<8:38:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46915/100000 [14:04:04<8:38:11,  1.71it/s]
Train steps ... :  47%|████▋     | 46916/100000 [14:04:05<8:38:01,  1.71it/s]
Train steps ... :  47%|████▋     | 46917/100000 [14:04:05<8:37:20,  1.71it/s]
Train steps ... :  47%|████▋     | 46918/100000 [14:04:06<8:37:52,  1.71it/s]
Train steps ... :  47%|████▋     | 46919/100000 [14:04:06<8:38:14,  1.71it/s]
Train steps ... :  47%|████▋     | 46920/100000 [14:04:07<8:37:53,  1.71it/s]
Train steps ... :  47%|████▋     | 46921/100000 [14:04:08<8:37:20,  1.71it/s]
Train steps ... :  47%|████▋     | 46922/100000 [14:04:08<8:37:27,  1.71it/s]
Train steps ... :  47%|████▋     | 46923/100000 [14:04:09<8:36:50,  1.71it/s]
Train steps ... :  47%|████▋     | 46924/100000 [14:04:09<8:36:57,  1.71it/s]
Train steps ... :  47%|████▋     | 46925/100000 [14:04:10<8:36:37,  1.71it/s]Step... (46925 / 100000 | Loss: 0.7503794431686401, Learning Rate: 5.334170854271357e-05)
+
                                                                             
Step... (46925 / 100000 | Loss: 0.7190534472465515, Learning Rate: 5.334170854271357e-05)
+
Train steps ... :  47%|████▋     | 46925/100000 [14:04:10<8:36:37,  1.71it/s]
Train steps ... :  47%|████▋     | 46926/100000 [14:04:10<8:37:06,  1.71it/s]
Train steps ... :  47%|████▋     | 46927/100000 [14:04:11<8:37:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46928/100000 [14:04:12<8:37:05,  1.71it/s]
Train steps ... :  47%|████▋     | 46929/100000 [14:04:12<8:36:45,  1.71it/s]
Train steps ... :  47%|████▋     | 46930/100000 [14:04:13<8:36:37,  1.71it/s]
Train steps ... :  47%|████▋     | 46931/100000 [14:04:13<8:36:36,  1.71it/s]
Train steps ... :  47%|████▋     | 46932/100000 [14:04:14<8:36:40,  1.71it/s]
Train steps ... :  47%|████▋     | 46933/100000 [14:04:15<8:37:11,  1.71it/s]
Train steps ... :  47%|████▋     | 46934/100000 [14:04:15<8:37:37,  1.71it/s]
Train steps ... :  47%|████▋     | 46935/100000 [14:04:16<8:36:36,  1.71it/s]
Train steps ... :  47%|████▋     | 46936/100000 [14:04:16<8:36:38,  1.71it/s]
Train steps ... :  47%|████▋     | 46937/100000 [14:04:17<8:36:54,  1.71it/s]
Train steps ... :  47%|████▋     | 46938/100000 [14:04:17<8:37:15,  1.71it/s]
Train steps ... :  47%|████▋     | 46939/100000 [14:04:18<8:37:07,  1.71it/s]
Train steps ... :  47%|████▋     | 46940/100000 [14:04:19<8:37:22,  1.71it/s]
Train steps ... :  47%|████▋     | 46941/100000 [14:04:19<8:38:25,  1.71it/s]
Train steps ... :  47%|████▋     | 46942/100000 [14:04:20<8:38:15,  1.71it/s]
Train steps ... :  47%|████▋     | 46943/100000 [14:04:20<8:37:32,  1.71it/s]
Train steps ... :  47%|████▋     | 46944/100000 [14:04:21<8:36:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46945/100000 [14:04:22<8:36:49,  1.71it/s]
Train steps ... :  47%|████▋     | 46946/100000 [14:04:22<8:37:14,  1.71it/s]
Train steps ... :  47%|████▋     | 46947/100000 [14:04:23<8:36:55,  1.71it/s]
Train steps ... :  47%|████▋     | 46948/100000 [14:04:23<8:36:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46949/100000 [14:04:24<8:36:32,  1.71it/s]
Train steps ... :  47%|████▋     | 46950/100000 [14:04:25<8:36:19,  1.71it/s]Step... (46950 / 100000 | Loss: 0.7975716590881348, Learning Rate: 5.331658291457287e-05)
+
                                                                             
Step... (46950 / 100000 | Loss: 1.160685658454895, Learning Rate: 5.331658291457287e-05)
+
Train steps ... :  47%|████▋     | 46950/100000 [14:04:25<8:36:19,  1.71it/s]
Train steps ... :  47%|████▋     | 46951/100000 [14:04:25<8:36:12,  1.71it/s]
Train steps ... :  47%|████▋     | 46952/100000 [14:04:26<8:36:25,  1.71it/s]
Train steps ... :  47%|████▋     | 46953/100000 [14:04:26<8:36:10,  1.71it/s]
Train steps ... :  47%|████▋     | 46954/100000 [14:04:27<8:36:50,  1.71it/s]
Train steps ... :  47%|████▋     | 46955/100000 [14:04:27<8:36:18,  1.71it/s]
Train steps ... :  47%|████▋     | 46956/100000 [14:04:28<8:36:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46957/100000 [14:04:29<8:36:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46958/100000 [14:04:29<8:37:10,  1.71it/s]
Train steps ... :  47%|████▋     | 46959/100000 [14:04:30<8:37:07,  1.71it/s]
Train steps ... :  47%|████▋     | 46960/100000 [14:04:30<8:37:23,  1.71it/s]
Train steps ... :  47%|████▋     | 46961/100000 [14:04:31<8:37:23,  1.71it/s]
Train steps ... :  47%|████▋     | 46962/100000 [14:04:32<8:36:41,  1.71it/s]
Train steps ... :  47%|████▋     | 46963/100000 [14:04:32<8:37:04,  1.71it/s]
Train steps ... :  47%|████▋     | 46964/100000 [14:04:33<8:36:59,  1.71it/s]
Train steps ... :  47%|████▋     | 46965/100000 [14:04:33<8:37:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46966/100000 [14:04:34<8:36:53,  1.71it/s]
Train steps ... :  47%|████▋     | 46967/100000 [14:04:34<8:36:24,  1.71it/s]
Train steps ... :  47%|████▋     | 46968/100000 [14:04:35<8:36:45,  1.71it/s]
Train steps ... :  47%|████▋     | 46969/100000 [14:04:36<8:37:09,  1.71it/s]
Train steps ... :  47%|████▋     | 46970/100000 [14:04:36<8:37:04,  1.71it/s]
Train steps ... :  47%|████▋     | 46971/100000 [14:04:37<8:37:11,  1.71it/s]
Train steps ... :  47%|████▋     | 46972/100000 [14:04:37<8:36:49,  1.71it/s]
Train steps ... :  47%|████▋     | 46973/100000 [14:04:38<8:37:24,  1.71it/s]
Train steps ... :  47%|████▋     | 46974/100000 [14:04:39<8:37:17,  1.71it/s]
Train steps ... :  47%|████▋     | 46975/100000 [14:04:39<8:37:03,  1.71it/s]Step... (46975 / 100000 | Loss: 0.7859479784965515, Learning Rate: 5.3291457286432165e-05)
+
                                                                             
Step... (46975 / 100000 | Loss: 0.6394953727722168, Learning Rate: 5.3291457286432165e-05)
+
Train steps ... :  47%|████▋     | 46975/100000 [14:04:39<8:37:03,  1.71it/s]
Train steps ... :  47%|████▋     | 46976/100000 [14:04:40<8:37:21,  1.71it/s]
Train steps ... :  47%|████▋     | 46977/100000 [14:04:40<8:36:49,  1.71it/s]
Train steps ... :  47%|████▋     | 46978/100000 [14:04:41<8:37:42,  1.71it/s]
Train steps ... :  47%|████▋     | 46979/100000 [14:04:41<8:36:57,  1.71it/s]
Train steps ... :  47%|████▋     | 46980/100000 [14:04:42<8:36:34,  1.71it/s]
Train steps ... :  47%|████▋     | 46981/100000 [14:04:43<8:35:58,  1.71it/s]
Train steps ... :  47%|████▋     | 46982/100000 [14:04:43<8:35:48,  1.71it/s]
Train steps ... :  47%|████▋     | 46983/100000 [14:04:44<8:36:26,  1.71it/s]
Train steps ... :  47%|████▋     | 46984/100000 [14:04:44<8:37:09,  1.71it/s]
Train steps ... :  47%|████▋     | 46985/100000 [14:04:45<8:36:12,  1.71it/s]
Train steps ... :  47%|████▋     | 46986/100000 [14:04:46<8:35:44,  1.71it/s]
Train steps ... :  47%|████▋     | 46987/100000 [14:04:46<8:35:56,  1.71it/s]
Train steps ... :  47%|████▋     | 46988/100000 [14:04:47<8:36:39,  1.71it/s]
Train steps ... :  47%|████▋     | 46989/100000 [14:04:47<8:36:51,  1.71it/s]
Train steps ... :  47%|████▋     | 46990/100000 [14:04:48<8:36:41,  1.71it/s]
Train steps ... :  47%|████▋     | 46991/100000 [14:04:48<8:36:08,  1.71it/s]
Train steps ... :  47%|████▋     | 46992/100000 [14:04:49<8:35:58,  1.71it/s]
Train steps ... :  47%|████▋     | 46993/100000 [14:04:50<8:35:54,  1.71it/s]
Train steps ... :  47%|████▋     | 46994/100000 [14:04:50<8:36:03,  1.71it/s]
Train steps ... :  47%|████▋     | 46995/100000 [14:04:51<8:36:02,  1.71it/s]
Train steps ... :  47%|████▋     | 46996/100000 [14:04:51<8:35:47,  1.71it/s]
Train steps ... :  47%|████▋     | 46997/100000 [14:04:52<8:36:02,  1.71it/s]
Train steps ... :  47%|████▋     | 46998/100000 [14:04:53<8:36:41,  1.71it/s]
Train steps ... :  47%|████▋     | 46999/100000 [14:04:53<8:36:38,  1.71it/s]
Train steps ... :  47%|████▋     | 47000/100000 [14:04:54<8:36:39,  1.71it/s]Step... (47000 / 100000 | Loss: 0.8763388395309448, Learning Rate: 5.3266331658291455e-05)
+
                                                                             
Step... (47000 / 100000 | Loss: 0.9292571544647217, Learning Rate: 5.3266331658291455e-05)
+
Train steps ... :  47%|████▋     | 47000/100000 [14:04:54<8:36:39,  1.71it/s]
Train steps ... :  47%|████▋     | 47001/100000 [14:04:54<8:37:09,  1.71it/s]
Train steps ... :  47%|████▋     | 47002/100000 [14:04:55<8:37:33,  1.71it/s]
Train steps ... :  47%|████▋     | 47003/100000 [14:04:56<8:37:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47004/100000 [14:04:56<8:36:25,  1.71it/s]
Train steps ... :  47%|████▋     | 47005/100000 [14:04:57<8:36:05,  1.71it/s]
Train steps ... :  47%|████▋     | 47006/100000 [14:04:57<8:36:07,  1.71it/s]
Train steps ... :  47%|████▋     | 47007/100000 [14:04:58<8:35:55,  1.71it/s]
Train steps ... :  47%|████▋     | 47008/100000 [14:04:58<8:35:49,  1.71it/s]
Train steps ... :  47%|████▋     | 47009/100000 [14:04:59<8:36:52,  1.71it/s]
Train steps ... :  47%|████▋     | 47010/100000 [14:05:00<8:36:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47011/100000 [14:05:00<8:36:55,  1.71it/s]
Train steps ... :  47%|████▋     | 47012/100000 [14:05:01<8:36:18,  1.71it/s]
Train steps ... :  47%|████▋     | 47013/100000 [14:05:01<8:36:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47014/100000 [14:05:02<8:36:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47015/100000 [14:05:03<8:36:58,  1.71it/s]
Train steps ... :  47%|████▋     | 47016/100000 [14:05:03<8:37:09,  1.71it/s]
Train steps ... :  47%|████▋     | 47017/100000 [14:05:04<8:36:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47018/100000 [14:05:04<8:37:41,  1.71it/s]
Train steps ... :  47%|████▋     | 47019/100000 [14:05:05<8:37:12,  1.71it/s]
Train steps ... :  47%|████▋     | 47020/100000 [14:05:05<8:37:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47021/100000 [14:05:06<8:36:38,  1.71it/s]
Train steps ... :  47%|████▋     | 47022/100000 [14:05:07<8:36:42,  1.71it/s]
Train steps ... :  47%|████▋     | 47023/100000 [14:05:07<8:36:31,  1.71it/s]
Train steps ... :  47%|████▋     | 47024/100000 [14:05:08<8:35:53,  1.71it/s]
Train steps ... :  47%|████▋     | 47025/100000 [14:05:08<8:36:01,  1.71it/s]Step... (47025 / 100000 | Loss: 1.0108293294906616, Learning Rate: 5.324120603015076e-05)
+
                                                                             
Step... (47025 / 100000 | Loss: 0.8637237548828125, Learning Rate: 5.324120603015076e-05)
+
Train steps ... :  47%|████▋     | 47025/100000 [14:05:09<8:36:01,  1.71it/s]
Train steps ... :  47%|████▋     | 47026/100000 [14:05:09<8:36:43,  1.71it/s]
Train steps ... :  47%|████▋     | 47027/100000 [14:05:10<8:36:45,  1.71it/s]
Train steps ... :  47%|████▋     | 47028/100000 [14:05:10<8:36:51,  1.71it/s]
Train steps ... :  47%|████▋     | 47029/100000 [14:05:11<8:36:23,  1.71it/s]
Train steps ... :  47%|████▋     | 47030/100000 [14:05:11<8:36:10,  1.71it/s]
Train steps ... :  47%|████▋     | 47031/100000 [14:05:12<8:36:18,  1.71it/s]
Train steps ... :  47%|████▋     | 47032/100000 [14:05:12<8:36:31,  1.71it/s]
Train steps ... :  47%|████▋     | 47033/100000 [14:05:13<8:35:55,  1.71it/s]
Train steps ... :  47%|████▋     | 47034/100000 [14:05:14<8:35:57,  1.71it/s]
Train steps ... :  47%|████▋     | 47035/100000 [14:05:14<8:36:23,  1.71it/s]
Train steps ... :  47%|████▋     | 47036/100000 [14:05:15<8:36:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47037/100000 [14:05:15<8:36:33,  1.71it/s]
Train steps ... :  47%|████▋     | 47038/100000 [14:05:16<8:36:20,  1.71it/s]
Train steps ... :  47%|████▋     | 47039/100000 [14:05:17<8:36:07,  1.71it/s]
Train steps ... :  47%|████▋     | 47040/100000 [14:05:17<8:35:46,  1.71it/s]
Train steps ... :  47%|████▋     | 47041/100000 [14:05:18<8:36:31,  1.71it/s]
Train steps ... :  47%|████▋     | 47042/100000 [14:05:18<8:35:52,  1.71it/s]
Train steps ... :  47%|████▋     | 47043/100000 [14:05:19<8:35:51,  1.71it/s]
Train steps ... :  47%|████▋     | 47044/100000 [14:05:19<8:35:38,  1.71it/s]
Train steps ... :  47%|████▋     | 47045/100000 [14:05:20<8:35:50,  1.71it/s]
Train steps ... :  47%|████▋     | 47046/100000 [14:05:21<8:36:25,  1.71it/s]
Train steps ... :  47%|████▋     | 47047/100000 [14:05:21<8:35:43,  1.71it/s]
Train steps ... :  47%|████▋     | 47048/100000 [14:05:22<8:36:18,  1.71it/s]
Train steps ... :  47%|████▋     | 47049/100000 [14:05:22<8:36:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47050/100000 [14:05:23<8:36:22,  1.71it/s]Step... (47050 / 100000 | Loss: 0.719372034072876, Learning Rate: 5.321608040201005e-05)
+
                                                                             
Step... (47050 / 100000 | Loss: 0.6515759825706482, Learning Rate: 5.321608040201005e-05)
+
Train steps ... :  47%|████▋     | 47050/100000 [14:05:23<8:36:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47051/100000 [14:05:24<8:36:06,  1.71it/s]
Train steps ... :  47%|████▋     | 47052/100000 [14:05:24<8:36:19,  1.71it/s]
Train steps ... :  47%|████▋     | 47053/100000 [14:05:25<8:36:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47054/100000 [14:05:25<8:36:04,  1.71it/s]
Train steps ... :  47%|████▋     | 47055/100000 [14:05:26<8:35:29,  1.71it/s]
Train steps ... :  47%|████▋     | 47056/100000 [14:05:27<8:36:13,  1.71it/s]
Train steps ... :  47%|████▋     | 47057/100000 [14:05:27<8:35:35,  1.71it/s]
Train steps ... :  47%|████▋     | 47058/100000 [14:05:28<8:35:09,  1.71it/s]
Train steps ... :  47%|████▋     | 47059/100000 [14:05:28<8:35:53,  1.71it/s]
Train steps ... :  47%|████▋     | 47060/100000 [14:05:29<8:35:46,  1.71it/s]
Train steps ... :  47%|████▋     | 47061/100000 [14:05:29<8:35:32,  1.71it/s]
Train steps ... :  47%|████▋     | 47062/100000 [14:05:30<8:35:46,  1.71it/s]
Train steps ... :  47%|████▋     | 47063/100000 [14:05:31<8:36:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47064/100000 [14:05:31<8:35:50,  1.71it/s]
Train steps ... :  47%|████▋     | 47065/100000 [14:05:32<8:35:38,  1.71it/s]
Train steps ... :  47%|████▋     | 47066/100000 [14:05:32<8:35:14,  1.71it/s]
Train steps ... :  47%|████▋     | 47067/100000 [14:05:33<8:35:59,  1.71it/s]
Train steps ... :  47%|████▋     | 47068/100000 [14:05:34<8:35:55,  1.71it/s]
Train steps ... :  47%|████▋     | 47069/100000 [14:05:34<8:36:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47070/100000 [14:05:35<8:36:08,  1.71it/s]
Train steps ... :  47%|████▋     | 47071/100000 [14:05:35<8:35:25,  1.71it/s]
Train steps ... :  47%|████▋     | 47072/100000 [14:05:36<8:35:11,  1.71it/s]
Train steps ... :  47%|████▋     | 47073/100000 [14:05:36<8:34:30,  1.71it/s]
Train steps ... :  47%|████▋     | 47074/100000 [14:05:37<8:34:53,  1.71it/s]
Train steps ... :  47%|████▋     | 47075/100000 [14:05:38<8:34:57,  1.71it/s]Step... (47075 / 100000 | Loss: 0.8514232635498047, Learning Rate: 5.319095477386935e-05)
+
                                                                             
Step... (47075 / 100000 | Loss: 0.8109411001205444, Learning Rate: 5.319095477386935e-05)
+
Train steps ... :  47%|████▋     | 47075/100000 [14:05:38<8:34:57,  1.71it/s]
Train steps ... :  47%|████▋     | 47076/100000 [14:05:38<8:34:34,  1.71it/s]
Train steps ... :  47%|████▋     | 47077/100000 [14:05:39<8:34:33,  1.71it/s]
Train steps ... :  47%|████▋     | 47078/100000 [14:05:39<8:34:53,  1.71it/s]
Train steps ... :  47%|████▋     | 47079/100000 [14:05:40<8:34:35,  1.71it/s]
Train steps ... :  47%|████▋     | 47080/100000 [14:05:41<8:34:36,  1.71it/s]
Train steps ... :  47%|████▋     | 47081/100000 [14:05:41<8:34:23,  1.71it/s]
Train steps ... :  47%|████▋     | 47082/100000 [14:05:42<8:34:57,  1.71it/s]
Train steps ... :  47%|████▋     | 47083/100000 [14:05:42<8:34:45,  1.71it/s]
Train steps ... :  47%|████▋     | 47084/100000 [14:05:43<8:34:53,  1.71it/s]
Train steps ... :  47%|████▋     | 47085/100000 [14:05:43<8:34:20,  1.71it/s]
Train steps ... :  47%|████▋     | 47086/100000 [14:05:44<8:35:30,  1.71it/s]
Train steps ... :  47%|████▋     | 47087/100000 [14:05:45<8:35:17,  1.71it/s]
Train steps ... :  47%|████▋     | 47088/100000 [14:05:45<8:35:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47089/100000 [14:05:46<8:35:14,  1.71it/s]
Train steps ... :  47%|████▋     | 47090/100000 [14:05:46<8:34:27,  1.71it/s]
Train steps ... :  47%|���███▋     | 47091/100000 [14:05:47<8:34:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47092/100000 [14:05:48<8:34:10,  1.71it/s]
Train steps ... :  47%|████▋     | 47093/100000 [14:05:48<8:34:09,  1.71it/s]
Train steps ... :  47%|████▋     | 47094/100000 [14:05:49<8:34:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47095/100000 [14:05:49<8:35:20,  1.71it/s]
Train steps ... :  47%|████▋     | 47096/100000 [14:05:50<8:35:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47097/100000 [14:05:50<8:35:05,  1.71it/s]
Train steps ... :  47%|████▋     | 47098/100000 [14:05:51<8:35:04,  1.71it/s]
Train steps ... :  47%|████▋     | 47099/100000 [14:05:52<8:34:52,  1.71it/s]
Train steps ... :  47%|████▋     | 47100/100000 [14:05:52<8:35:05,  1.71it/s]Step... (47100 / 100000 | Loss: 0.7213412523269653, Learning Rate: 5.316582914572864e-05)
+
                                                                             
Step... (47100 / 100000 | Loss: 0.8806257843971252, Learning Rate: 5.316582914572864e-05)
+
Train steps ... :  47%|████▋     | 47100/100000 [14:05:53<8:35:05,  1.71it/s]
Train steps ... :  47%|████▋     | 47101/100000 [14:05:53<8:35:54,  1.71it/s]
Train steps ... :  47%|████▋     | 47102/100000 [14:05:53<8:35:03,  1.71it/s]
Train steps ... :  47%|████▋     | 47103/100000 [14:05:54<8:34:57,  1.71it/s]
Train steps ... :  47%|████▋     | 47104/100000 [14:05:55<8:34:34,  1.71it/s]
Train steps ... :  47%|████▋     | 47105/100000 [14:05:55<8:35:09,  1.71it/s]
Train steps ... :  47%|████▋     | 47106/100000 [14:05:56<8:35:33,  1.71it/s]
Train steps ... :  47%|████▋     | 47107/100000 [14:05:56<8:35:27,  1.71it/s]
Train steps ... :  47%|████▋     | 47108/100000 [14:05:57<8:34:58,  1.71it/s]
Train steps ... :  47%|████▋     | 47109/100000 [14:05:57<8:35:13,  1.71it/s]
Train steps ... :  47%|████▋     | 47110/100000 [14:05:58<8:34:51,  1.71it/s]
Train steps ... :  47%|████▋     | 47111/100000 [14:05:59<8:34:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47112/100000 [14:05:59<8:34:15,  1.71it/s]
Train steps ... :  47%|████▋     | 47113/100000 [14:06:00<8:34:18,  1.71it/s]
Train steps ... :  47%|████▋     | 47114/100000 [14:06:00<8:34:30,  1.71it/s]
Train steps ... :  47%|████▋     | 47115/100000 [14:06:01<8:34:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47116/100000 [14:06:02<8:34:31,  1.71it/s]
Train steps ... :  47%|████▋     | 47117/100000 [14:06:02<8:35:07,  1.71it/s]
Train steps ... :  47%|████▋     | 47118/100000 [14:06:03<8:34:30,  1.71it/s]
Train steps ... :  47%|████▋     | 47119/100000 [14:06:03<8:34:29,  1.71it/s]
Train steps ... :  47%|████▋     | 47120/100000 [14:06:04<8:34:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47121/100000 [14:06:04<8:34:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47122/100000 [14:06:05<8:34:19,  1.71it/s]
Train steps ... :  47%|████▋     | 47123/100000 [14:06:06<8:34:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47124/100000 [14:06:06<8:34:45,  1.71it/s]
Train steps ... :  47%|████▋     | 47125/100000 [14:06:07<8:34:24,  1.71it/s]Step... (47125 / 100000 | Loss: 0.5978145003318787, Learning Rate: 5.3140703517587945e-05)
+
                                                                             
Step... (47125 / 100000 | Loss: 0.789502739906311, Learning Rate: 5.3140703517587945e-05)
+
Train steps ... :  47%|████▋     | 47125/100000 [14:06:07<8:34:24,  1.71it/s]
Train steps ... :  47%|████▋     | 47126/100000 [14:06:07<8:35:29,  1.71it/s]
Train steps ... :  47%|████▋     | 47127/100000 [14:06:08<8:35:36,  1.71it/s]
Train steps ... :  47%|████▋     | 47128/100000 [14:06:09<8:35:33,  1.71it/s]
Train steps ... :  47%|████▋     | 47129/100000 [14:06:09<8:35:29,  1.71it/s]
Train steps ... :  47%|████▋     | 47130/100000 [14:06:10<8:35:11,  1.71it/s]
Train steps ... :  47%|████▋     | 47131/100000 [14:06:10<8:35:01,  1.71it/s]
Train steps ... :  47%|████▋     | 47132/100000 [14:06:11<8:34:56,  1.71it/s]
Train steps ... :  47%|████▋     | 47133/100000 [14:06:11<8:35:19,  1.71it/s]
Train steps ... :  47%|████▋     | 47134/100000 [14:06:12<8:35:05,  1.71it/s]
Train steps ... :  47%|████▋     | 47135/100000 [14:06:13<8:35:32,  1.71it/s]
Train steps ... :  47%|████▋     | 47136/100000 [14:06:13<8:34:48,  1.71it/s]
Train steps ... :  47%|████▋     | 47137/100000 [14:06:14<8:34:57,  1.71it/s]
Train steps ... :  47%|████▋     | 47138/100000 [14:06:14<8:35:32,  1.71it/s]
Train steps ... :  47%|████▋     | 47139/100000 [14:06:15<8:35:17,  1.71it/s]
Train steps ... :  47%|████▋     | 47140/100000 [14:06:16<8:35:03,  1.71it/s]
Train steps ... :  47%|████▋     | 47141/100000 [14:06:16<8:35:25,  1.71it/s]
Train steps ... :  47%|████▋     | 47142/100000 [14:06:17<8:35:01,  1.71it/s]
Train steps ... :  47%|████▋     | 47143/100000 [14:06:17<8:35:31,  1.71it/s]
Train steps ... :  47%|████▋     | 47144/100000 [14:06:18<8:35:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47145/100000 [14:06:18<8:35:16,  1.71it/s]
Train steps ... :  47%|████▋     | 47146/100000 [14:06:19<8:35:12,  1.71it/s]
Train steps ... :  47%|████▋     | 47147/100000 [14:06:20<8:35:03,  1.71it/s]
Train steps ... :  47%|████▋     | 47148/100000 [14:06:20<8:35:55,  1.71it/s]
Train steps ... :  47%|████▋     | 47149/100000 [14:06:21<8:36:09,  1.71it/s]
Train steps ... :  47%|████▋     | 47150/100000 [14:06:21<8:35:33,  1.71it/s]Step... (47150 / 100000 | Loss: 0.554803729057312, Learning Rate: 5.311557788944724e-05)
+
                                                                             
Step... (47150 / 100000 | Loss: 0.9505492448806763, Learning Rate: 5.311557788944724e-05)
+
Train steps ... :  47%|████▋     | 47150/100000 [14:06:22<8:35:33,  1.71it/s]
Train steps ... :  47%|████▋     | 47151/100000 [14:06:22<8:35:14,  1.71it/s]
Train steps ... :  47%|████▋     | 47152/100000 [14:06:23<8:34:57,  1.71it/s]
Train steps ... :  47%|████▋     | 47153/100000 [14:06:23<8:34:55,  1.71it/s]
Train steps ... :  47%|████▋     | 47154/100000 [14:06:24<8:35:33,  1.71it/s]
Train steps ... :  47%|████▋     | 47155/100000 [14:06:24<8:35:34,  1.71it/s]
Train steps ... :  47%|████▋     | 47156/100000 [14:06:25<8:35:14,  1.71it/s]
Train steps ... :  47%|████▋     | 47157/100000 [14:06:26<8:36:29,  1.71it/s]
Train steps ... :  47%|████▋     | 47158/100000 [14:06:26<8:36:09,  1.71it/s]
Train steps ... :  47%|████▋     | 47159/100000 [14:06:27<8:35:29,  1.71it/s]
Train steps ... :  47%|████▋     | 47160/100000 [14:06:27<8:34:55,  1.71it/s]
Train steps ... :  47%|████▋     | 47161/100000 [14:06:28<8:34:25,  1.71it/s]
Train steps ... :  47%|████▋     | 47162/100000 [14:06:28<8:34:29,  1.71it/s]
Train steps ... :  47%|████▋     | 47163/100000 [14:06:29<8:34:35,  1.71it/s]
Train steps ... :  47%|████▋     | 47164/100000 [14:06:30<8:34:47,  1.71it/s]
Train steps ... :  47%|████▋     | 47165/100000 [14:06:30<8:34:33,  1.71it/s]
Train steps ... :  47%|████▋     | 47166/100000 [14:06:31<8:34:07,  1.71it/s]
Train steps ... :  47%|████▋     | 47167/100000 [14:06:31<8:34:17,  1.71it/s]
Train steps ... :  47%|████▋     | 47168/100000 [14:06:32<8:34:50,  1.71it/s]
Train steps ... :  47%|████▋     | 47169/100000 [14:06:33<8:34:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47170/100000 [14:06:33<8:34:28,  1.71it/s]
Train steps ... :  47%|████▋     | 47171/100000 [14:06:34<8:34:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47172/100000 [14:06:34<8:34:15,  1.71it/s]
Train steps ... :  47%|████▋     | 47173/100000 [14:06:35<8:35:24,  1.71it/s]
Train steps ... :  47%|████▋     | 47174/100000 [14:06:35<8:35:00,  1.71it/s]
Train steps ... :  47%|████▋     | 47175/100000 [14:06:36<8:34:38,  1.71it/s]Step... (47175 / 100000 | Loss: 0.7633590698242188, Learning Rate: 5.309045226130653e-05)
+
                                                                             
Step... (47175 / 100000 | Loss: 0.8653665781021118, Learning Rate: 5.309045226130653e-05)
+
Train steps ... :  47%|████▋     | 47175/100000 [14:06:36<8:34:38,  1.71it/s]
Train steps ... :  47%|████▋     | 47176/100000 [14:06:37<8:34:35,  1.71it/s]
Train steps ... :  47%|████▋     | 47177/100000 [14:06:37<8:34:28,  1.71it/s]
Train steps ... :  47%|████▋     | 47178/100000 [14:06:38<8:34:16,  1.71it/s]
Train steps ... :  47%|████▋     | 47179/100000 [14:06:38<8:34:18,  1.71it/s]
Train steps ... :  47%|████▋     | 47180/100000 [14:06:39<8:34:07,  1.71it/s]
Train steps ... :  47%|████▋     | 47181/100000 [14:06:40<8:34:20,  1.71it/s]
Train steps ... :  47%|████▋     | 47182/100000 [14:06:40<8:34:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47183/100000 [14:06:41<8:34:46,  1.71it/s]
Train steps ... :  47%|████▋     | 47184/100000 [14:06:41<8:34:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47185/100000 [14:06:42<8:34:39,  1.71it/s]
Train steps ... :  47%|████▋     | 47186/100000 [14:06:42<8:34:57,  1.71it/s]
Train steps ... :  47%|████▋     | 47187/100000 [14:06:43<8:35:03,  1.71it/s]
Train steps ... :  47%|████▋     | 47188/100000 [14:06:44<8:34:11,  1.71it/s]
Train steps ... :  47%|████▋     | 47189/100000 [14:06:44<8:34:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47190/100000 [14:06:45<8:34:15,  1.71it/s]
Train steps ... :  47%|████▋     | 47191/100000 [14:06:45<8:34:43,  1.71it/s]
Train steps ... :  47%|████▋     | 47192/100000 [14:06:46<8:34:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47193/100000 [14:06:47<8:34:07,  1.71it/s]
Train steps ... :  47%|████▋     | 47194/100000 [14:06:47<8:34:23,  1.71it/s]
Train steps ... :  47%|████▋     | 47195/100000 [14:06:48<8:34:28,  1.71it/s]
Train steps ... :  47%|████▋     | 47196/100000 [14:06:48<8:35:19,  1.71it/s]
Train steps ... :  47%|████▋     | 47197/100000 [14:06:49<8:35:40,  1.71it/s]
Train steps ... :  47%|████▋     | 47198/100000 [14:06:49<8:35:30,  1.71it/s]
Train steps ... :  47%|████▋     | 47199/100000 [14:06:50<8:35:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47200/100000 [14:06:51<8:34:43,  1.71it/s]Step... (47200 / 100000 | Loss: 0.7887016534805298, Learning Rate: 5.3065326633165835e-05)
+
                                                                             
Step... (47200 / 100000 | Loss: 0.9787333011627197, Learning Rate: 5.3065326633165835e-05)
+
Train steps ... :  47%|████▋     | 47200/100000 [14:06:51<8:34:43,  1.71it/s]
Train steps ... :  47%|████▋     | 47201/100000 [14:06:51<8:35:08,  1.71it/s]
Train steps ... :  47%|████▋     | 47202/100000 [14:06:52<8:34:45,  1.71it/s]
Train steps ... :  47%|████▋     | 47203/100000 [14:06:52<8:34:33,  1.71it/s]
Train steps ... :  47%|████▋     | 47204/100000 [14:06:53<8:34:53,  1.71it/s]
Train steps ... :  47%|████▋     | 47205/100000 [14:06:54<8:34:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47206/100000 [14:06:54<8:34:36,  1.71it/s]
Train steps ... :  47%|████▋     | 47207/100000 [14:06:55<8:34:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47208/100000 [14:06:55<8:35:09,  1.71it/s]
Train steps ... :  47%|████▋     | 47209/100000 [14:06:56<8:34:59,  1.71it/s]
Train steps ... :  47%|████▋     | 47210/100000 [14:06:57<8:35:20,  1.71it/s]
Train steps ... :  47%|████▋     | 47211/100000 [14:06:57<8:35:11,  1.71it/s]
Train steps ... :  47%|████▋     | 47212/100000 [14:06:58<8:34:31,  1.71it/s]
Train steps ... :  47%|████▋     | 47213/100000 [14:06:58<8:34:16,  1.71it/s]
Train steps ... :  47%|████▋     | 47214/100000 [14:06:59<8:34:25,  1.71it/s]
Train steps ... :  47%|████▋     | 47215/100000 [14:06:59<8:34:04,  1.71it/s]
Train steps ... :  47%|████▋     | 47216/100000 [14:07:00<8:34:27,  1.71it/s]
Train steps ... :  47%|████▋     | 47217/100000 [14:07:01<8:34:49,  1.71it/s]
Train steps ... :  47%|████▋     | 47218/100000 [14:07:01<8:34:48,  1.71it/s]
Train steps ... :  47%|████▋     | 47219/100000 [14:07:02<8:34:16,  1.71it/s]
Train steps ... :  47%|████▋     | 47220/100000 [14:07:02<8:33:52,  1.71it/s]
Train steps ... :  47%|████▋     | 47221/100000 [14:07:03<8:34:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47222/100000 [14:07:04<8:34:30,  1.71it/s]
Train steps ... :  47%|████▋     | 47223/100000 [14:07:04<8:34:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47224/100000 [14:07:05<8:34:06,  1.71it/s]
Train steps ... :  47%|████▋     | 47225/100000 [14:07:05<8:35:31,  1.71it/s]Step... (47225 / 100000 | Loss: 1.1112573146820068, Learning Rate: 5.3040201005025125e-05)
+
                                                                             
Step... (47225 / 100000 | Loss: 0.9841567873954773, Learning Rate: 5.3040201005025125e-05)
+
Train steps ... :  47%|████▋     | 47225/100000 [14:07:06<8:35:31,  1.71it/s]
Train steps ... :  47%|████▋     | 47226/100000 [14:07:06<8:37:05,  1.70it/s]
Train steps ... :  47%|████▋     | 47227/100000 [14:07:06<8:35:49,  1.71it/s]
Train steps ... :  47%|████▋     | 47228/100000 [14:07:07<8:35:23,  1.71it/s]
Train steps ... :  47%|████▋     | 47229/100000 [14:07:08<8:35:25,  1.71it/s]
Train steps ... :  47%|████▋     | 47230/100000 [14:07:08<8:35:10,  1.71it/s]
Train steps ... :  47%|████▋     | 47231/100000 [14:07:09<8:34:58,  1.71it/s]
Train steps ... :  47%|████▋     | 47232/100000 [14:07:09<8:34:43,  1.71it/s]
Train steps ... :  47%|████▋     | 47233/100000 [14:07:10<8:34:33,  1.71it/s]
Train steps ... :  47%|████▋     | 47234/100000 [14:07:11<8:34:03,  1.71it/s]
Train steps ... :  47%|████▋     | 47235/100000 [14:07:11<8:33:48,  1.71it/s]
Train steps ... :  47%|████▋     | 47236/100000 [14:07:12<8:34:12,  1.71it/s]
Train steps ... :  47%|████▋     | 47237/100000 [14:07:12<8:33:49,  1.71it/s]
Train steps ... :  47%|████▋     | 47238/100000 [14:07:13<8:33:38,  1.71it/s]
Train steps ... :  47%|████▋     | 47239/100000 [14:07:13<8:34:15,  1.71it/s]
Train steps ... :  47%|████▋     | 47240/100000 [14:07:14<8:34:12,  1.71it/s]
Train steps ... :  47%|████▋     | 47241/100000 [14:07:15<8:33:57,  1.71it/s]
Train steps ... :  47%|████▋     | 47242/100000 [14:07:15<8:34:56,  1.71it/s]
Train steps ... :  47%|████▋     | 47243/100000 [14:07:16<8:34:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47244/100000 [14:07:16<8:34:03,  1.71it/s]
Train steps ... :  47%|████▋     | 47245/100000 [14:07:17<8:34:17,  1.71it/s]
Train steps ... :  47%|████▋     | 47246/100000 [14:07:18<8:35:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47247/100000 [14:07:18<8:34:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47248/100000 [14:07:19<8:34:12,  1.71it/s]
Train steps ... :  47%|████▋     | 47249/100000 [14:07:19<8:34:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47250/100000 [14:07:20<8:34:30,  1.71it/s]Step... (47250 / 100000 | Loss: 0.5657108426094055, Learning Rate: 5.301507537688443e-05)
+
                                                                             
Step... (47250 / 100000 | Loss: 1.2039098739624023, Learning Rate: 5.301507537688443e-05)
+
Train steps ... :  47%|████▋     | 47250/100000 [14:07:20<8:34:30,  1.71it/s]
Train steps ... :  47%|████▋     | 47251/100000 [14:07:21<8:34:46,  1.71it/s]
Train steps ... :  47%|████▋     | 47252/100000 [14:07:21<8:34:31,  1.71it/s]
Train steps ... :  47%|████▋     | 47253/100000 [14:07:22<8:34:05,  1.71it/s]
Train steps ... :  47%|████▋     | 47254/100000 [14:07:22<8:33:51,  1.71it/s]
Train steps ... :  47%|████▋     | 47255/100000 [14:07:23<8:33:50,  1.71it/s]
Train steps ... :  47%|████▋     | 47256/100000 [14:07:23<8:34:03,  1.71it/s]
Train steps ... :  47%|████▋     | 47257/100000 [14:07:24<8:33:54,  1.71it/s]
Train steps ... :  47%|████▋     | 47258/100000 [14:07:25<8:33:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47259/100000 [14:07:25<8:33:50,  1.71it/s]
Train steps ... :  47%|████▋     | 47260/100000 [14:07:26<8:34:28,  1.71it/s]
Train steps ... :  47%|████▋     | 47261/100000 [14:07:26<8:34:17,  1.71it/s]
Train steps ... :  47%|████▋     | 47262/100000 [14:07:27<8:34:59,  1.71it/s]
Train steps ... :  47%|████▋     | 47263/100000 [14:07:28<8:35:18,  1.71it/s]
Train steps ... :  47%|████▋     | 47264/100000 [14:07:28<8:34:49,  1.71it/s]
Train steps ... :  47%|████▋     | 47265/100000 [14:07:29<8:34:17,  1.71it/s]
Train steps ... :  47%|████▋     | 47266/100000 [14:07:29<8:34:52,  1.71it/s]
Train steps ... :  47%|████▋     | 47267/100000 [14:07:30<8:34:39,  1.71it/s]
Train steps ... :  47%|████▋     | 47268/100000 [14:07:30<8:34:03,  1.71it/s]
Train steps ... :  47%|████▋     | 47269/100000 [14:07:31<8:34:28,  1.71it/s]
Train steps ... :  47%|████▋     | 47270/100000 [14:07:32<8:34:34,  1.71it/s]
Train steps ... :  47%|████▋     | 47271/100000 [14:07:32<8:34:08,  1.71it/s]
Train steps ... :  47%|████▋     | 47272/100000 [14:07:33<8:34:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47273/100000 [14:07:33<8:34:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47274/100000 [14:07:34<8:34:29,  1.71it/s]
Train steps ... :  47%|████▋     | 47275/100000 [14:07:35<8:33:43,  1.71it/s]Step... (47275 / 100000 | Loss: 0.94809889793396, Learning Rate: 5.298994974874372e-05)
+
                                                                             
Step... (47275 / 100000 | Loss: 0.7344460487365723, Learning Rate: 5.298994974874372e-05)
+
Train steps ... :  47%|████▋     | 47275/100000 [14:07:35<8:33:43,  1.71it/s]
Train steps ... :  47%|████▋     | 47276/100000 [14:07:35<8:34:10,  1.71it/s]
Train steps ... :  47%|████▋     | 47277/100000 [14:07:36<8:33:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47278/100000 [14:07:36<8:33:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47279/100000 [14:07:37<8:34:09,  1.71it/s]
Train steps ... :  47%|████▋     | 47280/100000 [14:07:37<8:33:53,  1.71it/s]
Train steps ... :  47%|████▋     | 47281/100000 [14:07:38<8:33:39,  1.71it/s]
Train steps ... :  47%|████▋     | 47282/100000 [14:07:39<8:33:45,  1.71it/s]
Train steps ... :  47%|████▋     | 47283/100000 [14:07:39<8:34:12,  1.71it/s]
Train steps ... :  47%|████▋     | 47284/100000 [14:07:40<8:33:48,  1.71it/s]
Train steps ... :  47%|████▋     | 47285/100000 [14:07:40<8:34:15,  1.71it/s]
Train steps ... :  47%|████▋     | 47286/100000 [14:07:41<8:34:06,  1.71it/s]
Train steps ... :  47%|████▋     | 47287/100000 [14:07:42<8:34:12,  1.71it/s]
Train steps ... :  47%|████▋     | 47288/100000 [14:07:42<8:34:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47289/100000 [14:07:43<8:33:49,  1.71it/s]
Train steps ... :  47%|████▋     | 47290/100000 [14:07:43<8:34:08,  1.71it/s]
Train steps ... :  47%|████▋     | 47291/100000 [14:07:44<8:33:43,  1.71it/s]
Train steps ... :  47%|████▋     | 47292/100000 [14:07:44<8:33:23,  1.71it/s]
Train steps ... :  47%|████▋     | 47293/100000 [14:07:45<8:33:19,  1.71it/s]
Train steps ... :  47%|████▋     | 47294/100000 [14:07:46<8:34:04,  1.71it/s]
Train steps ... :  47%|████▋     | 47295/100000 [14:07:46<8:34:31,  1.71it/s]
Train steps ... :  47%|████▋     | 47296/100000 [14:07:47<8:34:34,  1.71it/s]
Train steps ... :  47%|████▋     | 47297/100000 [14:07:47<8:34:47,  1.71it/s]
Train steps ... :  47%|████▋     | 47298/100000 [14:07:48<8:34:09,  1.71it/s]
Train steps ... :  47%|████▋     | 47299/100000 [14:07:49<8:34:13,  1.71it/s]
Train steps ... :  47%|████▋     | 47300/100000 [14:07:49<8:34:21,  1.71it/s]Step... (47300 / 100000 | Loss: 0.867268443107605, Learning Rate: 5.296482412060302e-05)
+
                                                                             
Step... (47300 / 100000 | Loss: 0.6983559727668762, Learning Rate: 5.296482412060302e-05)
+
Train steps ... :  47%|████▋     | 47300/100000 [14:07:50<8:34:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47301/100000 [14:07:50<8:34:11,  1.71it/s]
Train steps ... :  47%|████▋     | 47302/100000 [14:07:50<8:33:23,  1.71it/s]
Train steps ... :  47%|████▋     | 47303/100000 [14:07:51<8:33:11,  1.71it/s]
Train steps ... :  47%|████▋     | 47304/100000 [14:07:52<8:32:56,  1.71it/s]
Train steps ... :  47%|████▋     | 47305/100000 [14:07:52<8:32:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47306/100000 [14:07:53<8:32:28,  1.71it/s]
Train steps ... :  47%|████▋     | 47307/100000 [14:07:53<8:32:29,  1.71it/s]
Train steps ... :  47%|████▋     | 47308/100000 [14:07:54<8:32:25,  1.71it/s]
Train steps ... :  47%|████▋     | 47309/100000 [14:07:54<8:33:03,  1.71it/s]
Train steps ... :  47%|████▋     | 47310/100000 [14:07:55<8:33:20,  1.71it/s]
Train steps ... :  47%|████▋     | 47311/100000 [14:07:56<8:33:17,  1.71it/s]
Train steps ... :  47%|████▋     | 47312/100000 [14:07:56<8:33:10,  1.71it/s]
Train steps ... :  47%|████▋     | 47313/100000 [14:07:57<8:33:35,  1.71it/s]
Train steps ... :  47%|████▋     | 47314/100000 [14:07:57<8:32:20,  1.71it/s]
Train steps ... :  47%|████▋     | 47315/100000 [14:07:58<8:33:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47316/100000 [14:07:59<8:33:38,  1.71it/s]
Train steps ... :  47%|████▋     | 47317/100000 [14:07:59<8:33:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47318/100000 [14:08:00<8:33:57,  1.71it/s]
Train steps ... :  47%|████▋     | 47319/100000 [14:08:00<8:34:15,  1.71it/s]
Train steps ... :  47%|████▋     | 47320/100000 [14:08:01<8:34:08,  1.71it/s]
Train steps ... :  47%|████▋     | 47321/100000 [14:08:01<8:33:56,  1.71it/s]
Train steps ... :  47%|████▋     | 47322/100000 [14:08:02<8:33:18,  1.71it/s]
Train steps ... :  47%|████▋     | 47323/100000 [14:08:03<8:33:28,  1.71it/s]
Train steps ... :  47%|████▋     | 47324/100000 [14:08:03<8:32:53,  1.71it/s]
Train steps ... :  47%|████▋     | 47325/100000 [14:08:04<8:32:33,  1.71it/s]Step... (47325 / 100000 | Loss: 0.8073360919952393, Learning Rate: 5.293969849246232e-05)
+
                                                                             
Step... (47325 / 100000 | Loss: 0.9250425100326538, Learning Rate: 5.293969849246232e-05)
+
Train steps ... :  47%|████▋     | 47325/100000 [14:08:04<8:32:33,  1.71it/s]
Train steps ... :  47%|████▋     | 47326/100000 [14:08:04<8:33:36,  1.71it/s]
Train steps ... :  47%|████▋     | 47327/100000 [14:08:05<8:33:19,  1.71it/s]
Train steps ... :  47%|████▋     | 47328/100000 [14:08:06<8:32:47,  1.71it/s]
Train steps ... :  47%|████▋     | 47329/100000 [14:08:06<8:33:15,  1.71it/s]
Train steps ... :  47%|████▋     | 47330/100000 [14:08:07<8:33:14,  1.71it/s]
Train steps ... :  47%|████▋     | 47331/100000 [14:08:07<8:33:12,  1.71it/s]
Train steps ... :  47%|████▋     | 47332/100000 [14:08:08<8:33:05,  1.71it/s]
Train steps ... :  47%|████▋     | 47333/100000 [14:08:08<8:32:59,  1.71it/s]
Train steps ... :  47%|████▋     | 47334/100000 [14:08:09<8:32:48,  1.71it/s]
Train steps ... :  47%|████▋     | 47335/100000 [14:08:10<8:32:39,  1.71it/s]
Train steps ... :  47%|████▋     | 47336/100000 [14:08:10<8:32:58,  1.71it/s]
Train steps ... :  47%|████▋     | 47337/100000 [14:08:11<8:32:41,  1.71it/s]
Train steps ... :  47%|████▋     | 47338/100000 [14:08:11<8:33:04,  1.71it/s]
Train steps ... :  47%|████▋     | 47339/100000 [14:08:12<8:32:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47340/100000 [14:08:13<8:32:46,  1.71it/s]
Train steps ... :  47%|████▋     | 47341/100000 [14:08:13<8:33:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47342/100000 [14:08:14<8:33:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47343/100000 [14:08:14<8:33:29,  1.71it/s]
Train steps ... :  47%|████▋     | 47344/100000 [14:08:15<8:33:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47345/100000 [14:08:15<8:33:08,  1.71it/s]
Train steps ... :  47%|████▋     | 47346/100000 [14:08:16<8:33:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47347/100000 [14:08:17<8:33:36,  1.71it/s]
Train steps ... :  47%|████▋     | 47348/100000 [14:08:17<8:33:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47349/100000 [14:08:18<8:33:35,  1.71it/s]
Train steps ... :  47%|████▋     | 47350/100000 [14:08:18<8:32:54,  1.71it/s]Step... (47350 / 100000 | Loss: 0.9976280927658081, Learning Rate: 5.291457286432161e-05)
+
                                                                             
Step... (47350 / 100000 | Loss: 1.213230848312378, Learning Rate: 5.291457286432161e-05)
+
Train steps ... :  47%|████▋     | 47350/100000 [14:08:19<8:32:54,  1.71it/s]
Train steps ... :  47%|████▋     | 47351/100000 [14:08:19<8:33:51,  1.71it/s]
Train steps ... :  47%|████▋     | 47352/100000 [14:08:20<8:33:24,  1.71it/s]
Train steps ... :  47%|████▋     | 47353/100000 [14:08:20<8:34:08,  1.71it/s]
Train steps ... :  47%|████▋     | 47354/100000 [14:08:21<8:33:33,  1.71it/s]
Train steps ... :  47%|████▋     | 47355/100000 [14:08:21<8:33:40,  1.71it/s]
Train steps ... :  47%|████▋     | 47356/100000 [14:08:22<8:33:13,  1.71it/s]
Train steps ... :  47%|████▋     | 47357/100000 [14:08:23<8:33:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47358/100000 [14:08:23<8:32:52,  1.71it/s]
Train steps ... :  47%|████▋     | 47359/100000 [14:08:24<8:32:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47360/100000 [14:08:24<8:33:04,  1.71it/s]
Train steps ... :  47%|████▋     | 47361/100000 [14:08:25<8:32:52,  1.71it/s]
Train steps ... :  47%|████▋     | 47362/100000 [14:08:25<8:32:49,  1.71it/s]
Train steps ... :  47%|████▋     | 47363/100000 [14:08:26<8:33:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47364/100000 [14:08:27<8:32:58,  1.71it/s]
Train steps ... :  47%|████▋     | 47365/100000 [14:08:27<8:32:49,  1.71it/s]
Train steps ... :  47%|████▋     | 47366/100000 [14:08:28<8:32:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47367/100000 [14:08:28<8:33:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47368/100000 [14:08:29<8:33:06,  1.71it/s]
Train steps ... :  47%|████▋     | 47369/100000 [14:08:30<8:33:01,  1.71it/s]
Train steps ... :  47%|████▋     | 47370/100000 [14:08:30<8:32:47,  1.71it/s]
Train steps ... :  47%|████▋     | 47371/100000 [14:08:31<8:33:17,  1.71it/s]
Train steps ... :  47%|████▋     | 47372/100000 [14:08:31<8:32:39,  1.71it/s]
Train steps ... :  47%|████▋     | 47373/100000 [14:08:32<8:32:13,  1.71it/s]
Train steps ... :  47%|████▋     | 47374/100000 [14:08:32<8:32:08,  1.71it/s]
Train steps ... :  47%|████▋     | 47375/100000 [14:08:33<8:32:30,  1.71it/s]Step... (47375 / 100000 | Loss: 0.6937940120697021, Learning Rate: 5.288944723618091e-05)
+
                                                                             
Step... (47375 / 100000 | Loss: 0.6897395253181458, Learning Rate: 5.288944723618091e-05)
+
Train steps ... :  47%|████▋     | 47375/100000 [14:08:33<8:32:30,  1.71it/s]
Train steps ... :  47%|████▋     | 47376/100000 [14:08:34<8:33:25,  1.71it/s]
Train steps ... :  47%|████▋     | 47377/100000 [14:08:34<8:33:56,  1.71it/s]
Train steps ... :  47%|████▋     | 47378/100000 [14:08:35<8:33:34,  1.71it/s]
Train steps ... :  47%|████▋     | 47379/100000 [14:08:35<8:32:47,  1.71it/s]
Train steps ... :  47%|████▋     | 47380/100000 [14:08:36<8:33:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47381/100000 [14:08:37<8:33:14,  1.71it/s]
Train steps ... :  47%|████▋     | 47382/100000 [14:08:37<8:32:55,  1.71it/s]
Train steps ... :  47%|████▋     | 47383/100000 [14:08:38<8:33:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47384/100000 [14:08:38<8:32:58,  1.71it/s]
Train steps ... :  47%|████▋     | 47385/100000 [14:08:39<8:33:09,  1.71it/s]
Train steps ... :  47%|████▋     | 47386/100000 [14:08:39<8:32:29,  1.71it/s]
Train steps ... :  47%|████▋     | 47387/100000 [14:08:40<8:33:55,  1.71it/s]
Train steps ... :  47%|████▋     | 47388/100000 [14:08:41<8:33:01,  1.71it/s]
Train steps ... :  47%|████▋     | 47389/100000 [14:08:41<8:33:31,  1.71it/s]
Train steps ... :  47%|████▋     | 47390/100000 [14:08:42<8:33:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47391/100000 [14:08:42<8:32:25,  1.71it/s]
Train steps ... :  47%|████▋     | 47392/100000 [14:08:43<8:32:15,  1.71it/s]
Train steps ... :  47%|████▋     | 47393/100000 [14:08:44<8:32:13,  1.71it/s]
Train steps ... :  47%|████▋     | 47394/100000 [14:08:44<8:33:08,  1.71it/s]
Train steps ... :  47%|████▋     | 47395/100000 [14:08:45<8:32:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47396/100000 [14:08:45<8:32:47,  1.71it/s]
Train steps ... :  47%|████▋     | 47397/100000 [14:08:46<8:32:38,  1.71it/s]
Train steps ... :  47%|████▋     | 47398/100000 [14:08:46<8:32:45,  1.71it/s]
Train steps ... :  47%|████▋     | 47399/100000 [14:08:47<8:32:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47400/100000 [14:08:48<8:32:16,  1.71it/s]Step... (47400 / 100000 | Loss: 0.9012608528137207, Learning Rate: 5.28643216080402e-05)
+
                                                                             
Step... (47400 / 100000 | Loss: 0.9699180722236633, Learning Rate: 5.28643216080402e-05)
+
Train steps ... :  47%|████▋     | 47400/100000 [14:08:48<8:32:16,  1.71it/s]
Train steps ... :  47%|████▋     | 47401/100000 [14:08:48<8:32:20,  1.71it/s]
Train steps ... :  47%|████▋     | 47402/100000 [14:08:49<8:32:11,  1.71it/s]
Train steps ... :  47%|████▋     | 47403/100000 [14:08:49<8:32:25,  1.71it/s]
Train steps ... :  47%|████▋     | 47404/100000 [14:08:50<8:32:20,  1.71it/s]
Train steps ... :  47%|████▋     | 47405/100000 [14:08:51<8:32:12,  1.71it/s]
Train steps ... :  47%|████▋     | 47406/100000 [14:08:51<8:32:45,  1.71it/s]
Train steps ... :  47%|████▋     | 47407/100000 [14:08:52<8:32:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47408/100000 [14:08:52<8:32:28,  1.71it/s]
Train steps ... :  47%|████▋     | 47409/100000 [14:08:53<8:33:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47410/100000 [14:08:53<8:33:04,  1.71it/s]
Train steps ... :  47%|████▋     | 47411/100000 [14:08:54<8:33:00,  1.71it/s]
Train steps ... :  47%|████▋     | 47412/100000 [14:08:55<8:33:47,  1.71it/s]
Train steps ... :  47%|████▋     | 47413/100000 [14:08:55<8:33:50,  1.71it/s]
Train steps ... :  47%|████▋     | 47414/100000 [14:08:56<8:33:35,  1.71it/s]
Train steps ... :  47%|████▋     | 47415/100000 [14:08:56<8:32:53,  1.71it/s]
Train steps ... :  47%|████▋     | 47416/100000 [14:08:57<8:32:23,  1.71it/s]
Train steps ... :  47%|████▋     | 47417/100000 [14:08:58<8:31:56,  1.71it/s]
Train steps ... :  47%|████▋     | 47418/100000 [14:08:58<8:32:07,  1.71it/s]
Train steps ... :  47%|████▋     | 47419/100000 [14:08:59<8:31:59,  1.71it/s]
Train steps ... :  47%|████▋     | 47420/100000 [14:08:59<8:32:36,  1.71it/s]
Train steps ... :  47%|████▋     | 47421/100000 [14:09:00<8:32:50,  1.71it/s]
Train steps ... :  47%|████▋     | 47422/100000 [14:09:01<8:32:43,  1.71it/s]
Train steps ... :  47%|████▋     | 47423/100000 [14:09:01<8:33:39,  1.71it/s]
Train steps ... :  47%|████▋     | 47424/100000 [14:09:02<8:32:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47425/100000 [14:09:02<8:33:22,  1.71it/s]Step... (47425 / 100000 | Loss: 1.1105457544326782, Learning Rate: 5.2839195979899505e-05)
+
                                                                             
Step... (47425 / 100000 | Loss: 0.7191609740257263, Learning Rate: 5.2839195979899505e-05)
+
Train steps ... :  47%|████▋     | 47425/100000 [14:09:03<8:33:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47426/100000 [14:09:03<8:32:00,  1.71it/s]
Train steps ... :  47%|████▋     | 47427/100000 [14:09:03<8:31:51,  1.71it/s]
Train steps ... :  47%|████▋     | 47428/100000 [14:09:04<8:32:56,  1.71it/s]
Train steps ... :  47%|████▋     | 47429/100000 [14:09:05<8:33:00,  1.71it/s]
Train steps ... :  47%|████▋     | 47430/100000 [14:09:05<8:33:20,  1.71it/s]
Train steps ... :  47%|████▋     | 47431/100000 [14:09:06<8:32:38,  1.71it/s]
Train steps ... :  47%|████▋     | 47432/100000 [14:09:06<8:32:30,  1.71it/s]
Train steps ... :  47%|████▋     | 47433/100000 [14:09:07<8:32:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47434/100000 [14:09:08<8:31:58,  1.71it/s]
Train steps ... :  47%|████▋     | 47435/100000 [14:09:08<8:31:36,  1.71it/s]
Train steps ... :  47%|████▋     | 47436/100000 [14:09:09<8:31:53,  1.71it/s]
Train steps ... :  47%|████▋     | 47437/100000 [14:09:09<8:31:54,  1.71it/s]
Train steps ... :  47%|████▋     | 47438/100000 [14:09:10<8:33:54,  1.70it/s]
Train steps ... :  47%|████▋     | 47439/100000 [14:09:10<8:32:46,  1.71it/s]
Train steps ... :  47%|████▋     | 47440/100000 [14:09:11<8:32:24,  1.71it/s]
Train steps ... :  47%|████▋     | 47441/100000 [14:09:12<8:31:54,  1.71it/s]
Train steps ... :  47%|████▋     | 47442/100000 [14:09:12<8:33:04,  1.71it/s]
Train steps ... :  47%|████▋     | 47443/100000 [14:09:13<8:32:29,  1.71it/s]
Train steps ... :  47%|████▋     | 47444/100000 [14:09:13<8:32:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47445/100000 [14:09:14<8:32:01,  1.71it/s]
Train steps ... :  47%|████▋     | 47446/100000 [14:09:15<8:31:55,  1.71it/s]
Train steps ... :  47%|████▋     | 47447/100000 [14:09:15<8:31:57,  1.71it/s]
Train steps ... :  47%|████▋     | 47448/100000 [14:09:16<8:32:04,  1.71it/s]
Train steps ... :  47%|████▋     | 47449/100000 [14:09:16<8:31:52,  1.71it/s]
Train steps ... :  47%|████▋     | 47450/100000 [14:09:17<8:32:23,  1.71it/s]Step... (47450 / 100000 | Loss: 0.9061756134033203, Learning Rate: 5.2814070351758794e-05)
+
                                                                             
Step... (47450 / 100000 | Loss: 1.0188031196594238, Learning Rate: 5.2814070351758794e-05)
+
Train steps ... :  47%|████▋     | 47450/100000 [14:09:17<8:32:23,  1.71it/s]
Train steps ... :  47%|████▋     | 47451/100000 [14:09:17<8:33:43,  1.70it/s]
Train steps ... :  47%|████▋     | 47452/100000 [14:09:18<8:32:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47453/100000 [14:09:19<8:32:25,  1.71it/s]
Train steps ... :  47%|████▋     | 47454/100000 [14:09:19<8:32:57,  1.71it/s]
Train steps ... :  47%|████▋     | 47455/100000 [14:09:20<8:32:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47456/100000 [14:09:20<8:32:56,  1.71it/s]
Train steps ... :  47%|████▋     | 47457/100000 [14:09:21<8:32:12,  1.71it/s]
Train steps ... :  47%|████▋     | 47458/100000 [14:09:22<8:32:31,  1.71it/s]
Train steps ... :  47%|████▋     | 47459/100000 [14:09:22<8:32:24,  1.71it/s]
Train steps ... :  47%|████▋     | 47460/100000 [14:09:23<8:33:30,  1.71it/s]
Train steps ... :  47%|████▋     | 47461/100000 [14:09:23<8:33:30,  1.71it/s]
Train steps ... :  47%|████▋     | 47462/100000 [14:09:24<8:32:44,  1.71it/s]
Train steps ... :  47%|████▋     | 47463/100000 [14:09:25<8:33:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47464/100000 [14:09:25<8:33:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47465/100000 [14:09:26<8:32:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47466/100000 [14:09:26<8:32:23,  1.71it/s]
Train steps ... :  47%|████▋     | 47467/100000 [14:09:27<8:32:43,  1.71it/s]
Train steps ... :  47%|████▋     | 47468/100000 [14:09:27<8:32:06,  1.71it/s]
Train steps ... :  47%|████▋     | 47469/100000 [14:09:28<8:32:07,  1.71it/s]
Train steps ... :  47%|████▋     | 47470/100000 [14:09:29<8:32:04,  1.71it/s]
Train steps ... :  47%|████▋     | 47471/100000 [14:09:29<8:31:43,  1.71it/s]
Train steps ... :  47%|████▋     | 47472/100000 [14:09:30<8:31:51,  1.71it/s]
Train steps ... :  47%|████▋     | 47473/100000 [14:09:30<8:31:54,  1.71it/s]
Train steps ... :  47%|████▋     | 47474/100000 [14:09:31<8:31:58,  1.71it/s]
Train steps ... :  47%|████▋     | 47475/100000 [14:09:32<8:32:00,  1.71it/s]Step... (47475 / 100000 | Loss: 0.9031528830528259, Learning Rate: 5.27889447236181e-05)
+
                                                                             
Step... (47475 / 100000 | Loss: 0.7901715040206909, Learning Rate: 5.27889447236181e-05)
+
Train steps ... :  47%|████▋     | 47475/100000 [14:09:32<8:32:00,  1.71it/s]
Train steps ... :  47%|████▋     | 47476/100000 [14:09:32<8:32:03,  1.71it/s]
Train steps ... :  47%|████▋     | 47477/100000 [14:09:33<8:32:00,  1.71it/s]
Train steps ... :  47%|████▋     | 47478/100000 [14:09:33<8:32:34,  1.71it/s]
Train steps ... :  47%|████▋     | 47479/100000 [14:09:34<8:32:03,  1.71it/s]
Train steps ... :  47%|████▋     | 47480/100000 [14:09:34<8:32:22,  1.71it/s]
Train steps ... :  47%|████▋     | 47481/100000 [14:09:35<8:32:07,  1.71it/s]
Train steps ... :  47%|████▋     | 47482/100000 [14:09:36<8:32:55,  1.71it/s]
Train steps ... :  47%|████▋     | 47483/100000 [14:09:36<8:32:28,  1.71it/s]
Train steps ... :  47%|████▋     | 47484/100000 [14:09:37<8:31:45,  1.71it/s]
Train steps ... :  47%|████▋     | 47485/100000 [14:09:37<8:31:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47486/100000 [14:09:38<8:31:47,  1.71it/s]
Train steps ... :  47%|████▋     | 47487/100000 [14:09:39<8:31:39,  1.71it/s]
Train steps ... :  47%|████▋     | 47488/100000 [14:09:39<8:31:14,  1.71it/s]
Train steps ... :  47%|████▋     | 47489/100000 [14:09:40<8:31:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47490/100000 [14:09:40<8:31:59,  1.71it/s]
Train steps ... :  47%|████▋     | 47491/100000 [14:09:41<8:32:21,  1.71it/s]
Train steps ... :  47%|████▋     | 47492/100000 [14:09:41<8:32:21,  1.71it/s]
Train steps ... :  47%|���███▋     | 47493/100000 [14:09:42<8:32:02,  1.71it/s]
Train steps ... :  47%|████▋     | 47494/100000 [14:09:43<8:32:00,  1.71it/s]
Train steps ... :  47%|████▋     | 47495/100000 [14:09:43<8:32:23,  1.71it/s]
Train steps ... :  47%|████▋     | 47496/100000 [14:09:44<8:31:37,  1.71it/s]
Train steps ... :  47%|████▋     | 47497/100000 [14:09:44<8:31:52,  1.71it/s]
Train steps ... :  47%|████▋     | 47498/100000 [14:09:45<8:32:26,  1.71it/s]
Train steps ... :  47%|████▋     | 47499/100000 [14:09:46<8:32:26,  1.71it/s]
Train steps ... :  48%|████▊     | 47500/100000 [14:09:46<8:32:04,  1.71it/s]Step... (47500 / 100000 | Loss: 0.8033710718154907, Learning Rate: 5.276381909547739e-05)
+
                                                                             
Step... (47500 / 100000 | Loss: 0.9841077327728271, Learning Rate: 5.276381909547739e-05)
+
Train steps ... :  48%|████▊     | 47500/100000 [14:09:46<8:32:04,  1.71it/s]
Train steps ... :  48%|████▊     | 47501/100000 [14:09:47<8:32:35,  1.71it/s]
Train steps ... :  48%|████▊     | 47502/100000 [14:09:47<8:31:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47503/100000 [14:09:48<8:31:35,  1.71it/s]
Train steps ... :  48%|████▊     | 47504/100000 [14:09:48<8:31:24,  1.71it/s]
Train steps ... :  48%|████▊     | 47505/100000 [14:09:49<8:31:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47506/100000 [14:09:50<8:31:36,  1.71it/s]
Train steps ... :  48%|████▊     | 47507/100000 [14:09:50<8:31:41,  1.71it/s]
Train steps ... :  48%|████▊     | 47508/100000 [14:09:51<8:31:24,  1.71it/s]
Train steps ... :  48%|████▊     | 47509/100000 [14:09:51<8:30:59,  1.71it/s]
Train steps ... :  48%|████▊     | 47510/100000 [14:09:52<8:31:55,  1.71it/s]
Train steps ... :  48%|████▊     | 47511/100000 [14:09:53<8:32:19,  1.71it/s]
Train steps ... :  48%|████▊     | 47512/100000 [14:09:53<8:32:24,  1.71it/s]
Train steps ... :  48%|████▊     | 47513/100000 [14:09:54<8:31:58,  1.71it/s]
Train steps ... :  48%|████▊     | 47514/100000 [14:09:54<8:32:04,  1.71it/s]
Train steps ... :  48%|████▊     | 47515/100000 [14:09:55<8:31:54,  1.71it/s]
Train steps ... :  48%|████▊     | 47516/100000 [14:09:56<8:32:25,  1.71it/s]
Train steps ... :  48%|████▊     | 47517/100000 [14:09:56<8:32:02,  1.71it/s]
Train steps ... :  48%|████▊     | 47518/100000 [14:09:57<8:31:25,  1.71it/s]
Train steps ... :  48%|████▊     | 47519/100000 [14:09:57<8:31:18,  1.71it/s]
Train steps ... :  48%|████▊     | 47520/100000 [14:09:58<8:31:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47521/100000 [14:09:58<8:31:22,  1.71it/s]
Train steps ... :  48%|████▊     | 47522/100000 [14:09:59<8:31:56,  1.71it/s]
Train steps ... :  48%|████▊     | 47523/100000 [14:10:00<8:31:36,  1.71it/s]
Train steps ... :  48%|████▊     | 47524/100000 [14:10:00<8:31:07,  1.71it/s]
Train steps ... :  48%|████▊     | 47525/100000 [14:10:01<8:31:28,  1.71it/s]Step... (47525 / 100000 | Loss: 0.9813603758811951, Learning Rate: 5.2738693467336684e-05)
+
                                                                             
Step... (47525 / 100000 | Loss: 0.7361882925033569, Learning Rate: 5.2738693467336684e-05)
+
Train steps ... :  48%|████▊     | 47525/100000 [14:10:01<8:31:28,  1.71it/s]
Train steps ... :  48%|████▊     | 47526/100000 [14:10:01<8:31:20,  1.71it/s]
Train steps ... :  48%|████▊     | 47527/100000 [14:10:02<8:31:02,  1.71it/s]
Train steps ... :  48%|████▊     | 47528/100000 [14:10:03<8:31:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47529/100000 [14:10:03<8:30:54,  1.71it/s]
Train steps ... :  48%|████▊     | 47530/100000 [14:10:04<8:31:18,  1.71it/s]
Train steps ... :  48%|████▊     | 47531/100000 [14:10:04<8:32:27,  1.71it/s]
Train steps ... :  48%|████▊     | 47532/100000 [14:10:05<8:32:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47533/100000 [14:10:05<8:31:15,  1.71it/s]
Train steps ... :  48%|████▊     | 47534/100000 [14:10:06<8:30:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47535/100000 [14:10:07<8:31:13,  1.71it/s]
Train steps ... :  48%|████▊     | 47536/100000 [14:10:07<8:31:08,  1.71it/s]
Train steps ... :  48%|████▊     | 47537/100000 [14:10:08<8:30:40,  1.71it/s]
Train steps ... :  48%|████▊     | 47538/100000 [14:10:08<8:30:30,  1.71it/s]
Train steps ... :  48%|████▊     | 47539/100000 [14:10:09<8:30:36,  1.71it/s]
Train steps ... :  48%|████▊     | 47540/100000 [14:10:10<8:30:50,  1.71it/s]
Train steps ... :  48%|████▊     | 47541/100000 [14:10:10<8:31:14,  1.71it/s]
Train steps ... :  48%|████▊     | 47542/100000 [14:10:11<8:31:01,  1.71it/s]
Train steps ... :  48%|████▊     | 47543/100000 [14:10:11<8:31:40,  1.71it/s]
Train steps ... :  48%|████▊     | 47544/100000 [14:10:12<8:31:55,  1.71it/s]
Train steps ... :  48%|████▊     | 47545/100000 [14:10:12<8:31:37,  1.71it/s]
Train steps ... :  48%|████▊     | 47546/100000 [14:10:13<8:31:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47547/100000 [14:10:14<8:31:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47548/100000 [14:10:14<8:31:34,  1.71it/s]
Train steps ... :  48%|████▊     | 47549/100000 [14:10:15<8:31:27,  1.71it/s]
Train steps ... :  48%|████▊     | 47550/100000 [14:10:15<8:31:17,  1.71it/s]Step... (47550 / 100000 | Loss: 0.6513136625289917, Learning Rate: 5.271356783919599e-05)
+
                                                                             
Step... (47550 / 100000 | Loss: 0.7854387760162354, Learning Rate: 5.271356783919599e-05)
+
Train steps ... :  48%|████▊     | 47550/100000 [14:10:16<8:31:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47551/100000 [14:10:16<8:31:48,  1.71it/s]
Train steps ... :  48%|████▊     | 47552/100000 [14:10:17<8:31:52,  1.71it/s]
Train steps ... :  48%|████▊     | 47553/100000 [14:10:17<8:31:59,  1.71it/s]
Train steps ... :  48%|████▊     | 47554/100000 [14:10:18<8:32:40,  1.70it/s]
Train steps ... :  48%|████▊     | 47555/100000 [14:10:18<8:32:28,  1.71it/s]
Train steps ... :  48%|████▊     | 47556/100000 [14:10:19<8:32:33,  1.71it/s]
Train steps ... :  48%|████▊     | 47557/100000 [14:10:20<8:31:52,  1.71it/s]
Train steps ... :  48%|████▊     | 47558/100000 [14:10:20<8:32:02,  1.71it/s]
Train steps ... :  48%|████▊     | 47559/100000 [14:10:21<8:31:39,  1.71it/s]
Train steps ... :  48%|████▊     | 47560/100000 [14:10:21<8:31:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47561/100000 [14:10:22<8:31:15,  1.71it/s]
Train steps ... :  48%|████▊     | 47562/100000 [14:10:22<8:31:33,  1.71it/s]
Train steps ... :  48%|████▊     | 47563/100000 [14:10:23<8:31:14,  1.71it/s]
Train steps ... :  48%|████▊     | 47564/100000 [14:10:24<8:31:01,  1.71it/s]
Train steps ... :  48%|████▊     | 47565/100000 [14:10:24<8:31:57,  1.71it/s]
Train steps ... :  48%|████▊     | 47566/100000 [14:10:25<8:31:49,  1.71it/s]
Train steps ... :  48%|████▊     | 47567/100000 [14:10:25<8:32:12,  1.71it/s]
Train steps ... :  48%|████▊     | 47568/100000 [14:10:26<8:32:23,  1.71it/s]
Train steps ... :  48%|████▊     | 47569/100000 [14:10:27<8:32:07,  1.71it/s]
Train steps ... :  48%|████▊     | 47570/100000 [14:10:27<8:31:27,  1.71it/s]
Train steps ... :  48%|████▊     | 47571/100000 [14:10:28<8:31:27,  1.71it/s]
Train steps ... :  48%|████▊     | 47572/100000 [14:10:28<8:30:52,  1.71it/s]
Train steps ... :  48%|████▊     | 47573/100000 [14:10:29<8:30:38,  1.71it/s]
Train steps ... :  48%|████▊     | 47574/100000 [14:10:29<8:30:38,  1.71it/s]
Train steps ... :  48%|████▊     | 47575/100000 [14:10:30<8:30:39,  1.71it/s]Step... (47575 / 100000 | Loss: 0.7213624119758606, Learning Rate: 5.268844221105528e-05)
+
                                                                             
Step... (47575 / 100000 | Loss: 0.7658520936965942, Learning Rate: 5.268844221105528e-05)
+
Train steps ... :  48%|████▊     | 47575/100000 [14:10:30<8:30:39,  1.71it/s]
Train steps ... :  48%|████▊     | 47576/100000 [14:10:31<8:31:12,  1.71it/s]
Train steps ... :  48%|████▊     | 47577/100000 [14:10:31<8:30:45,  1.71it/s]
Train steps ... :  48%|████▊     | 47578/100000 [14:10:32<8:30:36,  1.71it/s]
Train steps ... :  48%|████▊     | 47579/100000 [14:10:32<8:31:08,  1.71it/s]
Train steps ... :  48%|████▊     | 47580/100000 [14:10:33<8:30:58,  1.71it/s]
Train steps ... :  48%|████▊     | 47581/100000 [14:10:34<8:30:29,  1.71it/s]
Train steps ... :  48%|████▊     | 47582/100000 [14:10:34<8:31:10,  1.71it/s]
Train steps ... :  48%|████▊     | 47583/100000 [14:10:35<8:32:02,  1.71it/s]
Train steps ... :  48%|████▊     | 47584/100000 [14:10:35<8:31:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47585/100000 [14:10:36<8:31:07,  1.71it/s]
Train steps ... :  48%|████▊     | 47586/100000 [14:10:36<8:30:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47587/100000 [14:10:37<8:30:49,  1.71it/s]
Train steps ... :  48%|████▊     | 47588/100000 [14:10:38<8:30:40,  1.71it/s]
Train steps ... :  48%|████▊     | 47589/100000 [14:10:38<8:30:49,  1.71it/s]
Train steps ... :  48%|████▊     | 47590/100000 [14:10:39<8:31:20,  1.71it/s]
Train steps ... :  48%|████▊     | 47591/100000 [14:10:39<8:30:54,  1.71it/s]
Train steps ... :  48%|████▊     | 47592/100000 [14:10:40<8:31:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47593/100000 [14:10:41<8:30:53,  1.71it/s]
Train steps ... :  48%|████▊     | 47594/100000 [14:10:41<8:30:45,  1.71it/s]
Train steps ... :  48%|████▊     | 47595/100000 [14:10:42<8:30:34,  1.71it/s]
Train steps ... :  48%|████▊     | 47596/100000 [14:10:42<8:30:26,  1.71it/s]
Train steps ... :  48%|████▊     | 47597/100000 [14:10:43<8:30:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47598/100000 [14:10:43<8:30:15,  1.71it/s]
Train steps ... :  48%|████▊     | 47599/100000 [14:10:44<8:30:33,  1.71it/s]
Train steps ... :  48%|████▊     | 47600/100000 [14:10:45<8:30:24,  1.71it/s]Step... (47600 / 100000 | Loss: 0.6662415266036987, Learning Rate: 5.266331658291458e-05)
+
                                                                             
Step... (47600 / 100000 | Loss: 0.8980718851089478, Learning Rate: 5.266331658291458e-05)
+
Train steps ... :  48%|████▊     | 47600/100000 [14:10:45<8:30:24,  1.71it/s]
Train steps ... :  48%|████▊     | 47601/100000 [14:10:45<8:31:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47602/100000 [14:10:46<8:30:52,  1.71it/s]
Train steps ... :  48%|████▊     | 47603/100000 [14:10:46<8:31:38,  1.71it/s]
Train steps ... :  48%|████▊     | 47604/100000 [14:10:47<8:31:30,  1.71it/s]
Train steps ... :  48%|████▊     | 47605/100000 [14:10:48<8:31:10,  1.71it/s]
Train steps ... :  48%|████▊     | 47606/100000 [14:10:48<8:30:37,  1.71it/s]
Train steps ... :  48%|████▊     | 47607/100000 [14:10:49<8:30:48,  1.71it/s]
Train steps ... :  48%|████▊     | 47608/100000 [14:10:49<8:30:38,  1.71it/s]
Train steps ... :  48%|████▊     | 47609/100000 [14:10:50<8:30:04,  1.71it/s]
Train steps ... :  48%|████▊     | 47610/100000 [14:10:51<8:30:45,  1.71it/s]
Train steps ... :  48%|████▊     | 47611/100000 [14:10:51<8:30:35,  1.71it/s]
Train steps ... :  48%|████▊     | 47612/100000 [14:10:52<8:30:51,  1.71it/s]
Train steps ... :  48%|████▊     | 47613/100000 [14:10:52<8:31:06,  1.71it/s]
Train steps ... :  48%|████▊     | 47614/100000 [14:10:53<8:30:32,  1.71it/s]
Train steps ... :  48%|████▊     | 47615/100000 [14:10:53<8:31:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47616/100000 [14:10:54<8:30:27,  1.71it/s]
Train steps ... :  48%|████▊     | 47617/100000 [14:10:55<8:30:53,  1.71it/s]
Train steps ... :  48%|████▊     | 47618/100000 [14:10:55<8:30:45,  1.71it/s]
Train steps ... :  48%|████▊     | 47619/100000 [14:10:56<8:30:15,  1.71it/s]
Train steps ... :  48%|████▊     | 47620/100000 [14:10:56<8:29:56,  1.71it/s]
Train steps ... :  48%|████▊     | 47621/100000 [14:10:57<8:29:58,  1.71it/s]
Train steps ... :  48%|████▊     | 47622/100000 [14:10:58<8:29:50,  1.71it/s]
Train steps ... :  48%|████▊     | 47623/100000 [14:10:58<8:30:14,  1.71it/s]
Train steps ... :  48%|████▊     | 47624/100000 [14:10:59<8:30:27,  1.71it/s]
Train steps ... :  48%|████▊     | 47625/100000 [14:10:59<8:29:54,  1.71it/s]Step... (47625 / 100000 | Loss: 0.9327548742294312, Learning Rate: 5.263819095477387e-05)
+
                                                                             
Step... (47625 / 100000 | Loss: 0.8089396953582764, Learning Rate: 5.263819095477387e-05)
+
Train steps ... :  48%|████▊     | 47625/100000 [14:11:00<8:29:54,  1.71it/s]
Train steps ... :  48%|████▊     | 47626/100000 [14:11:00<8:30:43,  1.71it/s]
Train steps ... :  48%|████▊     | 47627/100000 [14:11:00<8:30:10,  1.71it/s]
Train steps ... :  48%|████▊     | 47628/100000 [14:11:01<8:29:37,  1.71it/s]
Train steps ... :  48%|████▊     | 47629/100000 [14:11:02<8:29:50,  1.71it/s]
Train steps ... :  48%|████▊     | 47630/100000 [14:11:02<8:30:03,  1.71it/s]
Train steps ... :  48%|████▊     | 47631/100000 [14:11:03<8:29:31,  1.71it/s]
Train steps ... :  48%|████▊     | 47632/100000 [14:11:03<8:30:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47633/100000 [14:11:04<8:31:18,  1.71it/s]
Train steps ... :  48%|████▊     | 47634/100000 [14:11:05<8:30:31,  1.71it/s]
Train steps ... :  48%|████▊     | 47635/100000 [14:11:05<8:29:54,  1.71it/s]
Train steps ... :  48%|████▊     | 47636/100000 [14:11:06<8:30:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47637/100000 [14:11:06<8:30:51,  1.71it/s]
Train steps ... :  48%|████▊     | 47638/100000 [14:11:07<8:30:26,  1.71it/s]
Train steps ... :  48%|████▊     | 47639/100000 [14:11:07<8:30:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47640/100000 [14:11:08<8:30:24,  1.71it/s]
Train steps ... :  48%|████▊     | 47641/100000 [14:11:09<8:30:32,  1.71it/s]
Train steps ... :  48%|████▊     | 47642/100000 [14:11:09<8:31:11,  1.71it/s]
Train steps ... :  48%|████▊     | 47643/100000 [14:11:10<8:30:20,  1.71it/s]
Train steps ... :  48%|████▊     | 47644/100000 [14:11:10<8:30:11,  1.71it/s]
Train steps ... :  48%|████▊     | 47645/100000 [14:11:11<8:30:03,  1.71it/s]
Train steps ... :  48%|████▊     | 47646/100000 [14:11:12<8:29:52,  1.71it/s]
Train steps ... :  48%|████▊     | 47647/100000 [14:11:12<8:29:50,  1.71it/s]
Train steps ... :  48%|████▊     | 47648/100000 [14:11:13<8:30:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47649/100000 [14:11:13<8:30:18,  1.71it/s]
Train steps ... :  48%|████▊     | 47650/100000 [14:11:14<8:29:50,  1.71it/s]Step... (47650 / 100000 | Loss: 0.682300329208374, Learning Rate: 5.2613065326633174e-05)
+
                                                                             
Step... (47650 / 100000 | Loss: 0.6569377183914185, Learning Rate: 5.2613065326633174e-05)
+
Train steps ... :  48%|████▊     | 47650/100000 [14:11:14<8:29:50,  1.71it/s]
Train steps ... :  48%|████▊     | 47651/100000 [14:11:14<8:32:14,  1.70it/s]
Train steps ... :  48%|████▊     | 47652/100000 [14:11:15<8:30:58,  1.71it/s]
Train steps ... :  48%|████▊     | 47653/100000 [14:11:16<8:32:06,  1.70it/s]
Train steps ... :  48%|████▊     | 47654/100000 [14:11:16<8:30:37,  1.71it/s]
Train steps ... :  48%|████▊     | 47655/100000 [14:11:17<8:31:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47656/100000 [14:11:17<8:30:53,  1.71it/s]
Train steps ... :  48%|████▊     | 47657/100000 [14:11:18<8:30:48,  1.71it/s]
Train steps ... :  48%|████▊     | 47658/100000 [14:11:19<8:30:10,  1.71it/s]
Train steps ... :  48%|████▊     | 47659/100000 [14:11:19<8:29:41,  1.71it/s]
Train steps ... :  48%|████▊     | 47660/100000 [14:11:20<8:29:21,  1.71it/s]
Train steps ... :  48%|████▊     | 47661/100000 [14:11:20<8:30:32,  1.71it/s]
Train steps ... :  48%|████▊     | 47662/100000 [14:11:21<8:30:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47663/100000 [14:11:22<8:29:30,  1.71it/s]
Train steps ... :  48%|████▊     | 47664/100000 [14:11:22<8:29:43,  1.71it/s]
Train steps ... :  48%|████▊     | 47665/100000 [14:11:23<8:29:59,  1.71it/s]
Train steps ... :  48%|████▊     | 47666/100000 [14:11:23<8:29:56,  1.71it/s]
Train steps ... :  48%|████▊     | 47667/100000 [14:11:24<8:29:34,  1.71it/s]
Train steps ... :  48%|████▊     | 47668/100000 [14:11:24<8:29:41,  1.71it/s]
Train steps ... :  48%|████▊     | 47669/100000 [14:11:25<8:30:08,  1.71it/s]
Train steps ... :  48%|████▊     | 47670/100000 [14:11:26<8:30:15,  1.71it/s]
Train steps ... :  48%|████▊     | 47671/100000 [14:11:26<8:30:57,  1.71it/s]
Train steps ... :  48%|████▊     | 47672/100000 [14:11:27<8:31:30,  1.71it/s]
Train steps ... :  48%|████▊     | 47673/100000 [14:11:27<8:30:27,  1.71it/s]
Train steps ... :  48%|████▊     | 47674/100000 [14:11:28<8:30:14,  1.71it/s]
Train steps ... :  48%|████▊     | 47675/100000 [14:11:29<8:29:43,  1.71it/s]Step... (47675 / 100000 | Loss: 0.648827850818634, Learning Rate: 5.2587939698492464e-05)
+
                                                                             
Step... (47675 / 100000 | Loss: 0.711555004119873, Learning Rate: 5.2587939698492464e-05)
+
Train steps ... :  48%|████▊     | 47675/100000 [14:11:29<8:29:43,  1.71it/s]
Train steps ... :  48%|████▊     | 47676/100000 [14:11:29<8:29:50,  1.71it/s]
Train steps ... :  48%|████▊     | 47677/100000 [14:11:30<8:29:45,  1.71it/s]
Train steps ... :  48%|████▊     | 47678/100000 [14:11:30<8:29:24,  1.71it/s]
Train steps ... :  48%|████▊     | 47679/100000 [14:11:31<8:29:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47680/100000 [14:11:31<8:30:04,  1.71it/s]
Train steps ... :  48%|████▊     | 47681/100000 [14:11:32<8:30:09,  1.71it/s]
Train steps ... :  48%|████▊     | 47682/100000 [14:11:33<8:29:36,  1.71it/s]
Train steps ... :  48%|████▊     | 47683/100000 [14:11:33<8:29:58,  1.71it/s]
Train steps ... :  48%|████▊     | 47684/100000 [14:11:34<8:30:11,  1.71it/s]
Train steps ... :  48%|████▊     | 47685/100000 [14:11:34<8:30:09,  1.71it/s]
Train steps ... :  48%|████▊     | 47686/100000 [14:11:35<8:29:59,  1.71it/s]
Train steps ... :  48%|████▊     | 47687/100000 [14:11:36<8:30:11,  1.71it/s]
Train steps ... :  48%|████▊     | 47688/100000 [14:11:36<8:30:25,  1.71it/s]
Train steps ... :  48%|████▊     | 47689/100000 [14:11:37<8:30:29,  1.71it/s]
Train steps ... :  48%|████▊     | 47690/100000 [14:11:37<8:30:34,  1.71it/s]
Train steps ... :  48%|████▊     | 47691/100000 [14:11:38<8:29:58,  1.71it/s]
Train steps ... :  48%|████▊     | 47692/100000 [14:11:38<8:30:29,  1.71it/s]
Train steps ... :  48%|████▊     | 47693/100000 [14:11:39<8:31:00,  1.71it/s]
Train steps ... :  48%|████▊     | 47694/100000 [14:11:40<8:30:39,  1.71it/s]
Train steps ... :  48%|████▊     | 47695/100000 [14:11:40<8:31:04,  1.71it/s]
Train steps ... :  48%|████▊     | 47696/100000 [14:11:41<8:30:11,  1.71it/s]
Train steps ... :  48%|████▊     | 47697/100000 [14:11:41<8:30:32,  1.71it/s]
Train steps ... :  48%|████▊     | 47698/100000 [14:11:42<8:30:25,  1.71it/s]
Train steps ... :  48%|████▊     | 47699/100000 [14:11:43<8:29:38,  1.71it/s]
Train steps ... :  48%|████▊     | 47700/100000 [14:11:43<8:29:16,  1.71it/s]Step... (47700 / 100000 | Loss: 0.7152364253997803, Learning Rate: 5.256281407035176e-05)
+
                                                                             
Step... (47700 / 100000 | Loss: 0.6467728614807129, Learning Rate: 5.256281407035176e-05)
+
Train steps ... :  48%|████▊     | 47700/100000 [14:11:43<8:29:16,  1.71it/s]
Train steps ... :  48%|████▊     | 47701/100000 [14:11:44<8:29:40,  1.71it/s]
Train steps ... :  48%|████▊     | 47702/100000 [14:11:44<8:29:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47703/100000 [14:11:45<8:29:36,  1.71it/s]
Train steps ... :  48%|████▊     | 47704/100000 [14:11:45<8:29:16,  1.71it/s]
Train steps ... :  48%|████▊     | 47705/100000 [14:11:46<8:30:20,  1.71it/s]
Train steps ... :  48%|████▊     | 47706/100000 [14:11:47<8:29:25,  1.71it/s]
Train steps ... :  48%|████▊     | 47707/100000 [14:11:47<8:30:06,  1.71it/s]
Train steps ... :  48%|████▊     | 47708/100000 [14:11:48<8:30:35,  1.71it/s]
Train steps ... :  48%|████▊     | 47709/100000 [14:11:48<8:30:10,  1.71it/s]
Train steps ... :  48%|████▊     | 47710/100000 [14:11:49<8:30:30,  1.71it/s]
Train steps ... :  48%|████▊     | 47711/100000 [14:11:50<8:30:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47712/100000 [14:11:50<8:29:45,  1.71it/s]
Train steps ... :  48%|████▊     | 47713/100000 [14:11:51<8:29:20,  1.71it/s]
Train steps ... :  48%|████▊     | 47714/100000 [14:11:51<8:29:43,  1.71it/s]
Train steps ... :  48%|████▊     | 47715/100000 [14:11:52<8:29:23,  1.71it/s]
Train steps ... :  48%|████▊     | 47716/100000 [14:11:53<8:29:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47717/100000 [14:11:53<8:29:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47718/100000 [14:11:54<8:29:34,  1.71it/s]
Train steps ... :  48%|████▊     | 47719/100000 [14:11:54<8:29:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47720/100000 [14:11:55<8:29:41,  1.71it/s]
Train steps ... :  48%|████▊     | 47721/100000 [14:11:55<8:29:18,  1.71it/s]
Train steps ... :  48%|████▊     | 47722/100000 [14:11:56<8:28:43,  1.71it/s]
Train steps ... :  48%|████▊     | 47723/100000 [14:11:57<8:28:40,  1.71it/s]
Train steps ... :  48%|████▊     | 47724/100000 [14:11:57<8:28:28,  1.71it/s]
Train steps ... :  48%|████▊     | 47725/100000 [14:11:58<8:29:07,  1.71it/s]Step... (47725 / 100000 | Loss: 0.9937549829483032, Learning Rate: 5.253768844221105e-05)
+
                                                                             
Step... (47725 / 100000 | Loss: 0.7701163291931152, Learning Rate: 5.253768844221105e-05)
+
Train steps ... :  48%|████▊     | 47725/100000 [14:11:58<8:29:07,  1.71it/s]
Train steps ... :  48%|████▊     | 47726/100000 [14:11:58<8:29:19,  1.71it/s]
Train steps ... :  48%|████▊     | 47727/100000 [14:11:59<8:29:09,  1.71it/s]
Train steps ... :  48%|████▊     | 47728/100000 [14:12:00<8:29:19,  1.71it/s]
Train steps ... :  48%|████▊     | 47729/100000 [14:12:00<8:28:56,  1.71it/s]
Train steps ... :  48%|████▊     | 47730/100000 [14:12:01<8:28:34,  1.71it/s]
Train steps ... :  48%|████▊     | 47731/100000 [14:12:01<8:29:04,  1.71it/s]
Train steps ... :  48%|████▊     | 47732/100000 [14:12:02<8:28:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47733/100000 [14:12:02<8:29:18,  1.71it/s]
Train steps ... :  48%|████▊     | 47734/100000 [14:12:03<8:28:49,  1.71it/s]
Train steps ... :  48%|████▊     | 47735/100000 [14:12:04<8:29:39,  1.71it/s]
Train steps ... :  48%|████▊     | 47736/100000 [14:12:04<8:29:14,  1.71it/s]
Train steps ... :  48%|████▊     | 47737/100000 [14:12:05<8:29:04,  1.71it/s]
Train steps ... :  48%|████▊     | 47738/100000 [14:12:05<8:28:58,  1.71it/s]
Train steps ... :  48%|████▊     | 47739/100000 [14:12:06<8:29:28,  1.71it/s]
Train steps ... :  48%|████▊     | 47740/100000 [14:12:07<8:28:58,  1.71it/s]
Train steps ... :  48%|████▊     | 47741/100000 [14:12:07<8:29:09,  1.71it/s]
Train steps ... :  48%|████▊     | 47742/100000 [14:12:08<8:28:54,  1.71it/s]
Train steps ... :  48%|████▊     | 47743/100000 [14:12:08<8:28:57,  1.71it/s]
Train steps ... :  48%|████▊     | 47744/100000 [14:12:09<8:29:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47745/100000 [14:12:09<8:29:56,  1.71it/s]
Train steps ... :  48%|████▊     | 47746/100000 [14:12:10<8:29:42,  1.71it/s]
Train steps ... :  48%|████▊     | 47747/100000 [14:12:11<8:29:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47748/100000 [14:12:11<8:29:22,  1.71it/s]
Train steps ... :  48%|████▊     | 47749/100000 [14:12:12<8:29:34,  1.71it/s]
Train steps ... :  48%|████▊     | 47750/100000 [14:12:12<8:29:49,  1.71it/s]Step... (47750 / 100000 | Loss: 0.899582028388977, Learning Rate: 5.2512562814070354e-05)
+
                                                                             
Step... (47750 / 100000 | Loss: 0.7824035882949829, Learning Rate: 5.2512562814070354e-05)
+
Train steps ... :  48%|████▊     | 47750/100000 [14:12:13<8:29:49,  1.71it/s]
Train steps ... :  48%|████▊     | 47751/100000 [14:12:13<8:29:43,  1.71it/s]
Train steps ... :  48%|████▊     | 47752/100000 [14:12:14<8:29:39,  1.71it/s]
Train steps ... :  48%|████▊     | 47753/100000 [14:12:14<8:30:20,  1.71it/s]
Train steps ... :  48%|████▊     | 47754/100000 [14:12:15<8:29:40,  1.71it/s]
Train steps ... :  48%|████▊     | 47755/100000 [14:12:15<8:29:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47756/100000 [14:12:16<8:29:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47757/100000 [14:12:16<8:29:22,  1.71it/s]
Train steps ... :  48%|████▊     | 47758/100000 [14:12:17<8:28:49,  1.71it/s]
Train steps ... :  48%|████▊     | 47759/100000 [14:12:18<8:29:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47760/100000 [14:12:18<8:29:26,  1.71it/s]
Train steps ... :  48%|████▊     | 47761/100000 [14:12:19<8:29:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47762/100000 [14:12:19<8:28:37,  1.71it/s]
Train steps ... :  48%|████▊     | 47763/100000 [14:12:20<8:28:50,  1.71it/s]
Train steps ... :  48%|████▊     | 47764/100000 [14:12:21<8:29:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47765/100000 [14:12:21<8:29:35,  1.71it/s]
Train steps ... :  48%|████▊     | 47766/100000 [14:12:22<8:29:07,  1.71it/s]
Train steps ... :  48%|████▊     | 47767/100000 [14:12:22<8:28:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47768/100000 [14:12:23<8:28:53,  1.71it/s]
Train steps ... :  48%|████▊     | 47769/100000 [14:12:24<8:28:42,  1.71it/s]
Train steps ... :  48%|████▊     | 47770/100000 [14:12:24<8:28:39,  1.71it/s]
Train steps ... :  48%|████▊     | 47771/100000 [14:12:25<8:29:50,  1.71it/s]
Train steps ... :  48%|████▊     | 47772/100000 [14:12:25<8:29:53,  1.71it/s]
Train steps ... :  48%|████▊     | 47773/100000 [14:12:26<8:29:25,  1.71it/s]
Train steps ... :  48%|████▊     | 47774/100000 [14:12:26<8:30:56,  1.70it/s]
Train steps ... :  48%|████▊     | 47775/100000 [14:12:27<8:31:11,  1.70it/s]Step... (47775 / 100000 | Loss: 0.8891456127166748, Learning Rate: 5.248743718592966e-05)
+
                                                                             
Step... (47775 / 100000 | Loss: 0.8751808404922485, Learning Rate: 5.248743718592966e-05)
+
Train steps ... :  48%|████▊     | 47775/100000 [14:12:27<8:31:11,  1.70it/s]
Train steps ... :  48%|████▊     | 47776/100000 [14:12:28<8:30:24,  1.71it/s]
Train steps ... :  48%|████▊     | 47777/100000 [14:12:28<8:29:45,  1.71it/s]
Train steps ... :  48%|████▊     | 47778/100000 [14:12:29<8:29:34,  1.71it/s]
Train steps ... :  48%|████▊     | 47779/100000 [14:12:29<8:29:22,  1.71it/s]
Train steps ... :  48%|████▊     | 47780/100000 [14:12:30<8:29:19,  1.71it/s]
Train steps ... :  48%|████▊     | 47781/100000 [14:12:31<8:28:51,  1.71it/s]
Train steps ... :  48%|████▊     | 47782/100000 [14:12:31<8:28:51,  1.71it/s]
Train steps ... :  48%|████▊     | 47783/100000 [14:12:32<8:28:36,  1.71it/s]
Train steps ... :  48%|████▊     | 47784/100000 [14:12:32<8:29:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47785/100000 [14:12:33<8:28:55,  1.71it/s]
Train steps ... :  48%|████▊     | 47786/100000 [14:12:33<8:29:31,  1.71it/s]
Train steps ... :  48%|████▊     | 47787/100000 [14:12:34<8:29:10,  1.71it/s]
Train steps ... :  48%|████▊     | 47788/100000 [14:12:35<8:29:15,  1.71it/s]
Train steps ... :  48%|████▊     | 47789/100000 [14:12:35<8:28:56,  1.71it/s]
Train steps ... :  48%|████▊     | 47790/100000 [14:12:36<8:28:29,  1.71it/s]
Train steps ... :  48%|████▊     | 47791/100000 [14:12:36<8:29:35,  1.71it/s]
Train steps ... :  48%|████▊     | 47792/100000 [14:12:37<8:29:15,  1.71it/s]
Train steps ... :  48%|████▊     | 47793/100000 [14:12:38<8:29:16,  1.71it/s]
Train steps ... :  48%|████▊     | 47794/100000 [14:12:38<8:28:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47795/100000 [14:12:39<8:28:31,  1.71it/s]
Train steps ... :  48%|████▊     | 47796/100000 [14:12:39<8:28:30,  1.71it/s]
Train steps ... :  48%|████▊     | 47797/100000 [14:12:40<8:28:59,  1.71it/s]
Train steps ... :  48%|████▊     | 47798/100000 [14:12:40<8:29:16,  1.71it/s]
Train steps ... :  48%|████▊     | 47799/100000 [14:12:41<8:28:44,  1.71it/s]
Train steps ... :  48%|████▊     | 47800/100000 [14:12:42<8:28:13,  1.71it/s]Step... (47800 / 100000 | Loss: 0.7742588520050049, Learning Rate: 5.246231155778895e-05)
+
                                                                             
Step... (47800 / 100000 | Loss: 0.7949121594429016, Learning Rate: 5.246231155778895e-05)
+
Train steps ... :  48%|████▊     | 47800/100000 [14:12:42<8:28:13,  1.71it/s]
Train steps ... :  48%|████▊     | 47801/100000 [14:12:42<8:28:07,  1.71it/s]
Train steps ... :  48%|████▊     | 47802/100000 [14:12:43<8:28:13,  1.71it/s]
Train steps ... :  48%|████▊     | 47803/100000 [14:12:43<8:28:48,  1.71it/s]
Train steps ... :  48%|████▊     | 47804/100000 [14:12:44<8:28:53,  1.71it/s]
Train steps ... :  48%|████▊     | 47805/100000 [14:12:45<8:29:06,  1.71it/s]
Train steps ... :  48%|████▊     | 47806/100000 [14:12:45<8:29:25,  1.71it/s]
Train steps ... :  48%|████▊     | 47807/100000 [14:12:46<8:29:09,  1.71it/s]
Train steps ... :  48%|████▊     | 47808/100000 [14:12:46<8:29:06,  1.71it/s]
Train steps ... :  48%|████▊     | 47809/100000 [14:12:47<8:29:09,  1.71it/s]
Train steps ... :  48%|████▊     | 47810/100000 [14:12:47<8:28:50,  1.71it/s]
Train steps ... :  48%|████▊     | 47811/100000 [14:12:48<8:28:43,  1.71it/s]
Train steps ... :  48%|████▊     | 47812/100000 [14:12:49<8:28:45,  1.71it/s]
Train steps ... :  48%|████▊     | 47813/100000 [14:12:49<8:28:18,  1.71it/s]
Train steps ... :  48%|████▊     | 47814/100000 [14:12:50<8:27:52,  1.71it/s]
Train steps ... :  48%|████▊     | 47815/100000 [14:12:50<8:27:55,  1.71it/s]
Train steps ... :  48%|████▊     | 47816/100000 [14:12:51<8:28:21,  1.71it/s]
Train steps ... :  48%|████▊     | 47817/100000 [14:12:52<8:28:45,  1.71it/s]
Train steps ... :  48%|████▊     | 47818/100000 [14:12:52<8:28:39,  1.71it/s]
Train steps ... :  48%|████▊     | 47819/100000 [14:12:53<8:28:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47820/100000 [14:12:53<8:30:25,  1.70it/s]
Train steps ... :  48%|████▊     | 47821/100000 [14:12:54<8:30:52,  1.70it/s]
Train steps ... :  48%|████▊     | 47822/100000 [14:12:55<8:29:49,  1.71it/s]
Train steps ... :  48%|████▊     | 47823/100000 [14:12:55<8:31:05,  1.70it/s]
Train steps ... :  48%|████▊     | 47824/100000 [14:12:56<8:30:42,  1.70it/s]
Train steps ... :  48%|████▊     | 47825/100000 [14:12:56<8:29:37,  1.71it/s]Step... (47825 / 100000 | Loss: 0.8251168131828308, Learning Rate: 5.2437185929648244e-05)
+
                                                                             
Step... (47825 / 100000 | Loss: 0.7703317403793335, Learning Rate: 5.2437185929648244e-05)
+
Train steps ... :  48%|████▊     | 47825/100000 [14:12:57<8:29:37,  1.71it/s]
Train steps ... :  48%|████▊     | 47826/100000 [14:12:57<8:29:22,  1.71it/s]
Train steps ... :  48%|████▊     | 47827/100000 [14:12:57<8:28:27,  1.71it/s]
Train steps ... :  48%|████▊     | 47828/100000 [14:12:58<8:28:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47829/100000 [14:12:59<8:28:15,  1.71it/s]
Train steps ... :  48%|████▊     | 47830/100000 [14:12:59<8:28:29,  1.71it/s]
Train steps ... :  48%|████▊     | 47831/100000 [14:13:00<8:28:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47832/100000 [14:13:00<8:28:59,  1.71it/s]
Train steps ... :  48%|████▊     | 47833/100000 [14:13:01<8:28:51,  1.71it/s]
Train steps ... :  48%|████▊     | 47834/100000 [14:13:02<8:28:32,  1.71it/s]
Train steps ... :  48%|████▊     | 47835/100000 [14:13:02<8:28:08,  1.71it/s]
Train steps ... :  48%|████▊     | 47836/100000 [14:13:03<8:28:34,  1.71it/s]
Train steps ... :  48%|████▊     | 47837/100000 [14:13:03<8:29:23,  1.71it/s]
Train steps ... :  48%|████▊     | 47838/100000 [14:13:04<8:29:23,  1.71it/s]
Train steps ... :  48%|████▊     | 47839/100000 [14:13:04<8:28:57,  1.71it/s]
Train steps ... :  48%|████▊     | 47840/100000 [14:13:05<8:29:24,  1.71it/s]
Train steps ... :  48%|████▊     | 47841/100000 [14:13:06<8:29:28,  1.71it/s]
Train steps ... :  48%|████▊     | 47842/100000 [14:13:06<8:29:48,  1.71it/s]
Train steps ... :  48%|████▊     | 47843/100000 [14:13:07<8:29:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47844/100000 [14:13:07<8:28:31,  1.71it/s]
Train steps ... :  48%|████▊     | 47845/100000 [14:13:08<8:28:15,  1.71it/s]
Train steps ... :  48%|████▊     | 47846/100000 [14:13:09<8:27:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47847/100000 [14:13:09<8:27:26,  1.71it/s]
Train steps ... :  48%|████▊     | 47848/100000 [14:13:10<8:27:39,  1.71it/s]
Train steps ... :  48%|████▊     | 47849/100000 [14:13:10<8:28:03,  1.71it/s]
Train steps ... :  48%|████▊     | 47850/100000 [14:13:11<8:27:58,  1.71it/s]Step... (47850 / 100000 | Loss: 0.6420678496360779, Learning Rate: 5.241206030150754e-05)
+
                                                                             
Step... (47850 / 100000 | Loss: 0.8584266901016235, Learning Rate: 5.241206030150754e-05)
+
Train steps ... :  48%|████▊     | 47850/100000 [14:13:11<8:27:58,  1.71it/s]
Train steps ... :  48%|████▊     | 47851/100000 [14:13:11<8:28:01,  1.71it/s]
Train steps ... :  48%|████▊     | 47852/100000 [14:13:12<8:28:31,  1.71it/s]
Train steps ... :  48%|████▊     | 47853/100000 [14:13:13<8:28:28,  1.71it/s]
Train steps ... :  48%|████▊     | 47854/100000 [14:13:13<8:28:18,  1.71it/s]
Train steps ... :  48%|████▊     | 47855/100000 [14:13:14<8:27:59,  1.71it/s]
Train steps ... :  48%|████▊     | 47856/100000 [14:13:14<8:28:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47857/100000 [14:13:15<8:28:19,  1.71it/s]
Train steps ... :  48%|████▊     | 47858/100000 [14:13:16<8:27:49,  1.71it/s]
Train steps ... :  48%|████▊     | 47859/100000 [14:13:16<8:28:01,  1.71it/s]
Train steps ... :  48%|████▊     | 47860/100000 [14:13:17<8:27:36,  1.71it/s]
Train steps ... :  48%|████▊     | 47861/100000 [14:13:17<8:28:26,  1.71it/s]
Train steps ... :  48%|████▊     | 47862/100000 [14:13:18<8:28:14,  1.71it/s]
Train steps ... :  48%|████▊     | 47863/100000 [14:13:19<8:28:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47864/100000 [14:13:19<8:28:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47865/100000 [14:13:20<8:27:59,  1.71it/s]
Train steps ... :  48%|████▊     | 47866/100000 [14:13:20<8:27:42,  1.71it/s]
Train steps ... :  48%|████▊     | 47867/100000 [14:13:21<8:27:26,  1.71it/s]
Train steps ... :  48%|████▊     | 47868/100000 [14:13:21<8:27:25,  1.71it/s]
Train steps ... :  48%|████▊     | 47869/100000 [14:13:22<8:27:26,  1.71it/s]
Train steps ... :  48%|████▊     | 47870/100000 [14:13:23<8:27:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47871/100000 [14:13:23<8:27:26,  1.71it/s]
Train steps ... :  48%|████▊     | 47872/100000 [14:13:24<8:28:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47873/100000 [14:13:24<8:28:02,  1.71it/s]
Train steps ... :  48%|████▊     | 47874/100000 [14:13:25<8:28:43,  1.71it/s]
Train steps ... :  48%|████▊     | 47875/100000 [14:13:26<8:30:19,  1.70it/s]Step... (47875 / 100000 | Loss: 1.032800555229187, Learning Rate: 5.238693467336684e-05)
+
                                                                             
Step... (47875 / 100000 | Loss: 0.7710496187210083, Learning Rate: 5.238693467336684e-05)
+
Train steps ... :  48%|████▊     | 47875/100000 [14:13:26<8:30:19,  1.70it/s]
Train steps ... :  48%|████▊     | 47876/100000 [14:13:26<8:28:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47877/100000 [14:13:27<8:28:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47878/100000 [14:13:27<8:27:59,  1.71it/s]
Train steps ... :  48%|████▊     | 47879/100000 [14:13:28<8:28:03,  1.71it/s]
Train steps ... :  48%|████▊     | 47880/100000 [14:13:28<8:28:22,  1.71it/s]
Train steps ... :  48%|████▊     | 47881/100000 [14:13:29<8:28:04,  1.71it/s]
Train steps ... :  48%|████▊     | 47882/100000 [14:13:30<8:27:53,  1.71it/s]
Train steps ... :  48%|████▊     | 47883/100000 [14:13:30<8:28:01,  1.71it/s]
Train steps ... :  48%|████▊     | 47884/100000 [14:13:31<8:27:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47885/100000 [14:13:31<8:27:31,  1.71it/s]
Train steps ... :  48%|████▊     | 47886/100000 [14:13:32<8:28:08,  1.71it/s]
Train steps ... :  48%|████▊     | 47887/100000 [14:13:33<8:27:55,  1.71it/s]
Train steps ... :  48%|████▊     | 47888/100000 [14:13:33<8:28:24,  1.71it/s]
Train steps ... :  48%|████▊     | 47889/100000 [14:13:34<8:27:41,  1.71it/s]
Train steps ... :  48%|████▊     | 47890/100000 [14:13:34<8:28:22,  1.71it/s]
Train steps ... :  48%|████▊     | 47891/100000 [14:13:35<8:28:37,  1.71it/s]
Train steps ... :  48%|████▊     | 47892/100000 [14:13:35<8:28:37,  1.71it/s]
Train steps ... :  48%|████▊     | 47893/100000 [14:13:36<8:28:00,  1.71it/s]
Train steps ... :  48%|████▊     | 47894/100000 [14:13:37<8:28:32,  1.71it/s]
Train steps ... :  48%|████▊     | 47895/100000 [14:13:37<8:28:54,  1.71it/s]
Train steps ... :  48%|████▊     | 47896/100000 [14:13:38<8:28:12,  1.71it/s]
Train steps ... :  48%|████▊     | 47897/100000 [14:13:38<8:28:15,  1.71it/s]
Train steps ... :  48%|████▊     | 47898/100000 [14:13:39<8:28:29,  1.71it/s]
Train steps ... :  48%|████▊     | 47899/100000 [14:13:40<8:28:02,  1.71it/s]
Train steps ... :  48%|████▊     | 47900/100000 [14:13:40<8:28:19,  1.71it/s]Step... (47900 / 100000 | Loss: 0.6544508934020996, Learning Rate: 5.236180904522613e-05)
+
                                                                             
Step... (47900 / 100000 | Loss: 0.8416063189506531, Learning Rate: 5.236180904522613e-05)
+
Train steps ... :  48%|████▊     | 47900/100000 [14:13:40<8:28:19,  1.71it/s]
Train steps ... :  48%|████▊     | 47901/100000 [14:13:41<8:28:41,  1.71it/s]
Train steps ... :  48%|████▊     | 47902/100000 [14:13:41<8:28:15,  1.71it/s]
Train steps ... :  48%|████▊     | 47903/100000 [14:13:42<8:27:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47904/100000 [14:13:42<8:27:54,  1.71it/s]
Train steps ... :  48%|████▊     | 47905/100000 [14:13:43<8:28:12,  1.71it/s]
Train steps ... :  48%|████▊     | 47906/100000 [14:13:44<8:29:28,  1.70it/s]
Train steps ... :  48%|████▊     | 47907/100000 [14:13:44<8:28:34,  1.71it/s]
Train steps ... :  48%|████▊     | 47908/100000 [14:13:45<8:28:45,  1.71it/s]
Train steps ... :  48%|████▊     | 47909/100000 [14:13:45<8:28:39,  1.71it/s]
Train steps ... :  48%|████▊     | 47910/100000 [14:13:46<8:27:58,  1.71it/s]
Train steps ... :  48%|████▊     | 47911/100000 [14:13:47<8:27:37,  1.71it/s]
Train steps ... :  48%|████▊     | 47912/100000 [14:13:47<8:27:41,  1.71it/s]
Train steps ... :  48%|████▊     | 47913/100000 [14:13:48<8:27:25,  1.71it/s]
Train steps ... :  48%|████▊     | 47914/100000 [14:13:48<8:27:00,  1.71it/s]
Train steps ... :  48%|████▊     | 47915/100000 [14:13:49<8:27:42,  1.71it/s]
Train steps ... :  48%|████▊     | 47916/100000 [14:13:50<8:27:52,  1.71it/s]
Train steps ... :  48%|████▊     | 47917/100000 [14:13:50<8:28:25,  1.71it/s]
Train steps ... :  48%|████▊     | 47918/100000 [14:13:51<8:28:49,  1.71it/s]
Train steps ... :  48%|████▊     | 47919/100000 [14:13:51<8:28:44,  1.71it/s]
Train steps ... :  48%|████▊     | 47920/100000 [14:13:52<8:28:20,  1.71it/s]
Train steps ... :  48%|████▊     | 47921/100000 [14:13:52<8:28:24,  1.71it/s]
Train steps ... :  48%|████▊     | 47922/100000 [14:13:53<8:27:43,  1.71it/s]
Train steps ... :  48%|████▊     | 47923/100000 [14:13:54<8:27:53,  1.71it/s]
Train steps ... :  48%|████▊     | 47924/100000 [14:13:54<8:28:03,  1.71it/s]
Train steps ... :  48%|████▊     | 47925/100000 [14:13:55<8:27:52,  1.71it/s]Step... (47925 / 100000 | Loss: 0.8186078667640686, Learning Rate: 5.233668341708543e-05)
+
                                                                             
Step... (47925 / 100000 | Loss: 0.9347899556159973, Learning Rate: 5.233668341708543e-05)
+
Train steps ... :  48%|████▊     | 47925/100000 [14:13:55<8:27:52,  1.71it/s]
Train steps ... :  48%|████▊     | 47926/100000 [14:13:55<8:28:29,  1.71it/s]
Train steps ... :  48%|████▊     | 47927/100000 [14:13:56<8:28:21,  1.71it/s]
Train steps ... :  48%|████▊     | 47928/100000 [14:13:57<8:28:29,  1.71it/s]
Train steps ... :  48%|████▊     | 47929/100000 [14:13:57<8:28:13,  1.71it/s]
Train steps ... :  48%|████▊     | 47930/100000 [14:13:58<8:28:31,  1.71it/s]
Train steps ... :  48%|████▊     | 47931/100000 [14:13:58<8:27:59,  1.71it/s]
Train steps ... :  48%|████▊     | 47932/100000 [14:13:59<8:27:38,  1.71it/s]
Train steps ... :  48%|████▊     | 47933/100000 [14:13:59<8:28:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47934/100000 [14:14:00<8:28:11,  1.71it/s]
Train steps ... :  48%|████▊     | 47935/100000 [14:14:01<8:28:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47936/100000 [14:14:01<8:27:53,  1.71it/s]
Train steps ... :  48%|████▊     | 47937/100000 [14:14:02<8:27:19,  1.71it/s]
Train steps ... :  48%|████▊     | 47938/100000 [14:14:02<8:27:43,  1.71it/s]
Train steps ... :  48%|████▊     | 47939/100000 [14:14:03<8:27:13,  1.71it/s]
Train steps ... :  48%|████▊     | 47940/100000 [14:14:04<8:27:40,  1.71it/s]
Train steps ... :  48%|████▊     | 47941/100000 [14:14:04<8:27:17,  1.71it/s]
Train steps ... :  48%|████▊     | 47942/100000 [14:14:05<8:27:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47943/100000 [14:14:05<8:27:10,  1.71it/s]
Train steps ... :  48%|████▊     | 47944/100000 [14:14:06<8:27:52,  1.71it/s]
Train steps ... :  48%|████▊     | 47945/100000 [14:14:06<8:28:21,  1.71it/s]
Train steps ... :  48%|████▊     | 47946/100000 [14:14:07<8:28:48,  1.71it/s]
Train steps ... :  48%|████▊     | 47947/100000 [14:14:08<8:27:56,  1.71it/s]
Train steps ... :  48%|████▊     | 47948/100000 [14:14:08<8:27:49,  1.71it/s]
Train steps ... :  48%|████▊     | 47949/100000 [14:14:09<8:26:55,  1.71it/s]
Train steps ... :  48%|████▊     | 47950/100000 [14:14:09<8:27:02,  1.71it/s]Step... (47950 / 100000 | Loss: 0.7316240072250366, Learning Rate: 5.231155778894472e-05)
+
                                                                             
Step... (47950 / 100000 | Loss: 0.6776219606399536, Learning Rate: 5.231155778894472e-05)
+
Train steps ... :  48%|████▊     | 47950/100000 [14:14:10<8:27:02,  1.71it/s]
Train steps ... :  48%|████▊     | 47951/100000 [14:14:10<8:27:19,  1.71it/s]
Train steps ... :  48%|████▊     | 47952/100000 [14:14:11<8:26:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47953/100000 [14:14:11<8:26:33,  1.71it/s]
Train steps ... :  48%|████▊     | 47954/100000 [14:14:12<8:26:21,  1.71it/s]
Train steps ... :  48%|████▊     | 47955/100000 [14:14:12<8:27:26,  1.71it/s]
Train steps ... :  48%|████▊     | 47956/100000 [14:14:13<8:27:40,  1.71it/s]
Train steps ... :  48%|████▊     | 47957/100000 [14:14:14<8:27:26,  1.71it/s]
Train steps ... :  48%|████▊     | 47958/100000 [14:14:14<8:27:03,  1.71it/s]
Train steps ... :  48%|████▊     | 47959/100000 [14:14:15<8:27:07,  1.71it/s]
Train steps ... :  48%|████▊     | 47960/100000 [14:14:15<8:26:46,  1.71it/s]
Train steps ... :  48%|████▊     | 47961/100000 [14:14:16<8:27:43,  1.71it/s]
Train steps ... :  48%|████▊     | 47962/100000 [14:14:16<8:27:59,  1.71it/s]
Train steps ... :  48%|████▊     | 47963/100000 [14:14:17<8:27:18,  1.71it/s]
Train steps ... :  48%|████▊     | 47964/100000 [14:14:18<8:28:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47965/100000 [14:14:18<8:27:07,  1.71it/s]
Train steps ... :  48%|████▊     | 47966/100000 [14:14:19<8:26:37,  1.71it/s]
Train steps ... :  48%|████▊     | 47967/100000 [14:14:19<8:26:52,  1.71it/s]
Train steps ... :  48%|████▊     | 47968/100000 [14:14:20<8:26:58,  1.71it/s]
Train steps ... :  48%|████▊     | 47969/100000 [14:14:21<8:26:30,  1.71it/s]
Train steps ... :  48%|████▊     | 47970/100000 [14:14:21<8:26:41,  1.71it/s]
Train steps ... :  48%|████▊     | 47971/100000 [14:14:22<8:26:58,  1.71it/s]
Train steps ... :  48%|████▊     | 47972/100000 [14:14:22<8:27:08,  1.71it/s]
Train steps ... :  48%|████▊     | 47973/100000 [14:14:23<8:27:07,  1.71it/s]
Train steps ... :  48%|████▊     | 47974/100000 [14:14:23<8:26:51,  1.71it/s]
Train steps ... :  48%|████▊     | 47975/100000 [14:14:24<8:27:01,  1.71it/s]Step... (47975 / 100000 | Loss: 0.8892427682876587, Learning Rate: 5.2286432160804023e-05)
+
                                                                             
Step... (47975 / 100000 | Loss: 0.7101600170135498, Learning Rate: 5.2286432160804023e-05)
+
Train steps ... :  48%|████▊     | 47975/100000 [14:14:24<8:27:01,  1.71it/s]
Train steps ... :  48%|████▊     | 47976/100000 [14:14:25<8:27:22,  1.71it/s]
Train steps ... :  48%|████▊     | 47977/100000 [14:14:25<8:27:08,  1.71it/s]
Train steps ... :  48%|████▊     | 47978/100000 [14:14:26<8:27:13,  1.71it/s]
Train steps ... :  48%|████▊     | 47979/100000 [14:14:26<8:28:35,  1.70it/s]
Train steps ... :  48%|████▊     | 47980/100000 [14:14:27<8:28:32,  1.70it/s]
Train steps ... :  48%|████▊     | 47981/100000 [14:14:28<8:27:49,  1.71it/s]
Train steps ... :  48%|████▊     | 47982/100000 [14:14:28<8:27:32,  1.71it/s]
Train steps ... :  48%|████▊     | 47983/100000 [14:14:29<8:28:05,  1.71it/s]
Train steps ... :  48%|████▊     | 47984/100000 [14:14:29<8:28:04,  1.71it/s]
Train steps ... :  48%|████▊     | 47985/100000 [14:14:30<8:27:38,  1.71it/s]
Train steps ... :  48%|████▊     | 47986/100000 [14:14:30<8:28:16,  1.71it/s]
Train steps ... :  48%|████▊     | 47987/100000 [14:14:31<8:27:43,  1.71it/s]
Train steps ... :  48%|████▊     | 47988/100000 [14:14:32<8:27:35,  1.71it/s]
Train steps ... :  48%|████▊     | 47989/100000 [14:14:32<8:27:14,  1.71it/s]
Train steps ... :  48%|████▊     | 47990/100000 [14:14:33<8:27:39,  1.71it/s]
Train steps ... :  48%|████▊     | 47991/100000 [14:14:33<8:27:11,  1.71it/s]
Train steps ... :  48%|████▊     | 47992/100000 [14:14:34<8:26:47,  1.71it/s]
Train steps ... :  48%|████▊     | 47993/100000 [14:14:35<8:26:52,  1.71it/s]
Train steps ... :  48%|████▊     | 47994/100000 [14:14:35<8:27:09,  1.71it/s]
Train steps ... :  48%|████▊     | 47995/100000 [14:14:36<8:26:40,  1.71it/s]
Train steps ... :  48%|████▊     | 47996/100000 [14:14:36<8:26:34,  1.71it/s]
Train steps ... :  48%|████▊     | 47997/100000 [14:14:37<8:27:25,  1.71it/s]
Train steps ... :  48%|████▊     | 47998/100000 [14:14:38<8:27:26,  1.71it/s]
Train steps ... :  48%|████▊     | 47999/100000 [14:14:38<8:27:31,  1.71it/s]
Train steps ... :  48%|████▊     | 48000/100000 [14:14:39<8:27:05,  1.71it/s]Step... (48000 / 100000 | Loss: 0.8686950206756592, Learning Rate: 5.226130653266332e-05)
+
                                                                             
Step... (48000 / 100000 | Loss: 0.9626612663269043, Learning Rate: 5.226130653266332e-05)
+
Train steps ... :  48%|████▊     | 48000/100000 [14:14:39<8:27:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48001/100000 [14:14:39<8:26:51,  1.71it/s]
Train steps ... :  48%|████▊     | 48002/100000 [14:14:40<8:26:19,  1.71it/s]
Train steps ... :  48%|████▊     | 48003/100000 [14:14:40<8:27:04,  1.71it/s]
Train steps ... :  48%|████▊     | 48004/100000 [14:14:41<8:26:40,  1.71it/s]
Train steps ... :  48%|████▊     | 48005/100000 [14:14:42<8:26:20,  1.71it/s]
Train steps ... :  48%|████▊     | 48006/100000 [14:14:42<8:26:17,  1.71it/s]
Train steps ... :  48%|████▊     | 48007/100000 [14:14:43<8:26:27,  1.71it/s]
Train steps ... :  48%|████▊     | 48008/100000 [14:14:43<8:26:19,  1.71it/s]
Train steps ... :  48%|████▊     | 48009/100000 [14:14:44<8:26:54,  1.71it/s]
Train steps ... :  48%|████▊     | 48010/100000 [14:14:45<8:27:13,  1.71it/s]
Train steps ... :  48%|████▊     | 48011/100000 [14:14:45<8:27:36,  1.71it/s]
Train steps ... :  48%|████▊     | 48012/100000 [14:14:46<8:27:12,  1.71it/s]
Train steps ... :  48%|████▊     | 48013/100000 [14:14:46<8:26:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48014/100000 [14:14:47<8:26:36,  1.71it/s]
Train steps ... :  48%|████▊     | 48015/100000 [14:14:47<8:26:09,  1.71it/s]
Train steps ... :  48%|████▊     | 48016/100000 [14:14:48<8:26:23,  1.71it/s]
Train steps ... :  48%|████▊     | 48017/100000 [14:14:49<8:25:58,  1.71it/s]
Train steps ... :  48%|████▊     | 48018/100000 [14:14:49<8:25:54,  1.71it/s]
Train steps ... :  48%|████▊     | 48019/100000 [14:14:50<8:26:23,  1.71it/s]
Train steps ... :  48%|████▊     | 48020/100000 [14:14:50<8:26:32,  1.71it/s]
Train steps ... :  48%|████▊     | 48021/100000 [14:14:51<8:27:02,  1.71it/s]
Train steps ... :  48%|████▊     | 48022/100000 [14:14:52<8:26:49,  1.71it/s]
Train steps ... :  48%|████▊     | 48023/100000 [14:14:52<8:26:35,  1.71it/s]
Train steps ... :  48%|████▊     | 48024/100000 [14:14:53<8:26:21,  1.71it/s]
Train steps ... :  48%|████▊     | 48025/100000 [14:14:53<8:26:17,  1.71it/s]Step... (48025 / 100000 | Loss: 0.6707463264465332, Learning Rate: 5.223618090452262e-05)
+
                                                                             
Step... (48025 / 100000 | Loss: 0.7308930158615112, Learning Rate: 5.223618090452262e-05)
+
Train steps ... :  48%|████▊     | 48025/100000 [14:14:54<8:26:17,  1.71it/s]
Train steps ... :  48%|████▊     | 48026/100000 [14:14:54<8:27:19,  1.71it/s]
Train steps ... :  48%|████▊     | 48027/100000 [14:14:54<8:27:28,  1.71it/s]
Train steps ... :  48%|████▊     | 48028/100000 [14:14:55<8:26:54,  1.71it/s]
Train steps ... :  48%|████▊     | 48029/100000 [14:14:56<8:26:56,  1.71it/s]
Train steps ... :  48%|████▊     | 48030/100000 [14:14:56<8:26:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48031/100000 [14:14:57<8:26:03,  1.71it/s]
Train steps ... :  48%|████▊     | 48032/100000 [14:14:57<8:26:10,  1.71it/s]
Train steps ... :  48%|████▊     | 48033/100000 [14:14:58<8:26:01,  1.71it/s]
Train steps ... :  48%|████▊     | 48034/100000 [14:14:59<8:26:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48035/100000 [14:14:59<8:26:29,  1.71it/s]
Train steps ... :  48%|████▊     | 48036/100000 [14:15:00<8:26:37,  1.71it/s]
Train steps ... :  48%|████▊     | 48037/100000 [14:15:00<8:26:49,  1.71it/s]
Train steps ... :  48%|████▊     | 48038/100000 [14:15:01<8:26:16,  1.71it/s]
Train steps ... :  48%|████▊     | 48039/100000 [14:15:01<8:25:59,  1.71it/s]
Train steps ... :  48%|████▊     | 48040/100000 [14:15:02<8:26:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48041/100000 [14:15:03<8:26:12,  1.71it/s]
Train steps ... :  48%|████▊     | 48042/100000 [14:15:03<8:26:41,  1.71it/s]
Train steps ... :  48%|████▊     | 48043/100000 [14:15:04<8:26:02,  1.71it/s]
Train steps ... :  48%|████▊     | 48044/100000 [14:15:04<8:27:14,  1.71it/s]
Train steps ... :  48%|████▊     | 48045/100000 [14:15:05<8:27:59,  1.70it/s]
Train steps ... :  48%|████▊     | 48046/100000 [14:15:06<8:26:54,  1.71it/s]
Train steps ... :  48%|████▊     | 48047/100000 [14:15:06<8:27:12,  1.71it/s]
Train steps ... :  48%|████▊     | 48048/100000 [14:15:07<8:26:41,  1.71it/s]
Train steps ... :  48%|████▊     | 48049/100000 [14:15:07<8:26:32,  1.71it/s]
Train steps ... :  48%|████▊     | 48050/100000 [14:15:08<8:26:25,  1.71it/s]Step... (48050 / 100000 | Loss: 0.9202510714530945, Learning Rate: 5.221105527638191e-05)
+
                                                                             
Step... (48050 / 100000 | Loss: 1.299219012260437, Learning Rate: 5.221105527638191e-05)
+
Train steps ... :  48%|████▊     | 48050/100000 [14:15:08<8:26:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48051/100000 [14:15:09<8:26:32,  1.71it/s]
Train steps ... :  48%|████▊     | 48052/100000 [14:15:09<8:26:04,  1.71it/s]
Train steps ... :  48%|████▊     | 48053/100000 [14:15:10<8:26:00,  1.71it/s]
Train steps ... :  48%|████▊     | 48054/100000 [14:15:10<8:27:06,  1.71it/s]
Train steps ... :  48%|████▊     | 48055/100000 [14:15:11<8:27:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48056/100000 [14:15:11<8:27:00,  1.71it/s]
Train steps ... :  48%|████▊     | 48057/100000 [14:15:12<8:26:40,  1.71it/s]
Train steps ... :  48%|████▊     | 48058/100000 [14:15:13<8:26:07,  1.71it/s]
Train steps ... :  48%|████▊     | 48059/100000 [14:15:13<8:26:20,  1.71it/s]
Train steps ... :  48%|████▊     | 48060/100000 [14:15:14<8:26:06,  1.71it/s]
Train steps ... :  48%|████▊     | 48061/100000 [14:15:14<8:26:55,  1.71it/s]
Train steps ... :  48%|████▊     | 48062/100000 [14:15:15<8:26:30,  1.71it/s]
Train steps ... :  48%|████▊     | 48063/100000 [14:15:16<8:26:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48064/100000 [14:15:16<8:26:52,  1.71it/s]
Train steps ... :  48%|████▊     | 48065/100000 [14:15:17<8:26:56,  1.71it/s]
Train steps ... :  48%|████▊     | 48066/100000 [14:15:17<8:26:58,  1.71it/s]
Train steps ... :  48%|████▊     | 48067/100000 [14:15:18<8:26:58,  1.71it/s]
Train steps ... :  48%|████▊     | 48068/100000 [14:15:18<8:27:17,  1.71it/s]
Train steps ... :  48%|████▊     | 48069/100000 [14:15:19<8:27:19,  1.71it/s]
Train steps ... :  48%|████▊     | 48070/100000 [14:15:20<8:27:06,  1.71it/s]
Train steps ... :  48%|████▊     | 48071/100000 [14:15:20<8:27:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48072/100000 [14:15:21<8:26:47,  1.71it/s]
Train steps ... :  48%|████▊     | 48073/100000 [14:15:21<8:26:34,  1.71it/s]
Train steps ... :  48%|████▊     | 48074/100000 [14:15:22<8:26:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48075/100000 [14:15:23<8:26:14,  1.71it/s]Step... (48075 / 100000 | Loss: 0.848216712474823, Learning Rate: 5.21859296482412e-05)
+
                                                                             
Step... (48075 / 100000 | Loss: 0.7508078217506409, Learning Rate: 5.21859296482412e-05)
+
Train steps ... :  48%|████▊     | 48075/100000 [14:15:23<8:26:14,  1.71it/s]
Train steps ... :  48%|████▊     | 48076/100000 [14:15:23<8:26:09,  1.71it/s]
Train steps ... :  48%|████▊     | 48077/100000 [14:15:24<8:25:34,  1.71it/s]
Train steps ... :  48%|████▊     | 48078/100000 [14:15:24<8:25:27,  1.71it/s]
Train steps ... :  48%|████▊     | 48079/100000 [14:15:25<8:25:12,  1.71it/s]
Train steps ... :  48%|████▊     | 48080/100000 [14:15:25<8:26:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48081/100000 [14:15:26<8:26:57,  1.71it/s]
Train steps ... :  48%|████▊     | 48082/100000 [14:15:27<8:26:18,  1.71it/s]
Train steps ... :  48%|████▊     | 48083/100000 [14:15:27<8:27:56,  1.70it/s]
Train steps ... :  48%|████▊     | 48084/100000 [14:15:28<8:26:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48085/100000 [14:15:28<8:26:20,  1.71it/s]
Train steps ... :  48%|████▊     | 48086/100000 [14:15:29<8:26:07,  1.71it/s]
Train steps ... :  48%|████▊     | 48087/100000 [14:15:30<8:25:42,  1.71it/s]
Train steps ... :  48%|████▊     | 48088/100000 [14:15:30<8:25:23,  1.71it/s]
Train steps ... :  48%|████▊     | 48089/100000 [14:15:31<8:25:29,  1.71it/s]
Train steps ... :  48%|████▊     | 48090/100000 [14:15:31<8:26:12,  1.71it/s]
Train steps ... :  48%|████▊     | 48091/100000 [14:15:32<8:26:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48092/100000 [14:15:32<8:26:09,  1.71it/s]
Train steps ... :  48%|████▊     | 48093/100000 [14:15:33<8:25:41,  1.71it/s]
Train steps ... :  48%|████▊     | 48094/100000 [14:15:34<8:25:29,  1.71it/s]
Train steps ... :  48%|████▊     | 48095/100000 [14:15:34<8:25:52,  1.71it/s]
Train steps ... :  48%|████▊     | 48096/100000 [14:15:35<8:26:23,  1.71it/s]
Train steps ... :  48%|████▊     | 48097/100000 [14:15:35<8:27:27,  1.70it/s]
Train steps ... :  48%|████▊     | 48098/100000 [14:15:36<8:27:50,  1.70it/s]
Train steps ... :  48%|████▊     | 48099/100000 [14:15:37<8:27:49,  1.70it/s]
Train steps ... :  48%|████▊     | 48100/100000 [14:15:37<8:27:05,  1.71it/s]Step... (48100 / 100000 | Loss: 0.7815636992454529, Learning Rate: 5.2160804020100507e-05)
+
                                                                             
Step... (48100 / 100000 | Loss: 0.8415826559066772, Learning Rate: 5.2160804020100507e-05)
+
Train steps ... :  48%|████▊     | 48100/100000 [14:15:38<8:27:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48101/100000 [14:15:38<8:27:33,  1.70it/s]
Train steps ... :  48%|████▊     | 48102/100000 [14:15:38<8:26:56,  1.71it/s]
Train steps ... :  48%|████▊     | 48103/100000 [14:15:39<8:26:59,  1.71it/s]
Train steps ... :  48%|████▊     | 48104/100000 [14:15:40<8:26:13,  1.71it/s]
Train steps ... :  48%|████▊     | 48105/100000 [14:15:40<8:26:11,  1.71it/s]
Train steps ... :  48%|████▊     | 48106/100000 [14:15:41<8:25:53,  1.71it/s]
Train steps ... :  48%|████▊     | 48107/100000 [14:15:41<8:25:17,  1.71it/s]
Train steps ... :  48%|████▊     | 48108/100000 [14:15:42<8:25:54,  1.71it/s]
Train steps ... :  48%|████▊     | 48109/100000 [14:15:42<8:26:29,  1.71it/s]
Train steps ... :  48%|████▊     | 48110/100000 [14:15:43<8:27:11,  1.71it/s]
Train steps ... :  48%|████▊     | 48111/100000 [14:15:44<8:27:03,  1.71it/s]
Train steps ... :  48%|████▊     | 48112/100000 [14:15:44<8:27:00,  1.71it/s]
Train steps ... :  48%|████▊     | 48113/100000 [14:15:45<8:26:47,  1.71it/s]
Train steps ... :  48%|████▊     | 48114/100000 [14:15:45<8:26:31,  1.71it/s]
Train steps ... :  48%|████▊     | 48115/100000 [14:15:46<8:25:40,  1.71it/s]
Train steps ... :  48%|████▊     | 48116/100000 [14:15:47<8:25:38,  1.71it/s]
Train steps ... :  48%|████▊     | 48117/100000 [14:15:47<8:25:19,  1.71it/s]
Train steps ... :  48%|████▊     | 48118/100000 [14:15:48<8:25:13,  1.71it/s]
Train steps ... :  48%|████▊     | 48119/100000 [14:15:48<8:25:13,  1.71it/s]
Train steps ... :  48%|████▊     | 48120/100000 [14:15:49<8:26:19,  1.71it/s]
Train steps ... :  48%|████▊     | 48121/100000 [14:15:49<8:25:57,  1.71it/s]
Train steps ... :  48%|████▊     | 48122/100000 [14:15:50<8:25:41,  1.71it/s]
Train steps ... :  48%|████▊     | 48123/100000 [14:15:51<8:26:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48124/100000 [14:15:51<8:25:49,  1.71it/s]
Train steps ... :  48%|████▊     | 48125/100000 [14:15:52<8:25:52,  1.71it/s]Step... (48125 / 100000 | Loss: 0.6933411359786987, Learning Rate: 5.2135678391959796e-05)
+
                                                                             
Step... (48125 / 100000 | Loss: 0.6759322881698608, Learning Rate: 5.2135678391959796e-05)
+
Train steps ... :  48%|████▊     | 48125/100000 [14:15:52<8:25:52,  1.71it/s]
Train steps ... :  48%|████▊     | 48126/100000 [14:15:52<8:26:36,  1.71it/s]
Train steps ... :  48%|████▊     | 48127/100000 [14:15:53<8:26:02,  1.71it/s]
Train steps ... :  48%|████▊     | 48128/100000 [14:15:54<8:26:15,  1.71it/s]
Train steps ... :  48%|████▊     | 48129/100000 [14:15:54<8:25:38,  1.71it/s]
Train steps ... :  48%|████▊     | 48130/100000 [14:15:55<8:26:06,  1.71it/s]
Train steps ... :  48%|████▊     | 48131/100000 [14:15:55<8:26:07,  1.71it/s]
Train steps ... :  48%|████▊     | 48132/100000 [14:15:56<8:26:06,  1.71it/s]
Train steps ... :  48%|████▊     | 48133/100000 [14:15:57<8:26:36,  1.71it/s]
Train steps ... :  48%|████▊     | 48134/100000 [14:15:57<8:26:27,  1.71it/s]
Train steps ... :  48%|████▊     | 48135/100000 [14:15:58<8:26:09,  1.71it/s]
Train steps ... :  48%|████▊     | 48136/100000 [14:15:58<8:25:15,  1.71it/s]
Train steps ... :  48%|████▊     | 48137/100000 [14:15:59<8:25:32,  1.71it/s]
Train steps ... :  48%|████▊     | 48138/100000 [14:15:59<8:25:27,  1.71it/s]
Train steps ... :  48%|████▊     | 48139/100000 [14:16:00<8:25:44,  1.71it/s]
Train steps ... :  48%|████▊     | 48140/100000 [14:16:01<8:24:54,  1.71it/s]
Train steps ... :  48%|████▊     | 48141/100000 [14:16:01<8:24:51,  1.71it/s]
Train steps ... :  48%|████▊     | 48142/100000 [14:16:02<8:24:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48143/100000 [14:16:02<8:24:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48144/100000 [14:16:03<8:24:46,  1.71it/s]
Train steps ... :  48%|████▊     | 48145/100000 [14:16:04<8:24:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48146/100000 [14:16:04<8:25:01,  1.71it/s]
Train steps ... :  48%|████▊     | 48147/100000 [14:16:05<8:24:42,  1.71it/s]
Train steps ... :  48%|████▊     | 48148/100000 [14:16:05<8:24:59,  1.71it/s]
Train steps ... :  48%|████▊     | 48149/100000 [14:16:06<8:24:44,  1.71it/s]
Train steps ... :  48%|████▊     | 48150/100000 [14:16:06<8:24:27,  1.71it/s]Step... (48150 / 100000 | Loss: 0.8398271799087524, Learning Rate: 5.21105527638191e-05)
+
                                                                             
Step... (48150 / 100000 | Loss: 0.9893603324890137, Learning Rate: 5.21105527638191e-05)
+
Train steps ... :  48%|████▊     | 48150/100000 [14:16:07<8:24:27,  1.71it/s]
Train steps ... :  48%|████▊     | 48151/100000 [14:16:07<8:24:59,  1.71it/s]
Train steps ... :  48%|████▊     | 48152/100000 [14:16:08<8:24:48,  1.71it/s]
Train steps ... :  48%|████▊     | 48153/100000 [14:16:08<8:25:04,  1.71it/s]
Train steps ... :  48%|████▊     | 48154/100000 [14:16:09<8:25:39,  1.71it/s]
Train steps ... :  48%|████▊     | 48155/100000 [14:16:09<8:24:55,  1.71it/s]
Train steps ... :  48%|████▊     | 48156/100000 [14:16:10<8:24:50,  1.71it/s]
Train steps ... :  48%|████▊     | 48157/100000 [14:16:11<8:25:23,  1.71it/s]
Train steps ... :  48%|████▊     | 48158/100000 [14:16:11<8:25:18,  1.71it/s]
Train steps ... :  48%|████▊     | 48159/100000 [14:16:12<8:25:24,  1.71it/s]
Train steps ... :  48%|████▊     | 48160/100000 [14:16:12<8:25:04,  1.71it/s]
Train steps ... :  48%|████▊     | 48161/100000 [14:16:13<8:25:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48162/100000 [14:16:13<8:24:53,  1.71it/s]
Train steps ... :  48%|████▊     | 48163/100000 [14:16:14<8:25:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48164/100000 [14:16:15<8:25:04,  1.71it/s]
Train steps ... :  48%|████▊     | 48165/100000 [14:16:15<8:24:39,  1.71it/s]
Train steps ... :  48%|████▊     | 48166/100000 [14:16:16<8:25:12,  1.71it/s]
Train steps ... :  48%|████▊     | 48167/100000 [14:16:16<8:25:14,  1.71it/s]
Train steps ... :  48%|████▊     | 48168/100000 [14:16:17<8:24:55,  1.71it/s]
Train steps ... :  48%|████▊     | 48169/100000 [14:16:18<8:25:04,  1.71it/s]
Train steps ... :  48%|████▊     | 48170/100000 [14:16:18<8:24:38,  1.71it/s]
Train steps ... :  48%|████▊     | 48171/100000 [14:16:19<8:24:28,  1.71it/s]
Train steps ... :  48%|████▊     | 48172/100000 [14:16:19<8:24:54,  1.71it/s]
Train steps ... :  48%|████▊     | 48173/100000 [14:16:20<8:24:58,  1.71it/s]
Train steps ... :  48%|████▊     | 48174/100000 [14:16:20<8:25:06,  1.71it/s]
Train steps ... :  48%|████▊     | 48175/100000 [14:16:21<8:24:41,  1.71it/s]Step... (48175 / 100000 | Loss: 1.08658766746521, Learning Rate: 5.2085427135678396e-05)
+
                                                                             
Step... (48175 / 100000 | Loss: 0.8116369247436523, Learning Rate: 5.2085427135678396e-05)
+
Train steps ... :  48%|████▊     | 48175/100000 [14:16:21<8:24:41,  1.71it/s]
Train steps ... :  48%|████▊     | 48176/100000 [14:16:22<8:24:57,  1.71it/s]
Train steps ... :  48%|████▊     | 48177/100000 [14:16:22<8:24:30,  1.71it/s]
Train steps ... :  48%|████▊     | 48178/100000 [14:16:23<8:25:13,  1.71it/s]
Train steps ... :  48%|████▊     | 48179/100000 [14:16:23<8:24:41,  1.71it/s]
Train steps ... :  48%|████▊     | 48180/100000 [14:16:24<8:24:34,  1.71it/s]
Train steps ... :  48%|████▊     | 48181/100000 [14:16:25<8:24:47,  1.71it/s]
Train steps ... :  48%|████▊     | 48182/100000 [14:16:25<8:25:37,  1.71it/s]
Train steps ... :  48%|████▊     | 48183/100000 [14:16:26<8:25:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48184/100000 [14:16:26<8:25:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48185/100000 [14:16:27<8:25:08,  1.71it/s]
Train steps ... :  48%|████▊     | 48186/100000 [14:16:27<8:24:53,  1.71it/s]
Train steps ... :  48%|████▊     | 48187/100000 [14:16:28<8:24:30,  1.71it/s]
Train steps ... :  48%|████▊     | 48188/100000 [14:16:29<8:25:39,  1.71it/s]
Train steps ... :  48%|████▊     | 48189/100000 [14:16:29<8:25:40,  1.71it/s]
Train steps ... :  48%|████▊     | 48190/100000 [14:16:30<8:25:04,  1.71it/s]
Train steps ... :  48%|████▊     | 48191/100000 [14:16:30<8:25:15,  1.71it/s]
Train steps ... :  48%|████▊     | 48192/100000 [14:16:31<8:24:50,  1.71it/s]
Train steps ... :  48%|████▊     | 48193/100000 [14:16:32<8:24:53,  1.71it/s]
Train steps ... :  48%|████▊     | 48194/100000 [14:16:32<8:24:36,  1.71it/s]
Train steps ... :  48%|████▊     | 48195/100000 [14:16:33<8:24:16,  1.71it/s]
Train steps ... :  48%|████▊     | 48196/100000 [14:16:33<8:24:53,  1.71it/s]
Train steps ... :  48%|████▊     | 48197/100000 [14:16:34<8:25:28,  1.71it/s]
Train steps ... :  48%|████▊     | 48198/100000 [14:16:34<8:24:48,  1.71it/s]
Train steps ... :  48%|████▊     | 48199/100000 [14:16:35<8:24:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48200/100000 [14:16:36<8:24:13,  1.71it/s]Step... (48200 / 100000 | Loss: 0.6073811650276184, Learning Rate: 5.206030150753769e-05)
+
                                                                             
Step... (48200 / 100000 | Loss: 1.0428924560546875, Learning Rate: 5.206030150753769e-05)
+
Train steps ... :  48%|████▊     | 48200/100000 [14:16:36<8:24:13,  1.71it/s]
Train steps ... :  48%|████▊     | 48201/100000 [14:16:36<8:24:18,  1.71it/s]
Train steps ... :  48%|████▊     | 48202/100000 [14:16:37<8:24:07,  1.71it/s]
Train steps ... :  48%|████▊     | 48203/100000 [14:16:37<8:24:34,  1.71it/s]
Train steps ... :  48%|████▊     | 48204/100000 [14:16:38<8:25:00,  1.71it/s]
Train steps ... :  48%|████▊     | 48205/100000 [14:16:39<8:24:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48206/100000 [14:16:39<8:25:15,  1.71it/s]
Train steps ... :  48%|████▊     | 48207/100000 [14:16:40<8:24:54,  1.71it/s]
Train steps ... :  48%|████▊     | 48208/100000 [14:16:40<8:24:56,  1.71it/s]
Train steps ... :  48%|████▊     | 48209/100000 [14:16:41<8:25:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48210/100000 [14:16:42<8:24:50,  1.71it/s]
Train steps ... :  48%|████▊     | 48211/100000 [14:16:42<8:25:10,  1.71it/s]
Train steps ... :  48%|████▊     | 48212/100000 [14:16:43<8:24:45,  1.71it/s]
Train steps ... :  48%|████▊     | 48213/100000 [14:16:43<8:25:04,  1.71it/s]
Train steps ... :  48%|████▊     | 48214/100000 [14:16:44<8:24:38,  1.71it/s]
Train steps ... :  48%|████▊     | 48215/100000 [14:16:44<8:25:14,  1.71it/s]
Train steps ... :  48%|████▊     | 48216/100000 [14:16:45<8:24:58,  1.71it/s]
Train steps ... :  48%|████▊     | 48217/100000 [14:16:46<8:25:35,  1.71it/s]
Train steps ... :  48%|████▊     | 48218/100000 [14:16:46<8:24:40,  1.71it/s]
Train steps ... :  48%|████▊     | 48219/100000 [14:16:47<8:25:01,  1.71it/s]
Train steps ... :  48%|████▊     | 48220/100000 [14:16:47<8:24:21,  1.71it/s]
Train steps ... :  48%|████▊     | 48221/100000 [14:16:48<8:24:11,  1.71it/s]
Train steps ... :  48%|████▊     | 48222/100000 [14:16:49<8:24:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48223/100000 [14:16:49<8:24:14,  1.71it/s]
Train steps ... :  48%|████▊     | 48224/100000 [14:16:50<8:24:07,  1.71it/s]
Train steps ... :  48%|████▊     | 48225/100000 [14:16:50<8:24:14,  1.71it/s]Step... (48225 / 100000 | Loss: 0.6544308662414551, Learning Rate: 5.203517587939699e-05)
+
                                                                             
Step... (48225 / 100000 | Loss: 1.0159014463424683, Learning Rate: 5.203517587939699e-05)
+
Train steps ... :  48%|████▊     | 48225/100000 [14:16:51<8:24:14,  1.71it/s]
Train steps ... :  48%|████▊     | 48226/100000 [14:16:51<8:24:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48227/100000 [14:16:51<8:23:59,  1.71it/s]
Train steps ... :  48%|████▊     | 48228/100000 [14:16:52<8:24:08,  1.71it/s]
Train steps ... :  48%|████▊     | 48229/100000 [14:16:53<8:24:31,  1.71it/s]
Train steps ... :  48%|████▊     | 48230/100000 [14:16:53<8:24:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48231/100000 [14:16:54<8:24:36,  1.71it/s]
Train steps ... :  48%|████▊     | 48232/100000 [14:16:54<8:25:26,  1.71it/s]
Train steps ... :  48%|████▊     | 48233/100000 [14:16:55<8:24:58,  1.71it/s]
Train steps ... :  48%|████▊     | 48234/100000 [14:16:56<8:24:49,  1.71it/s]
Train steps ... :  48%|████▊     | 48235/100000 [14:16:56<8:25:53,  1.71it/s]
Train steps ... :  48%|████▊     | 48236/100000 [14:16:57<8:24:55,  1.71it/s]
Train steps ... :  48%|████▊     | 48237/100000 [14:16:57<8:24:40,  1.71it/s]
Train steps ... :  48%|████▊     | 48238/100000 [14:16:58<8:24:12,  1.71it/s]
Train steps ... :  48%|████▊     | 48239/100000 [14:16:58<8:24:32,  1.71it/s]
Train steps ... :  48%|████▊     | 48240/100000 [14:16:59<8:24:48,  1.71it/s]
Train steps ... :  48%|████▊     | 48241/100000 [14:17:00<8:25:01,  1.71it/s]
Train steps ... :  48%|████▊     | 48242/100000 [14:17:00<8:24:29,  1.71it/s]
Train steps ... :  48%|████▊     | 48243/100000 [14:17:01<8:24:13,  1.71it/s]
Train steps ... :  48%|████▊     | 48244/100000 [14:17:01<8:24:50,  1.71it/s]
Train steps ... :  48%|████▊     | 48245/100000 [14:17:02<8:25:07,  1.71it/s]
Train steps ... :  48%|████▊     | 48246/100000 [14:17:03<8:25:13,  1.71it/s]
Train steps ... :  48%|████▊     | 48247/100000 [14:17:03<8:25:00,  1.71it/s]
Train steps ... :  48%|████▊     | 48248/100000 [14:17:04<8:25:39,  1.71it/s]
Train steps ... :  48%|████▊     | 48249/100000 [14:17:04<8:25:28,  1.71it/s]
Train steps ... :  48%|████▊     | 48250/100000 [14:17:05<8:25:28,  1.71it/s]Step... (48250 / 100000 | Loss: 0.9153097867965698, Learning Rate: 5.201005025125628e-05)
+
                                                                             
Step... (48250 / 100000 | Loss: 1.1066137552261353, Learning Rate: 5.201005025125628e-05)
+
Train steps ... :  48%|████▊     | 48250/100000 [14:17:05<8:25:28,  1.71it/s]
Train steps ... :  48%|████▊     | 48251/100000 [14:17:06<8:25:54,  1.70it/s]
Train steps ... :  48%|████▊     | 48252/100000 [14:17:06<8:25:55,  1.70it/s]
Train steps ... :  48%|████▊     | 48253/100000 [14:17:07<8:25:09,  1.71it/s]
Train steps ... :  48%|████▊     | 48254/100000 [14:17:07<8:24:49,  1.71it/s]
Train steps ... :  48%|████▊     | 48255/100000 [14:17:08<8:24:14,  1.71it/s]
Train steps ... :  48%|████▊     | 48256/100000 [14:17:08<8:24:32,  1.71it/s]
Train steps ... :  48%|████▊     | 48257/100000 [14:17:09<8:24:19,  1.71it/s]
Train steps ... :  48%|████▊     | 48258/100000 [14:17:10<8:24:01,  1.71it/s]
Train steps ... :  48%|████▊     | 48259/100000 [14:17:10<8:24:28,  1.71it/s]
Train steps ... :  48%|████▊     | 48260/100000 [14:17:11<8:24:39,  1.71it/s]
Train steps ... :  48%|████▊     | 48261/100000 [14:17:11<8:24:17,  1.71it/s]
Train steps ... :  48%|████▊     | 48262/100000 [14:17:12<8:24:42,  1.71it/s]
Train steps ... :  48%|████▊     | 48263/100000 [14:17:13<8:25:09,  1.71it/s]
Train steps ... :  48%|████▊     | 48264/100000 [14:17:13<8:24:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48265/100000 [14:17:14<8:24:12,  1.71it/s]
Train steps ... :  48%|████▊     | 48266/100000 [14:17:14<8:24:09,  1.71it/s]
Train steps ... :  48%|████▊     | 48267/100000 [14:17:15<8:24:20,  1.71it/s]
Train steps ... :  48%|████▊     | 48268/100000 [14:17:15<8:23:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48269/100000 [14:17:16<8:23:41,  1.71it/s]
Train steps ... :  48%|████▊     | 48270/100000 [14:17:17<8:23:51,  1.71it/s]
Train steps ... :  48%|████▊     | 48271/100000 [14:17:17<8:23:56,  1.71it/s]
Train steps ... :  48%|████▊     | 48272/100000 [14:17:18<8:24:19,  1.71it/s]
Train steps ... :  48%|████▊     | 48273/100000 [14:17:18<8:24:26,  1.71it/s]
Train steps ... :  48%|████▊     | 48274/100000 [14:17:19<8:23:52,  1.71it/s]
Train steps ... :  48%|████▊     | 48275/100000 [14:17:20<8:24:17,  1.71it/s]Step... (48275 / 100000 | Loss: 0.8367422819137573, Learning Rate: 5.198492462311558e-05)
+
                                                                             
Step... (48275 / 100000 | Loss: 1.0824649333953857, Learning Rate: 5.198492462311558e-05)
+
Train steps ... :  48%|████▊     | 48275/100000 [14:17:20<8:24:17,  1.71it/s]
Train steps ... :  48%|████▊     | 48276/100000 [14:17:20<8:24:04,  1.71it/s]
Train steps ... :  48%|████▊     | 48277/100000 [14:17:21<8:23:27,  1.71it/s]
Train steps ... :  48%|████▊     | 48278/100000 [14:17:21<8:24:19,  1.71it/s]
Train steps ... :  48%|████▊     | 48279/100000 [14:17:22<8:23:49,  1.71it/s]
Train steps ... :  48%|████▊     | 48280/100000 [14:17:22<8:23:57,  1.71it/s]
Train steps ... :  48%|████▊     | 48281/100000 [14:17:23<8:24:01,  1.71it/s]
Train steps ... :  48%|████▊     | 48282/100000 [14:17:24<8:24:14,  1.71it/s]
Train steps ... :  48%|████▊     | 48283/100000 [14:17:24<8:24:07,  1.71it/s]
Train steps ... :  48%|████▊     | 48284/100000 [14:17:25<8:24:23,  1.71it/s]
Train steps ... :  48%|████▊     | 48285/100000 [14:17:25<8:24:35,  1.71it/s]
Train steps ... :  48%|████▊     | 48286/100000 [14:17:26<8:23:57,  1.71it/s]
Train steps ... :  48%|████▊     | 48287/100000 [14:17:27<8:24:27,  1.71it/s]
Train steps ... :  48%|████▊     | 48288/100000 [14:17:27<8:23:57,  1.71it/s]
Train steps ... :  48%|████▊     | 48289/100000 [14:17:28<8:24:19,  1.71it/s]
Train steps ... :  48%|████▊     | 48290/100000 [14:17:28<8:24:07,  1.71it/s]
Train steps ... :  48%|████▊     | 48291/100000 [14:17:29<8:24:32,  1.71it/s]
Train steps ... :  48%|████▊     | 48292/100000 [14:17:29<8:23:51,  1.71it/s]
Train steps ... :  48%|████▊     | 48293/100000 [14:17:30<8:24:37,  1.71it/s]
Train steps ... :  48%|████▊     | 48294/100000 [14:17:31<8:24:00,  1.71it/s]
Train steps ... :  48%|████▊     | 48295/100000 [14:17:31<8:23:35,  1.71it/s]
Train steps ... :  48%|████▊     | 48296/100000 [14:17:32<8:23:26,  1.71it/s]
Train steps ... :  48%|████▊     | 48297/100000 [14:17:32<8:24:00,  1.71it/s]
Train steps ... :  48%|████▊     | 48298/100000 [14:17:33<8:23:44,  1.71it/s]
Train steps ... :  48%|████▊     | 48299/100000 [14:17:34<8:23:41,  1.71it/s]
Train steps ... :  48%|████▊     | 48300/100000 [14:17:34<8:24:20,  1.71it/s]Step... (48300 / 100000 | Loss: 0.8464484214782715, Learning Rate: 5.195979899497487e-05)
+
                                                                             
Step... (48300 / 100000 | Loss: 1.1823843717575073, Learning Rate: 5.195979899497487e-05)
+
Train steps ... :  48%|████▊     | 48300/100000 [14:17:34<8:24:20,  1.71it/s]
Train steps ... :  48%|████▊     | 48301/100000 [14:17:35<8:23:26,  1.71it/s]
Train steps ... :  48%|████▊     | 48302/100000 [14:17:35<8:22:57,  1.71it/s]
Train steps ... :  48%|████▊     | 48303/100000 [14:17:36<8:22:59,  1.71it/s]
Train steps ... :  48%|████▊     | 48304/100000 [14:17:36<8:23:06,  1.71it/s]
Train steps ... :  48%|████▊     | 48305/100000 [14:17:37<8:23:08,  1.71it/s]
Train steps ... :  48%|████▊     | 48306/100000 [14:17:38<8:23:16,  1.71it/s]
Train steps ... :  48%|████▊     | 48307/100000 [14:17:38<8:23:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48308/100000 [14:17:39<8:23:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48309/100000 [14:17:39<8:23:28,  1.71it/s]
Train steps ... :  48%|████▊     | 48310/100000 [14:17:40<8:23:36,  1.71it/s]
Train steps ... :  48%|████▊     | 48311/100000 [14:17:41<8:23:54,  1.71it/s]
Train steps ... :  48%|████▊     | 48312/100000 [14:17:41<8:23:36,  1.71it/s]
Train steps ... :  48%|████▊     | 48313/100000 [14:17:42<8:24:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48314/100000 [14:17:42<8:23:30,  1.71it/s]
Train steps ... :  48%|████▊     | 48315/100000 [14:17:43<8:23:00,  1.71it/s]
Train steps ... :  48%|████▊     | 48316/100000 [14:17:44<8:22:36,  1.71it/s]
Train steps ... :  48%|████▊     | 48317/100000 [14:17:44<8:23:13,  1.71it/s]
Train steps ... :  48%|████▊     | 48318/100000 [14:17:45<8:23:00,  1.71it/s]
Train steps ... :  48%|████▊     | 48319/100000 [14:17:45<8:23:28,  1.71it/s]
Train steps ... :  48%|████▊     | 48320/100000 [14:17:46<8:23:06,  1.71it/s]
Train steps ... :  48%|████▊     | 48321/100000 [14:17:46<8:22:59,  1.71it/s]
Train steps ... :  48%|████▊     | 48322/100000 [14:17:47<8:23:51,  1.71it/s]
Train steps ... :  48%|████▊     | 48323/100000 [14:17:48<8:23:52,  1.71it/s]
Train steps ... :  48%|████▊     | 48324/100000 [14:17:48<8:23:49,  1.71it/s]
Train steps ... :  48%|████▊     | 48325/100000 [14:17:49<8:24:29,  1.71it/s]Step... (48325 / 100000 | Loss: 0.9296033382415771, Learning Rate: 5.1934673366834176e-05)
+
                                                                             
Step... (48325 / 100000 | Loss: 0.7689740657806396, Learning Rate: 5.1934673366834176e-05)
+
Train steps ... :  48%|████▊     | 48325/100000 [14:17:49<8:24:29,  1.71it/s]
Train steps ... :  48%|████▊     | 48326/100000 [14:17:49<8:24:51,  1.71it/s]
Train steps ... :  48%|████▊     | 48327/100000 [14:17:50<8:23:50,  1.71it/s]
Train steps ... :  48%|████▊     | 48328/100000 [14:17:51<8:23:27,  1.71it/s]
Train steps ... :  48%|████▊     | 48329/100000 [14:17:51<8:23:08,  1.71it/s]
Train steps ... :  48%|████▊     | 48330/100000 [14:17:52<8:23:11,  1.71it/s]
Train steps ... :  48%|████▊     | 48331/100000 [14:17:52<8:23:20,  1.71it/s]
Train steps ... :  48%|████▊     | 48332/100000 [14:17:53<8:23:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48333/100000 [14:17:53<8:23:51,  1.71it/s]
Train steps ... :  48%|████▊     | 48334/100000 [14:17:54<8:23:39,  1.71it/s]
Train steps ... :  48%|████▊     | 48335/100000 [14:17:55<8:23:10,  1.71it/s]
Train steps ... :  48%|████▊     | 48336/100000 [14:17:55<8:22:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48337/100000 [14:17:56<8:23:16,  1.71it/s]
Train steps ... :  48%|████▊     | 48338/100000 [14:17:56<8:22:50,  1.71it/s]
Train steps ... :  48%|████▊     | 48339/100000 [14:17:57<8:22:41,  1.71it/s]
Train steps ... :  48%|████▊     | 48340/100000 [14:17:58<8:22:50,  1.71it/s]
Train steps ... :  48%|████▊     | 48341/100000 [14:17:58<8:23:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48342/100000 [14:17:59<8:23:40,  1.71it/s]
Train steps ... :  48%|████▊     | 48343/100000 [14:17:59<8:23:32,  1.71it/s]
Train steps ... :  48%|████▊     | 48344/100000 [14:18:00<8:23:55,  1.71it/s]
Train steps ... :  48%|████▊     | 48345/100000 [14:18:00<8:23:32,  1.71it/s]
Train steps ... :  48%|████▊     | 48346/100000 [14:18:01<8:23:51,  1.71it/s]
Train steps ... :  48%|████▊     | 48347/100000 [14:18:02<8:23:44,  1.71it/s]
Train steps ... :  48%|████▊     | 48348/100000 [14:18:02<8:23:15,  1.71it/s]
Train steps ... :  48%|████▊     | 48349/100000 [14:18:03<8:23:07,  1.71it/s]
Train steps ... :  48%|████▊     | 48350/100000 [14:18:03<8:22:57,  1.71it/s]Step... (48350 / 100000 | Loss: 1.0113301277160645, Learning Rate: 5.1909547738693466e-05)
+
                                                                             
Step... (48350 / 100000 | Loss: 0.7443926334381104, Learning Rate: 5.1909547738693466e-05)
+
Train steps ... :  48%|████▊     | 48350/100000 [14:18:04<8:22:57,  1.71it/s]
Train steps ... :  48%|████▊     | 48351/100000 [14:18:04<8:23:18,  1.71it/s]
Train steps ... :  48%|████▊     | 48352/100000 [14:18:05<8:24:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48353/100000 [14:18:05<8:24:06,  1.71it/s]
Train steps ... :  48%|████▊     | 48354/100000 [14:18:06<8:23:34,  1.71it/s]
Train steps ... :  48%|████▊     | 48355/100000 [14:18:06<8:22:54,  1.71it/s]
Train steps ... :  48%|████▊     | 48356/100000 [14:18:07<8:23:13,  1.71it/s]
Train steps ... :  48%|████▊     | 48357/100000 [14:18:07<8:23:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48358/100000 [14:18:08<8:23:53,  1.71it/s]
Train steps ... :  48%|████▊     | 48359/100000 [14:18:09<8:23:29,  1.71it/s]
Train steps ... :  48%|████▊     | 48360/100000 [14:18:09<8:22:53,  1.71it/s]
Train steps ... :  48%|████▊     | 48361/100000 [14:18:10<8:23:02,  1.71it/s]
Train steps ... :  48%|████▊     | 48362/100000 [14:18:10<8:23:15,  1.71it/s]
Train steps ... :  48%|████▊     | 48363/100000 [14:18:11<8:23:00,  1.71it/s]
Train steps ... :  48%|████▊     | 48364/100000 [14:18:12<8:22:58,  1.71it/s]
Train steps ... :  48%|████▊     | 48365/100000 [14:18:12<8:23:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48366/100000 [14:18:13<8:23:03,  1.71it/s]
Train steps ... :  48%|████▊     | 48367/100000 [14:18:13<8:22:41,  1.71it/s]
Train steps ... :  48%|████▊     | 48368/100000 [14:18:14<8:23:28,  1.71it/s]
Train steps ... :  48%|████▊     | 48369/100000 [14:18:15<8:24:00,  1.71it/s]
Train steps ... :  48%|████▊     | 48370/100000 [14:18:15<8:23:57,  1.71it/s]
Train steps ... :  48%|████▊     | 48371/100000 [14:18:16<8:23:24,  1.71it/s]
Train steps ... :  48%|████▊     | 48372/100000 [14:18:16<8:23:35,  1.71it/s]
Train steps ... :  48%|████▊     | 48373/100000 [14:18:17<8:23:34,  1.71it/s]
Train steps ... :  48%|████▊     | 48374/100000 [14:18:17<8:23:16,  1.71it/s]
Train steps ... :  48%|████▊     | 48375/100000 [14:18:18<8:23:34,  1.71it/s]Step... (48375 / 100000 | Loss: 0.6808198690414429, Learning Rate: 5.188442211055277e-05)
+
                                                                             
Step... (48375 / 100000 | Loss: 0.8454222679138184, Learning Rate: 5.188442211055277e-05)
+
Train steps ... :  48%|████▊     | 48375/100000 [14:18:18<8:23:34,  1.71it/s]
Train steps ... :  48%|████▊     | 48376/100000 [14:18:19<8:23:19,  1.71it/s]
Train steps ... :  48%|████▊     | 48377/100000 [14:18:19<8:23:20,  1.71it/s]
Train steps ... :  48%|████▊     | 48378/100000 [14:18:20<8:23:28,  1.71it/s]
Train steps ... :  48%|████▊     | 48379/100000 [14:18:20<8:23:11,  1.71it/s]
Train steps ... :  48%|████▊     | 48380/100000 [14:18:21<8:23:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48381/100000 [14:18:22<8:22:37,  1.71it/s]
Train steps ... :  48%|████▊     | 48382/100000 [14:18:22<8:23:29,  1.71it/s]
Train steps ... :  48%|████▊     | 48383/100000 [14:18:23<8:22:52,  1.71it/s]
Train steps ... :  48%|████▊     | 48384/100000 [14:18:23<8:22:40,  1.71it/s]
Train steps ... :  48%|████▊     | 48385/100000 [14:18:24<8:22:37,  1.71it/s]
Train steps ... :  48%|████▊     | 48386/100000 [14:18:24<8:22:48,  1.71it/s]
Train steps ... :  48%|████▊     | 48387/100000 [14:18:25<8:22:38,  1.71it/s]
Train steps ... :  48%|████▊     | 48388/100000 [14:18:26<8:22:27,  1.71it/s]
Train steps ... :  48%|████▊     | 48389/100000 [14:18:26<8:22:06,  1.71it/s]
Train steps ... :  48%|████▊     | 48390/100000 [14:18:27<8:22:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48391/100000 [14:18:27<8:22:39,  1.71it/s]
Train steps ... :  48%|████▊     | 48392/100000 [14:18:28<8:22:11,  1.71it/s]
Train steps ... :  48%|████▊     | 48393/100000 [14:18:29<8:22:36,  1.71it/s]
Train steps ... :  48%|████▊     | 48394/100000 [14:18:29<8:22:31,  1.71it/s]
Train steps ... :  48%|████▊     | 48395/100000 [14:18:30<8:23:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48396/100000 [14:18:30<8:23:15,  1.71it/s]
Train steps ... :  48%|████▊     | 48397/100000 [14:18:31<8:23:27,  1.71it/s]
Train steps ... :  48%|████▊     | 48398/100000 [14:18:31<8:22:39,  1.71it/s]
Train steps ... :  48%|████▊     | 48399/100000 [14:18:32<8:22:57,  1.71it/s]
Train steps ... :  48%|████▊     | 48400/100000 [14:18:33<8:23:58,  1.71it/s]Step... (48400 / 100000 | Loss: 0.6784441471099854, Learning Rate: 5.1859296482412066e-05)
+
                                                                             
Step... (48400 / 100000 | Loss: 0.9755862951278687, Learning Rate: 5.1859296482412066e-05)
+
Train steps ... :  48%|████▊     | 48400/100000 [14:18:33<8:23:58,  1.71it/s]
Train steps ... :  48%|████▊     | 48401/100000 [14:18:33<8:24:01,  1.71it/s]
Train steps ... :  48%|████▊     | 48402/100000 [14:18:34<8:23:14,  1.71it/s]
Train steps ... :  48%|████▊     | 48403/100000 [14:18:34<8:22:49,  1.71it/s]
Train steps ... :  48%|████▊     | 48404/100000 [14:18:35<8:22:32,  1.71it/s]
Train steps ... :  48%|████▊     | 48405/100000 [14:18:36<8:22:18,  1.71it/s]
Train steps ... :  48%|████▊     | 48406/100000 [14:18:36<8:23:45,  1.71it/s]
Train steps ... :  48%|████▊     | 48407/100000 [14:18:37<8:23:21,  1.71it/s]
Train steps ... :  48%|████▊     | 48408/100000 [14:18:37<8:23:07,  1.71it/s]
Train steps ... :  48%|████▊     | 48409/100000 [14:18:38<8:23:15,  1.71it/s]
Train steps ... :  48%|████▊     | 48410/100000 [14:18:38<8:22:27,  1.71it/s]
Train steps ... :  48%|████▊     | 48411/100000 [14:18:39<8:23:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48412/100000 [14:18:40<8:22:38,  1.71it/s]
Train steps ... :  48%|████▊     | 48413/100000 [14:18:40<8:23:45,  1.71it/s]
Train steps ... :  48%|████▊     | 48414/100000 [14:18:41<8:23:14,  1.71it/s]
Train steps ... :  48%|████▊     | 48415/100000 [14:18:41<8:22:56,  1.71it/s]
Train steps ... :  48%|████▊     | 48416/100000 [14:18:42<8:22:23,  1.71it/s]
Train steps ... :  48%|████▊     | 48417/100000 [14:18:43<8:22:27,  1.71it/s]
Train steps ... :  48%|████▊     | 48418/100000 [14:18:43<8:22:24,  1.71it/s]
Train steps ... :  48%|████▊     | 48419/100000 [14:18:44<8:22:57,  1.71it/s]
Train steps ... :  48%|████▊     | 48420/100000 [14:18:44<8:22:38,  1.71it/s]
Train steps ... :  48%|████▊     | 48421/100000 [14:18:45<8:22:16,  1.71it/s]
Train steps ... :  48%|████▊     | 48422/100000 [14:18:45<8:22:04,  1.71it/s]
Train steps ... :  48%|████▊     | 48423/100000 [14:18:46<8:23:03,  1.71it/s]
Train steps ... :  48%|████▊     | 48424/100000 [14:18:47<8:22:32,  1.71it/s]
Train steps ... :  48%|████▊     | 48425/100000 [14:18:47<8:22:43,  1.71it/s]Step... (48425 / 100000 | Loss: 1.1610805988311768, Learning Rate: 5.1834170854271356e-05)
+
                                                                             
Step... (48425 / 100000 | Loss: 0.6571499109268188, Learning Rate: 5.1834170854271356e-05)
+
Train steps ... :  48%|████▊     | 48425/100000 [14:18:48<8:22:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48426/100000 [14:18:48<8:22:40,  1.71it/s]
Train steps ... :  48%|████▊     | 48427/100000 [14:18:48<8:23:07,  1.71it/s]
Train steps ... :  48%|████▊     | 48428/100000 [14:18:49<8:23:35,  1.71it/s]
Train steps ... :  48%|████▊     | 48429/100000 [14:18:50<8:23:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48430/100000 [14:18:50<8:23:12,  1.71it/s]
Train steps ... :  48%|████▊     | 48431/100000 [14:18:51<8:22:55,  1.71it/s]
Train steps ... :  48%|████▊     | 48432/100000 [14:18:51<8:22:56,  1.71it/s]
Train steps ... :  48%|████▊     | 48433/100000 [14:18:52<8:22:26,  1.71it/s]
Train steps ... :  48%|████▊     | 48434/100000 [14:18:53<8:22:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48435/100000 [14:18:53<8:21:53,  1.71it/s]
Train steps ... :  48%|████▊     | 48436/100000 [14:18:54<8:21:35,  1.71it/s]
Train steps ... :  48%|████▊     | 48437/100000 [14:18:54<8:22:34,  1.71it/s]
Train steps ... :  48%|████▊     | 48438/100000 [14:18:55<8:24:01,  1.71it/s]
Train steps ... :  48%|████▊     | 48439/100000 [14:18:55<8:23:02,  1.71it/s]
Train steps ... :  48%|████▊     | 48440/100000 [14:18:56<8:23:07,  1.71it/s]
Train steps ... :  48%|████▊     | 48441/100000 [14:18:57<8:23:05,  1.71it/s]
Train steps ... :  48%|████▊     | 48442/100000 [14:18:57<8:22:36,  1.71it/s]
Train steps ... :  48%|████▊     | 48443/100000 [14:18:58<8:22:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48444/100000 [14:18:58<8:22:40,  1.71it/s]
Train steps ... :  48%|████▊     | 48445/100000 [14:18:59<8:22:31,  1.71it/s]
Train steps ... :  48%|████▊     | 48446/100000 [14:19:00<8:22:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48447/100000 [14:19:00<8:22:08,  1.71it/s]
Train steps ... :  48%|████▊     | 48448/100000 [14:19:01<8:21:58,  1.71it/s]
Train steps ... :  48%|████▊     | 48449/100000 [14:19:01<8:21:52,  1.71it/s]
Train steps ... :  48%|████▊     | 48450/100000 [14:19:02<8:22:21,  1.71it/s]Step... (48450 / 100000 | Loss: 1.2154836654663086, Learning Rate: 5.180904522613066e-05)
+
                                                                             
Step... (48450 / 100000 | Loss: 0.9171408414840698, Learning Rate: 5.180904522613066e-05)
+
Train steps ... :  48%|████▊     | 48450/100000 [14:19:02<8:22:21,  1.71it/s]
Train steps ... :  48%|████▊     | 48451/100000 [14:19:02<8:22:18,  1.71it/s]
Train steps ... :  48%|████▊     | 48452/100000 [14:19:03<8:22:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48453/100000 [14:19:04<8:21:49,  1.71it/s]
Train steps ... :  48%|████▊     | 48454/100000 [14:19:04<8:22:26,  1.71it/s]
Train steps ... :  48%|████▊     | 48455/100000 [14:19:05<8:23:03,  1.71it/s]
Train steps ... :  48%|████▊     | 48456/100000 [14:19:05<8:22:13,  1.71it/s]
Train steps ... :  48%|████▊     | 48457/100000 [14:19:06<8:22:51,  1.71it/s]
Train steps ... :  48%|████▊     | 48458/100000 [14:19:07<8:22:19,  1.71it/s]
Train steps ... :  48%|████▊     | 48459/100000 [14:19:07<8:22:01,  1.71it/s]
Train steps ... :  48%|████▊     | 48460/100000 [14:19:08<8:22:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48461/100000 [14:19:08<8:22:08,  1.71it/s]
Train steps ... :  48%|████▊     | 48462/100000 [14:19:09<8:22:22,  1.71it/s]
Train steps ... :  48%|████▊     | 48463/100000 [14:19:09<8:21:49,  1.71it/s]
Train steps ... :  48%|████▊     | 48464/100000 [14:19:10<8:22:01,  1.71it/s]
Train steps ... :  48%|████▊     | 48465/100000 [14:19:11<8:22:01,  1.71it/s]
Train steps ... :  48%|████▊     | 48466/100000 [14:19:11<8:21:54,  1.71it/s]
Train steps ... :  48%|████▊     | 48467/100000 [14:19:12<8:22:04,  1.71it/s]
Train steps ... :  48%|████▊     | 48468/100000 [14:19:12<8:22:06,  1.71it/s]
Train steps ... :  48%|████▊     | 48469/100000 [14:19:13<8:23:10,  1.71it/s]
Train steps ... :  48%|████▊     | 48470/100000 [14:19:14<8:22:28,  1.71it/s]
Train steps ... :  48%|████▊     | 48471/100000 [14:19:14<8:22:17,  1.71it/s]
Train steps ... :  48%|████▊     | 48472/100000 [14:19:15<8:21:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48473/100000 [14:19:15<8:22:12,  1.71it/s]
Train steps ... :  48%|████▊     | 48474/100000 [14:19:16<8:21:42,  1.71it/s]
Train steps ... :  48%|████▊     | 48475/100000 [14:19:16<8:22:44,  1.71it/s]Step... (48475 / 100000 | Loss: 0.6259517073631287, Learning Rate: 5.178391959798995e-05)
+
                                                                             
Step... (48475 / 100000 | Loss: 1.056362271308899, Learning Rate: 5.178391959798995e-05)
+
Train steps ... :  48%|████▊     | 48475/100000 [14:19:17<8:22:44,  1.71it/s]
Train steps ... :  48%|████▊     | 48476/100000 [14:19:17<8:22:42,  1.71it/s]
Train steps ... :  48%|████▊     | 48477/100000 [14:19:18<8:22:00,  1.71it/s]
Train steps ... :  48%|████▊     | 48478/100000 [14:19:18<8:22:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48479/100000 [14:19:19<8:22:01,  1.71it/s]
Train steps ... :  48%|████▊     | 48480/100000 [14:19:19<8:22:18,  1.71it/s]
Train steps ... :  48%|████▊     | 48481/100000 [14:19:20<8:22:10,  1.71it/s]
Train steps ... :  48%|████▊     | 48482/100000 [14:19:21<8:21:51,  1.71it/s]
Train steps ... :  48%|████▊     | 48483/100000 [14:19:21<8:21:32,  1.71it/s]
Train steps ... :  48%|████▊     | 48484/100000 [14:19:22<8:21:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48485/100000 [14:19:22<8:21:25,  1.71it/s]
Train steps ... :  48%|████▊     | 48486/100000 [14:19:23<8:21:17,  1.71it/s]
Train steps ... :  48%|████▊     | 48487/100000 [14:19:24<8:22:34,  1.71it/s]
Train steps ... :  48%|████▊     | 48488/100000 [14:19:24<8:21:56,  1.71it/s]
Train steps ... :  48%|████▊     | 48489/100000 [14:19:25<8:23:09,  1.71it/s]
Train steps ... :  48%|████▊     | 48490/100000 [14:19:25<8:22:56,  1.71it/s]
Train steps ... :  48%|████▊     | 48491/100000 [14:19:26<8:24:45,  1.70it/s]
Train steps ... :  48%|████▊     | 48492/100000 [14:19:26<8:22:36,  1.71it/s]
Train steps ... :  48%|████▊     | 48493/100000 [14:19:27<8:22:43,  1.71it/s]
Train steps ... :  48%|████▊     | 48494/100000 [14:19:28<8:22:14,  1.71it/s]
Train steps ... :  48%|████▊     | 48495/100000 [14:19:28<8:22:06,  1.71it/s]
Train steps ... :  48%|████▊     | 48496/100000 [14:19:29<8:21:48,  1.71it/s]
Train steps ... :  48%|████▊     | 48497/100000 [14:19:29<8:21:34,  1.71it/s]
Train steps ... :  48%|████▊     | 48498/100000 [14:19:30<8:21:54,  1.71it/s]
Train steps ... :  48%|████▊     | 48499/100000 [14:19:31<8:21:49,  1.71it/s]
Train steps ... :  48%|████▊     | 48500/100000 [14:19:31<8:21:31,  1.71it/s]Step... (48500 / 100000 | Loss: 0.6908155083656311, Learning Rate: 5.175879396984925e-05)
+
                                                                             
Step... (48500 / 100000 | Loss: 0.7306506037712097, Learning Rate: 5.175879396984925e-05)
+
Train steps ... :  48%|████▊     | 48500/100000 [14:19:31<8:21:31,  1.71it/s]
Train steps ... :  49%|████▊     | 48501/100000 [14:19:32<8:21:41,  1.71it/s]
Train steps ... :  49%|████▊     | 48502/100000 [14:19:32<8:21:16,  1.71it/s]
Train steps ... :  49%|████▊     | 48503/100000 [14:19:33<8:21:10,  1.71it/s]
Train steps ... :  49%|████▊     | 48504/100000 [14:19:33<8:21:29,  1.71it/s]
Train steps ... :  49%|████▊     | 48505/100000 [14:19:34<8:21:19,  1.71it/s]
Train steps ... :  49%|████▊     | 48506/100000 [14:19:35<8:23:08,  1.71it/s]
Train steps ... :  49%|████▊     | 48507/100000 [14:19:35<8:22:13,  1.71it/s]
Train steps ... :  49%|████▊     | 48508/100000 [14:19:36<8:21:52,  1.71it/s]
Train steps ... :  49%|████▊     | 48509/100000 [14:19:36<8:22:18,  1.71it/s]
Train steps ... :  49%|████▊     | 48510/100000 [14:19:37<8:21:39,  1.71it/s]
Train steps ... :  49%|████▊     | 48511/100000 [14:19:38<8:21:47,  1.71it/s]
Train steps ... :  49%|████▊     | 48512/100000 [14:19:38<8:21:25,  1.71it/s]
Train steps ... :  49%|████▊     | 48513/100000 [14:19:39<8:21:40,  1.71it/s]
Train steps ... :  49%|████▊     | 48514/100000 [14:19:39<8:21:22,  1.71it/s]
Train steps ... :  49%|████▊     | 48515/100000 [14:19:40<8:21:15,  1.71it/s]
Train steps ... :  49%|████▊     | 48516/100000 [14:19:40<8:21:28,  1.71it/s]
Train steps ... :  49%|████▊     | 48517/100000 [14:19:41<8:21:03,  1.71it/s]
Train steps ... :  49%|████▊     | 48518/100000 [14:19:42<8:21:06,  1.71it/s]
Train steps ... :  49%|████▊     | 48519/100000 [14:19:42<8:21:11,  1.71it/s]
Train steps ... :  49%|████▊     | 48520/100000 [14:19:43<8:21:07,  1.71it/s]
Train steps ... :  49%|████▊     | 48521/100000 [14:19:43<8:22:13,  1.71it/s]
Train steps ... :  49%|████▊     | 48522/100000 [14:19:44<8:22:10,  1.71it/s]
Train steps ... :  49%|████▊     | 48523/100000 [14:19:45<8:21:59,  1.71it/s]
Train steps ... :  49%|████▊     | 48524/100000 [14:19:45<8:21:30,  1.71it/s]
Train steps ... :  49%|████▊     | 48525/100000 [14:19:46<8:21:43,  1.71it/s]Step... (48525 / 100000 | Loss: 0.7329034805297852, Learning Rate: 5.173366834170854e-05)
+
                                                                             
Step... (48525 / 100000 | Loss: 0.710071325302124, Learning Rate: 5.173366834170854e-05)
+
Train steps ... :  49%|████▊     | 48525/100000 [14:19:46<8:21:43,  1.71it/s]
Train steps ... :  49%|████▊     | 48526/100000 [14:19:46<8:21:52,  1.71it/s]
Train steps ... :  49%|████▊     | 48527/100000 [14:19:47<8:21:31,  1.71it/s]
Train steps ... :  49%|████▊     | 48528/100000 [14:19:47<8:21:06,  1.71it/s]
Train steps ... :  49%|████▊     | 48529/100000 [14:19:48<8:21:25,  1.71it/s]
Train steps ... :  49%|████▊     | 48530/100000 [14:19:49<8:21:20,  1.71it/s]
Train steps ... :  49%|████▊     | 48531/100000 [14:19:49<8:21:19,  1.71it/s]
Train steps ... :  49%|████▊     | 48532/100000 [14:19:50<8:21:44,  1.71it/s]
Train steps ... :  49%|████▊     | 48533/100000 [14:19:50<8:21:16,  1.71it/s]
Train steps ... :  49%|████▊     | 48534/100000 [14:19:51<8:21:07,  1.71it/s]
Train steps ... :  49%|████▊     | 48535/100000 [14:19:52<8:22:34,  1.71it/s]
Train steps ... :  49%|████▊     | 48536/100000 [14:19:52<8:21:28,  1.71it/s]
Train steps ... :  49%|████▊     | 48537/100000 [14:19:53<8:21:10,  1.71it/s]
Train steps ... :  49%|████▊     | 48538/100000 [14:19:53<8:20:51,  1.71it/s]
Train steps ... :  49%|████▊     | 48539/100000 [14:19:54<8:21:13,  1.71it/s]
Train steps ... :  49%|████▊     | 48540/100000 [14:19:54<8:20:57,  1.71it/s]
Train steps ... :  49%|████▊     | 48541/100000 [14:19:55<8:21:09,  1.71it/s]
Train steps ... :  49%|████▊     | 48542/100000 [14:19:56<8:21:14,  1.71it/s]
Train steps ... :  49%|████▊     | 48543/100000 [14:19:56<8:21:18,  1.71it/s]
Train steps ... :  49%|████▊     | 48544/100000 [14:19:57<8:21:29,  1.71it/s]
Train steps ... :  49%|████▊     | 48545/100000 [14:19:57<8:21:17,  1.71it/s]
Train steps ... :  49%|████▊     | 48546/100000 [14:19:58<8:21:29,  1.71it/s]
Train steps ... :  49%|████▊     | 48547/100000 [14:19:59<8:21:01,  1.71it/s]
Train steps ... :  49%|████▊     | 48548/100000 [14:19:59<8:21:39,  1.71it/s]
Train steps ... :  49%|████▊     | 48549/100000 [14:20:00<8:21:24,  1.71it/s]
Train steps ... :  49%|████▊     | 48550/100000 [14:20:00<8:21:16,  1.71it/s]Step... (48550 / 100000 | Loss: 0.8192480206489563, Learning Rate: 5.1708542713567846e-05)
+
                                                                             
Step... (48550 / 100000 | Loss: 0.9812374114990234, Learning Rate: 5.1708542713567846e-05)
+
Train steps ... :  49%|████▊     | 48550/100000 [14:20:01<8:21:16,  1.71it/s]
Train steps ... :  49%|████▊     | 48551/100000 [14:20:01<8:22:01,  1.71it/s]
Train steps ... :  49%|████▊     | 48552/100000 [14:20:02<8:21:48,  1.71it/s]
Train steps ... :  49%|████▊     | 48553/100000 [14:20:02<8:21:14,  1.71it/s]
Train steps ... :  49%|████▊     | 48554/100000 [14:20:03<8:21:26,  1.71it/s]
Train steps ... :  49%|████▊     | 48555/100000 [14:20:03<8:20:58,  1.71it/s]
Train steps ... :  49%|████▊     | 48556/100000 [14:20:04<8:20:17,  1.71it/s]
Train steps ... :  49%|████▊     | 48557/100000 [14:20:04<8:21:25,  1.71it/s]
Train steps ... :  49%|████▊     | 48558/100000 [14:20:05<8:21:22,  1.71it/s]
Train steps ... :  49%|████▊     | 48559/100000 [14:20:06<8:20:56,  1.71it/s]
Train steps ... :  49%|████▊     | 48560/100000 [14:20:06<8:20:32,  1.71it/s]
Train steps ... :  49%|████▊     | 48561/100000 [14:20:07<8:20:37,  1.71it/s]
Train steps ... :  49%|████▊     | 48562/100000 [14:20:07<8:20:35,  1.71it/s]
Train steps ... :  49%|████▊     | 48563/100000 [14:20:08<8:20:50,  1.71it/s]
Train steps ... :  49%|████▊     | 48564/100000 [14:20:09<8:21:17,  1.71it/s]
Train steps ... :  49%|████▊     | 48565/100000 [14:20:09<8:21:08,  1.71it/s]
Train steps ... :  49%|████▊     | 48566/100000 [14:20:10<8:21:27,  1.71it/s]
Train steps ... :  49%|████▊     | 48567/100000 [14:20:10<8:21:18,  1.71it/s]
Train steps ... :  49%|████▊     | 48568/100000 [14:20:11<8:21:30,  1.71it/s]
Train steps ... :  49%|████▊     | 48569/100000 [14:20:11<8:21:06,  1.71it/s]
Train steps ... :  49%|████▊     | 48570/100000 [14:20:12<8:21:01,  1.71it/s]
Train steps ... :  49%|████▊     | 48571/100000 [14:20:13<8:20:27,  1.71it/s]
Train steps ... :  49%|████▊     | 48572/100000 [14:20:13<8:20:28,  1.71it/s]
Train steps ... :  49%|████▊     | 48573/100000 [14:20:14<8:21:17,  1.71it/s]
Train steps ... :  49%|████▊     | 48574/100000 [14:20:14<8:21:50,  1.71it/s]
Train steps ... :  49%|████▊     | 48575/100000 [14:20:15<8:21:45,  1.71it/s]Step... (48575 / 100000 | Loss: 0.5931459665298462, Learning Rate: 5.1683417085427136e-05)
+
                                                                             
Step... (48575 / 100000 | Loss: 0.9462869167327881, Learning Rate: 5.1683417085427136e-05)
+
Train steps ... :  49%|████▊     | 48575/100000 [14:20:15<8:21:45,  1.71it/s]
Train steps ... :  49%|████▊     | 48576/100000 [14:20:16<8:21:54,  1.71it/s]
Train steps ... :  49%|████▊     | 48577/100000 [14:20:16<8:21:21,  1.71it/s]
Train steps ... :  49%|████▊     | 48578/100000 [14:20:17<8:22:07,  1.71it/s]
Train steps ... :  49%|████▊     | 48579/100000 [14:20:17<8:21:29,  1.71it/s]
Train steps ... :  49%|████▊     | 48580/100000 [14:20:18<8:20:58,  1.71it/s]
Train steps ... :  49%|████▊     | 48581/100000 [14:20:18<8:21:27,  1.71it/s]
Train steps ... :  49%|████▊     | 48582/100000 [14:20:19<8:20:54,  1.71it/s]
Train steps ... :  49%|████▊     | 48583/100000 [14:20:20<8:21:08,  1.71it/s]
Train steps ... :  49%|████▊     | 48584/100000 [14:20:20<8:20:45,  1.71it/s]
Train steps ... :  49%|████▊     | 48585/100000 [14:20:21<8:20:52,  1.71it/s]
Train steps ... :  49%|████▊     | 48586/100000 [14:20:21<8:21:21,  1.71it/s]
Train steps ... :  49%|████▊     | 48587/100000 [14:20:22<8:20:45,  1.71it/s]
Train steps ... :  49%|████▊     | 48588/100000 [14:20:23<8:20:46,  1.71it/s]
Train steps ... :  49%|████▊     | 48589/100000 [14:20:23<8:21:04,  1.71it/s]
Train steps ... :  49%|████▊     | 48590/100000 [14:20:24<8:20:41,  1.71it/s]
Train steps ... :  49%|████▊     | 48591/100000 [14:20:24<8:20:42,  1.71it/s]
Train steps ... :  49%|████▊     | 48592/100000 [14:20:25<8:21:36,  1.71it/s]
Train steps ... :  49%|████▊     | 48593/100000 [14:20:25<8:21:54,  1.71it/s]
Train steps ... :  49%|████▊     | 48594/100000 [14:20:26<8:20:49,  1.71it/s]
Train steps ... :  49%|████▊     | 48595/100000 [14:20:27<8:20:22,  1.71it/s]
Train steps ... :  49%|████▊     | 48596/100000 [14:20:27<8:20:45,  1.71it/s]
Train steps ... :  49%|████▊     | 48597/100000 [14:20:28<8:20:37,  1.71it/s]
Train steps ... :  49%|████▊     | 48598/100000 [14:20:28<8:20:51,  1.71it/s]
Train steps ... :  49%|████▊     | 48599/100000 [14:20:29<8:20:15,  1.71it/s]
Train steps ... :  49%|████▊     | 48600/100000 [14:20:30<8:21:09,  1.71it/s]Step... (48600 / 100000 | Loss: 0.8801199197769165, Learning Rate: 5.165829145728643e-05)
+
                                                                             
Step... (48600 / 100000 | Loss: 1.1096972227096558, Learning Rate: 5.165829145728643e-05)
+
Train steps ... :  49%|████▊     | 48600/100000 [14:20:30<8:21:09,  1.71it/s]
Train steps ... :  49%|████▊     | 48601/100000 [14:20:30<8:20:49,  1.71it/s]
Train steps ... :  49%|████▊     | 48602/100000 [14:20:31<8:21:32,  1.71it/s]
Train steps ... :  49%|████▊     | 48603/100000 [14:20:31<8:21:08,  1.71it/s]
Train steps ... :  49%|████▊     | 48604/100000 [14:20:32<8:20:58,  1.71it/s]
Train steps ... :  49%|████▊     | 48605/100000 [14:20:33<8:20:38,  1.71it/s]
Train steps ... :  49%|████▊     | 48606/100000 [14:20:33<8:20:26,  1.71it/s]
Train steps ... :  49%|████▊     | 48607/100000 [14:20:34<8:20:09,  1.71it/s]
Train steps ... :  49%|████▊     | 48608/100000 [14:20:34<8:20:03,  1.71it/s]
Train steps ... :  49%|████▊     | 48609/100000 [14:20:35<8:19:44,  1.71it/s]
Train steps ... :  49%|████▊     | 48610/100000 [14:20:35<8:20:12,  1.71it/s]
Train steps ... :  49%|████▊     | 48611/100000 [14:20:36<8:20:44,  1.71it/s]
Train steps ... :  49%|████▊     | 48612/100000 [14:20:37<8:20:26,  1.71it/s]
Train steps ... :  49%|████▊     | 48613/100000 [14:20:37<8:20:14,  1.71it/s]
Train steps ... :  49%|████▊     | 48614/100000 [14:20:38<8:20:23,  1.71it/s]
Train steps ... :  49%|████▊     | 48615/100000 [14:20:38<8:20:19,  1.71it/s]
Train steps ... :  49%|████▊     | 48616/100000 [14:20:39<8:20:26,  1.71it/s]
Train steps ... :  49%|████▊     | 48617/100000 [14:20:40<8:20:18,  1.71it/s]
Train steps ... :  49%|████▊     | 48618/100000 [14:20:40<8:20:17,  1.71it/s]
Train steps ... :  49%|████▊     | 48619/100000 [14:20:41<8:21:02,  1.71it/s]
Train steps ... :  49%|████▊     | 48620/100000 [14:20:41<8:20:41,  1.71it/s]
Train steps ... :  49%|████▊     | 48621/100000 [14:20:42<8:20:44,  1.71it/s]
Train steps ... :  49%|████▊     | 48622/100000 [14:20:42<8:20:13,  1.71it/s]
Train steps ... :  49%|████▊     | 48623/100000 [14:20:43<8:20:04,  1.71it/s]
Train steps ... :  49%|████▊     | 48624/100000 [14:20:44<8:20:33,  1.71it/s]
Train steps ... :  49%|████▊     | 48625/100000 [14:20:44<8:21:25,  1.71it/s]Step... (48625 / 100000 | Loss: 0.8187085390090942, Learning Rate: 5.1633165829145736e-05)
+
                                                                             
Step... (48625 / 100000 | Loss: 1.1295348405838013, Learning Rate: 5.1633165829145736e-05)
+
Train steps ... :  49%|████▊     | 48625/100000 [14:20:45<8:21:25,  1.71it/s]
Train steps ... :  49%|████▊     | 48626/100000 [14:20:45<8:20:57,  1.71it/s]
Train steps ... :  49%|████▊     | 48627/100000 [14:20:45<8:20:44,  1.71it/s]
Train steps ... :  49%|████▊     | 48628/100000 [14:20:46<8:20:50,  1.71it/s]
Train steps ... :  49%|████▊     | 48629/100000 [14:20:47<8:20:43,  1.71it/s]
Train steps ... :  49%|████▊     | 48630/100000 [14:20:47<8:20:29,  1.71it/s]
Train steps ... :  49%|████▊     | 48631/100000 [14:20:48<8:20:30,  1.71it/s]
Train steps ... :  49%|████▊     | 48632/100000 [14:20:48<8:20:47,  1.71it/s]
Train steps ... :  49%|████▊     | 48633/100000 [14:20:49<8:21:00,  1.71it/s]
Train steps ... :  49%|████▊     | 48634/100000 [14:20:49<8:21:00,  1.71it/s]
Train steps ... :  49%|████▊     | 48635/100000 [14:20:50<8:20:20,  1.71it/s]
Train steps ... :  49%|████▊     | 48636/100000 [14:20:51<8:20:25,  1.71it/s]
Train steps ... :  49%|████▊     | 48637/100000 [14:20:51<8:20:53,  1.71it/s]
Train steps ... :  49%|████▊     | 48638/100000 [14:20:52<8:20:56,  1.71it/s]
Train steps ... :  49%|████▊     | 48639/100000 [14:20:52<8:21:01,  1.71it/s]
Train steps ... :  49%|████▊     | 48640/100000 [14:20:53<8:20:35,  1.71it/s]
Train steps ... :  49%|████▊     | 48641/100000 [14:20:54<8:20:30,  1.71it/s]
Train steps ... :  49%|████▊     | 48642/100000 [14:20:54<8:21:27,  1.71it/s]
Train steps ... :  49%|████▊     | 48643/100000 [14:20:55<8:20:15,  1.71it/s]
Train steps ... :  49%|████▊     | 48644/100000 [14:20:55<8:21:22,  1.71it/s]
Train steps ... :  49%|████▊     | 48645/100000 [14:20:56<8:21:58,  1.71it/s]
Train steps ... :  49%|████▊     | 48646/100000 [14:20:56<8:21:43,  1.71it/s]
Train steps ... :  49%|████▊     | 48647/100000 [14:20:57<8:21:26,  1.71it/s]
Train steps ... :  49%|████▊     | 48648/100000 [14:20:58<8:21:18,  1.71it/s]
Train steps ... :  49%|████▊     | 48649/100000 [14:20:58<8:20:35,  1.71it/s]
Train steps ... :  49%|████▊     | 48650/100000 [14:20:59<8:20:54,  1.71it/s]Step... (48650 / 100000 | Loss: 1.0358858108520508, Learning Rate: 5.1608040201005025e-05)
+
                                                                             
Step... (48650 / 100000 | Loss: 0.7935410737991333, Learning Rate: 5.1608040201005025e-05)
+
Train steps ... :  49%|████▊     | 48650/100000 [14:20:59<8:20:54,  1.71it/s]
Train steps ... :  49%|████▊     | 48651/100000 [14:20:59<8:20:19,  1.71it/s]
Train steps ... :  49%|████▊     | 48652/100000 [14:21:00<8:19:50,  1.71it/s]
Train steps ... :  49%|████▊     | 48653/100000 [14:21:01<8:20:23,  1.71it/s]
Train steps ... :  49%|████▊     | 48654/100000 [14:21:01<8:20:02,  1.71it/s]
Train steps ... :  49%|████▊     | 48655/100000 [14:21:02<8:19:46,  1.71it/s]
Train steps ... :  49%|████▊     | 48656/100000 [14:21:02<8:19:58,  1.71it/s]
Train steps ... :  49%|████▊     | 48657/100000 [14:21:03<8:19:42,  1.71it/s]
Train steps ... :  49%|████▊     | 48658/100000 [14:21:03<8:20:00,  1.71it/s]
Train steps ... :  49%|████▊     | 48659/100000 [14:21:04<8:20:06,  1.71it/s]
Train steps ... :  49%|████▊     | 48660/100000 [14:21:05<8:20:53,  1.71it/s]
Train steps ... :  49%|████▊     | 48661/100000 [14:21:05<8:21:19,  1.71it/s]
Train steps ... :  49%|████▊     | 48662/100000 [14:21:06<8:22:45,  1.70it/s]
Train steps ... :  49%|████▊     | 48663/100000 [14:21:06<8:23:10,  1.70it/s]
Train steps ... :  49%|████▊     | 48664/100000 [14:21:07<8:22:38,  1.70it/s]
Train steps ... :  49%|████▊     | 48665/100000 [14:21:08<8:22:19,  1.70it/s]
Train steps ... :  49%|████▊     | 48666/100000 [14:21:08<8:22:06,  1.70it/s]
Train steps ... :  49%|████▊     | 48667/100000 [14:21:09<8:21:21,  1.71it/s]
Train steps ... :  49%|████▊     | 48668/100000 [14:21:09<8:21:23,  1.71it/s]
Train steps ... :  49%|████▊     | 48669/100000 [14:21:10<8:20:39,  1.71it/s]
Train steps ... :  49%|████▊     | 48670/100000 [14:21:11<8:20:23,  1.71it/s]
Train steps ... :  49%|████▊     | 48671/100000 [14:21:11<8:20:10,  1.71it/s]
Train steps ... :  49%|████▊     | 48672/100000 [14:21:12<8:20:08,  1.71it/s]
Train steps ... :  49%|████▊     | 48673/100000 [14:21:12<8:19:52,  1.71it/s]
Train steps ... :  49%|████▊     | 48674/100000 [14:21:13<8:19:43,  1.71it/s]
Train steps ... :  49%|████▊     | 48675/100000 [14:21:13<8:20:08,  1.71it/s]Step... (48675 / 100000 | Loss: 0.6668832302093506, Learning Rate: 5.158291457286433e-05)
+
                                                                             
Step... (48675 / 100000 | Loss: 1.0762144327163696, Learning Rate: 5.158291457286433e-05)
+
Train steps ... :  49%|████▊     | 48675/100000 [14:21:14<8:20:08,  1.71it/s]
Train steps ... :  49%|████▊     | 48676/100000 [14:21:14<8:20:01,  1.71it/s]
Train steps ... :  49%|████▊     | 48677/100000 [14:21:15<8:19:56,  1.71it/s]
Train steps ... :  49%|████▊     | 48678/100000 [14:21:15<8:20:11,  1.71it/s]
Train steps ... :  49%|████▊     | 48679/100000 [14:21:16<8:20:18,  1.71it/s]
Train steps ... :  49%|████▊     | 48680/100000 [14:21:16<8:19:45,  1.71it/s]
Train steps ... :  49%|████▊     | 48681/100000 [14:21:17<8:20:11,  1.71it/s]
Train steps ... :  49%|████▊     | 48682/100000 [14:21:18<8:20:11,  1.71it/s]
Train steps ... :  49%|████▊     | 48683/100000 [14:21:18<8:20:43,  1.71it/s]
Train steps ... :  49%|████▊     | 48684/100000 [14:21:19<8:20:48,  1.71it/s]
Train steps ... :  49%|████▊     | 48685/100000 [14:21:19<8:20:41,  1.71it/s]
Train steps ... :  49%|████▊     | 48686/100000 [14:21:20<8:20:04,  1.71it/s]
Train steps ... :  49%|████▊     | 48687/100000 [14:21:20<8:21:44,  1.70it/s]
Train steps ... :  49%|████▊     | 48688/100000 [14:21:21<8:20:57,  1.71it/s]
Train steps ... :  49%|████▊     | 48689/100000 [14:21:22<8:21:06,  1.71it/s]
Train steps ... :  49%|████▊     | 48690/100000 [14:21:22<8:20:46,  1.71it/s]
Train steps ... :  49%|████▊     | 48691/100000 [14:21:23<8:21:13,  1.71it/s]
Train steps ... :  49%|████▊     | 48692/100000 [14:21:23<8:20:30,  1.71it/s]
Train steps ... :  49%|████▊     | 48693/100000 [14:21:24<8:20:49,  1.71it/s]
Train steps ... :  49%|████▊     | 48694/100000 [14:21:25<8:20:18,  1.71it/s]
Train steps ... :  49%|████▊     | 48695/100000 [14:21:25<8:19:56,  1.71it/s]
Train steps ... :  49%|████▊     | 48696/100000 [14:21:26<8:20:16,  1.71it/s]
Train steps ... :  49%|████▊     | 48697/100000 [14:21:26<8:20:12,  1.71it/s]
Train steps ... :  49%|████▊     | 48698/100000 [14:21:27<8:20:13,  1.71it/s]
Train steps ... :  49%|████▊     | 48699/100000 [14:21:27<8:20:50,  1.71it/s]
Train steps ... :  49%|████▊     | 48700/100000 [14:21:28<8:21:20,  1.71it/s]Step... (48700 / 100000 | Loss: 0.7002507448196411, Learning Rate: 5.155778894472362e-05)
+
                                                                             
Step... (48700 / 100000 | Loss: 1.197474718093872, Learning Rate: 5.155778894472362e-05)
+
Train steps ... :  49%|████▊     | 48700/100000 [14:21:28<8:21:20,  1.71it/s]
Train steps ... :  49%|████▊     | 48701/100000 [14:21:29<8:21:34,  1.70it/s]
Train steps ... :  49%|████▊     | 48702/100000 [14:21:29<8:20:14,  1.71it/s]
Train steps ... :  49%|████▊     | 48703/100000 [14:21:30<8:20:02,  1.71it/s]
Train steps ... :  49%|████▊     | 48704/100000 [14:21:30<8:19:40,  1.71it/s]
Train steps ... :  49%|████▊     | 48705/100000 [14:21:31<8:19:57,  1.71it/s]
Train steps ... :  49%|████▊     | 48706/100000 [14:21:32<8:20:25,  1.71it/s]
Train steps ... :  49%|████▊     | 48707/100000 [14:21:32<8:19:45,  1.71it/s]
Train steps ... :  49%|████▊     | 48708/100000 [14:21:33<8:20:09,  1.71it/s]
Train steps ... :  49%|████▊     | 48709/100000 [14:21:33<8:20:32,  1.71it/s]
Train steps ... :  49%|████▊     | 48710/100000 [14:21:34<8:20:15,  1.71it/s]
Train steps ... :  49%|████▊     | 48711/100000 [14:21:35<8:20:14,  1.71it/s]
Train steps ... :  49%|████▊     | 48712/100000 [14:21:35<8:19:41,  1.71it/s]
Train steps ... :  49%|████▊     | 48713/100000 [14:21:36<8:20:57,  1.71it/s]
Train steps ... :  49%|████▊     | 48714/100000 [14:21:36<8:19:56,  1.71it/s]
Train steps ... :  49%|████▊     | 48715/100000 [14:21:37<8:20:33,  1.71it/s]
Train steps ... :  49%|████▊     | 48716/100000 [14:21:37<8:19:57,  1.71it/s]
Train steps ... :  49%|████▊     | 48717/100000 [14:21:38<8:20:19,  1.71it/s]
Train steps ... :  49%|████▊     | 48718/100000 [14:21:39<8:19:49,  1.71it/s]
Train steps ... :  49%|████▊     | 48719/100000 [14:21:39<8:19:38,  1.71it/s]
Train steps ... :  49%|████▊     | 48720/100000 [14:21:40<8:20:25,  1.71it/s]
Train steps ... :  49%|████▊     | 48721/100000 [14:21:40<8:19:50,  1.71it/s]
Train steps ... :  49%|████▊     | 48722/100000 [14:21:41<8:19:51,  1.71it/s]
Train steps ... :  49%|████▊     | 48723/100000 [14:21:42<8:19:46,  1.71it/s]
Train steps ... :  49%|████▊     | 48724/100000 [14:21:42<8:19:28,  1.71it/s]
Train steps ... :  49%|████▊     | 48725/100000 [14:21:43<8:20:04,  1.71it/s]Step... (48725 / 100000 | Loss: 0.7034691572189331, Learning Rate: 5.1532663316582915e-05)
+
                                                                             
Step... (48725 / 100000 | Loss: 0.9934941530227661, Learning Rate: 5.1532663316582915e-05)
+
Train steps ... :  49%|████▊     | 48725/100000 [14:21:43<8:20:04,  1.71it/s]
Train steps ... :  49%|████▊     | 48726/100000 [14:21:43<8:19:50,  1.71it/s]
Train steps ... :  49%|████▊     | 48727/100000 [14:21:44<8:19:32,  1.71it/s]
Train steps ... :  49%|████▊     | 48728/100000 [14:21:44<8:20:17,  1.71it/s]
Train steps ... :  49%|████▊     | 48729/100000 [14:21:45<8:20:34,  1.71it/s]
Train steps ... :  49%|████▊     | 48730/100000 [14:21:46<8:21:33,  1.70it/s]
Train steps ... :  49%|████▊     | 48731/100000 [14:21:46<8:20:22,  1.71it/s]
Train steps ... :  49%|████▊     | 48732/100000 [14:21:47<8:20:11,  1.71it/s]
Train steps ... :  49%|████▊     | 48733/100000 [14:21:47<8:21:00,  1.71it/s]
Train steps ... :  49%|████▊     | 48734/100000 [14:21:48<8:20:35,  1.71it/s]
Train steps ... :  49%|████▊     | 48735/100000 [14:21:49<8:20:26,  1.71it/s]
Train steps ... :  49%|████▊     | 48736/100000 [14:21:49<8:20:12,  1.71it/s]
Train steps ... :  49%|████▊     | 48737/100000 [14:21:50<8:20:23,  1.71it/s]
Train steps ... :  49%|████▊     | 48738/100000 [14:21:50<8:19:50,  1.71it/s]
Train steps ... :  49%|████▊     | 48739/100000 [14:21:51<8:19:30,  1.71it/s]
Train steps ... :  49%|████▊     | 48740/100000 [14:21:51<8:20:12,  1.71it/s]
Train steps ... :  49%|████▊     | 48741/100000 [14:21:52<8:20:13,  1.71it/s]
Train steps ... :  49%|████▊     | 48742/100000 [14:21:53<8:20:18,  1.71it/s]
Train steps ... :  49%|████▊     | 48743/100000 [14:21:53<8:20:01,  1.71it/s]
Train steps ... :  49%|████▊     | 48744/100000 [14:21:54<8:20:57,  1.71it/s]
Train steps ... :  49%|████▊     | 48745/100000 [14:21:54<8:19:36,  1.71it/s]
Train steps ... :  49%|████▊     | 48746/100000 [14:21:55<8:19:57,  1.71it/s]
Train steps ... :  49%|████▊     | 48747/100000 [14:21:56<8:21:31,  1.70it/s]
Train steps ... :  49%|████▊     | 48748/100000 [14:21:56<8:19:41,  1.71it/s]
Train steps ... :  49%|████▊     | 48749/100000 [14:21:57<8:19:15,  1.71it/s]
Train steps ... :  49%|████▉     | 48750/100000 [14:21:57<8:20:01,  1.71it/s]Step... (48750 / 100000 | Loss: 0.6176624894142151, Learning Rate: 5.150753768844221e-05)
+
                                                                             
Step... (48750 / 100000 | Loss: 1.2120444774627686, Learning Rate: 5.150753768844221e-05)
+
Train steps ... :  49%|████▉     | 48750/100000 [14:21:58<8:20:01,  1.71it/s]
Train steps ... :  49%|████▉     | 48751/100000 [14:21:58<8:19:52,  1.71it/s]
Train steps ... :  49%|████▉     | 48752/100000 [14:21:59<8:19:48,  1.71it/s]
Train steps ... :  49%|████▉     | 48753/100000 [14:21:59<8:19:44,  1.71it/s]
Train steps ... :  49%|████▉     | 48754/100000 [14:22:00<8:19:33,  1.71it/s]
Train steps ... :  49%|████▉     | 48755/100000 [14:22:00<8:20:12,  1.71it/s]
Train steps ... :  49%|████▉     | 48756/100000 [14:22:01<8:20:20,  1.71it/s]
Train steps ... :  49%|████▉     | 48757/100000 [14:22:01<8:19:30,  1.71it/s]
Train steps ... :  49%|████▉     | 48758/100000 [14:22:02<8:19:07,  1.71it/s]
Train steps ... :  49%|████▉     | 48759/100000 [14:22:03<8:19:09,  1.71it/s]
Train steps ... :  49%|████▉     | 48760/100000 [14:22:03<8:19:02,  1.71it/s]
Train steps ... :  49%|████▉     | 48761/100000 [14:22:04<8:19:07,  1.71it/s]
Train steps ... :  49%|████▉     | 48762/100000 [14:22:04<8:19:28,  1.71it/s]
Train steps ... :  49%|████▉     | 48763/100000 [14:22:05<8:19:47,  1.71it/s]
Train steps ... :  49%|████▉     | 48764/100000 [14:22:06<8:19:30,  1.71it/s]
Train steps ... :  49%|████▉     | 48765/100000 [14:22:06<8:19:47,  1.71it/s]
Train steps ... :  49%|████▉     | 48766/100000 [14:22:07<8:19:17,  1.71it/s]
Train steps ... :  49%|████▉     | 48767/100000 [14:22:07<8:19:18,  1.71it/s]
Train steps ... :  49%|████▉     | 48768/100000 [14:22:08<8:19:21,  1.71it/s]
Train steps ... :  49%|████▉     | 48769/100000 [14:22:08<8:19:40,  1.71it/s]
Train steps ... :  49%|████▉     | 48770/100000 [14:22:09<8:19:31,  1.71it/s]
Train steps ... :  49%|████▉     | 48771/100000 [14:22:10<8:19:28,  1.71it/s]
Train steps ... :  49%|████▉     | 48772/100000 [14:22:10<8:19:08,  1.71it/s]
Train steps ... :  49%|████▉     | 48773/100000 [14:22:11<8:18:52,  1.71it/s]
Train steps ... :  49%|████▉     | 48774/100000 [14:22:11<8:18:33,  1.71it/s]
Train steps ... :  49%|████▉     | 48775/100000 [14:22:12<8:18:56,  1.71it/s]Step... (48775 / 100000 | Loss: 1.0839571952819824, Learning Rate: 5.148241206030151e-05)
+
                                                                             
Step... (48775 / 100000 | Loss: 0.7731757760047913, Learning Rate: 5.148241206030151e-05)
+
Train steps ... :  49%|████▉     | 48775/100000 [14:22:12<8:18:56,  1.71it/s]
Train steps ... :  49%|████▉     | 48776/100000 [14:22:13<8:18:40,  1.71it/s]
Train steps ... :  49%|████▉     | 48777/100000 [14:22:13<8:18:33,  1.71it/s]
Train steps ... :  49%|████▉     | 48778/100000 [14:22:14<8:19:02,  1.71it/s]
Train steps ... :  49%|████▉     | 48779/100000 [14:22:14<8:19:04,  1.71it/s]
Train steps ... :  49%|████▉     | 48780/100000 [14:22:15<8:19:34,  1.71it/s]
Train steps ... :  49%|████▉     | 48781/100000 [14:22:15<8:19:12,  1.71it/s]
Train steps ... :  49%|████▉     | 48782/100000 [14:22:16<8:18:39,  1.71it/s]
Train steps ... :  49%|████▉     | 48783/100000 [14:22:17<8:19:23,  1.71it/s]
Train steps ... :  49%|████▉     | 48784/100000 [14:22:17<8:19:10,  1.71it/s]
Train steps ... :  49%|████▉     | 48785/100000 [14:22:18<8:19:18,  1.71it/s]
Train steps ... :  49%|████▉     | 48786/100000 [14:22:18<8:19:11,  1.71it/s]
Train steps ... :  49%|████▉     | 48787/100000 [14:22:19<8:19:34,  1.71it/s]
Train steps ... :  49%|████▉     | 48788/100000 [14:22:20<8:20:02,  1.71it/s]
Train steps ... :  49%|████▉     | 48789/100000 [14:22:20<8:19:52,  1.71it/s]
Train steps ... :  49%|████▉     | 48790/100000 [14:22:21<8:19:12,  1.71it/s]
Train steps ... :  49%|████▉     | 48791/100000 [14:22:21<8:19:43,  1.71it/s]
Train steps ... :  49%|████▉     | 48792/100000 [14:22:22<8:19:05,  1.71it/s]
Train steps ... :  49%|████▉     | 48793/100000 [14:22:22<8:19:12,  1.71it/s]
Train steps ... :  49%|████▉     | 48794/100000 [14:22:23<8:19:55,  1.71it/s]
Train steps ... :  49%|████▉     | 48795/100000 [14:22:24<8:19:26,  1.71it/s]
Train steps ... :  49%|████▉     | 48796/100000 [14:22:24<8:19:58,  1.71it/s]
Train steps ... :  49%|████▉     | 48797/100000 [14:22:25<8:20:42,  1.70it/s]
Train steps ... :  49%|████▉     | 48798/100000 [14:22:25<8:19:57,  1.71it/s]
Train steps ... :  49%|████▉     | 48799/100000 [14:22:26<8:19:23,  1.71it/s]
Train steps ... :  49%|████▉     | 48800/100000 [14:22:27<8:19:42,  1.71it/s]Step... (48800 / 100000 | Loss: 0.6991151571273804, Learning Rate: 5.145728643216081e-05)
+
                                                                             
Step... (48800 / 100000 | Loss: 0.989351749420166, Learning Rate: 5.145728643216081e-05)
+
Train steps ... :  49%|████▉     | 48800/100000 [14:22:27<8:19:42,  1.71it/s]
Train steps ... :  49%|████▉     | 48801/100000 [14:22:27<8:19:35,  1.71it/s]
Train steps ... :  49%|████▉     | 48802/100000 [14:22:28<8:19:23,  1.71it/s]
Train steps ... :  49%|████▉     | 48803/100000 [14:22:28<8:20:01,  1.71it/s]
Train steps ... :  49%|████▉     | 48804/100000 [14:22:29<8:19:21,  1.71it/s]
Train steps ... :  49%|████▉     | 48805/100000 [14:22:30<8:19:20,  1.71it/s]
Train steps ... :  49%|████▉     | 48806/100000 [14:22:30<8:19:14,  1.71it/s]
Train steps ... :  49%|████▉     | 48807/100000 [14:22:31<8:21:09,  1.70it/s]
Train steps ... :  49%|████▉     | 48808/100000 [14:22:31<8:20:30,  1.70it/s]
Train steps ... :  49%|████▉     | 48809/100000 [14:22:32<8:20:31,  1.70it/s]
Train steps ... :  49%|████▉     | 48810/100000 [14:22:32<8:20:56,  1.70it/s]
Train steps ... :  49%|████▉     | 48811/100000 [14:22:33<8:21:38,  1.70it/s]
Train steps ... :  49%|████▉     | 48812/100000 [14:22:34<8:21:39,  1.70it/s]
Train steps ... :  49%|████▉     | 48813/100000 [14:22:34<8:20:55,  1.70it/s]
Train steps ... :  49%|████▉     | 48814/100000 [14:22:35<8:21:06,  1.70it/s]
Train steps ... :  49%|████▉     | 48815/100000 [14:22:35<8:20:27,  1.70it/s]
Train steps ... :  49%|████▉     | 48816/100000 [14:22:36<8:20:37,  1.70it/s]
Train steps ... :  49%|████▉     | 48817/100000 [14:22:37<8:19:44,  1.71it/s]
Train steps ... :  49%|████▉     | 48818/100000 [14:22:37<8:19:18,  1.71it/s]
Train steps ... :  49%|████▉     | 48819/100000 [14:22:38<8:19:38,  1.71it/s]
Train steps ... :  49%|████▉     | 48820/100000 [14:22:38<8:19:34,  1.71it/s]
Train steps ... :  49%|████▉     | 48821/100000 [14:22:39<8:19:33,  1.71it/s]
Train steps ... :  49%|████▉     | 48822/100000 [14:22:40<8:20:17,  1.70it/s]
Train steps ... :  49%|████▉     | 48823/100000 [14:22:40<8:19:40,  1.71it/s]
Train steps ... :  49%|████▉     | 48824/100000 [14:22:41<8:19:12,  1.71it/s]
Train steps ... :  49%|████▉     | 48825/100000 [14:22:41<8:19:51,  1.71it/s]Step... (48825 / 100000 | Loss: 0.9739465117454529, Learning Rate: 5.14321608040201e-05)
+
                                                                             
Step... (48825 / 100000 | Loss: 0.6279456615447998, Learning Rate: 5.14321608040201e-05)
+
Train steps ... :  49%|████▉     | 48825/100000 [14:22:42<8:19:51,  1.71it/s]
Train steps ... :  49%|████▉     | 48826/100000 [14:22:42<8:20:09,  1.71it/s]
Train steps ... :  49%|████▉     | 48827/100000 [14:22:42<8:20:27,  1.70it/s]
Train steps ... :  49%|████▉     | 48828/100000 [14:22:43<8:20:12,  1.70it/s]
Train steps ... :  49%|████▉     | 48829/100000 [14:22:44<8:20:17,  1.70it/s]
Train steps ... :  49%|████▉     | 48830/100000 [14:22:44<8:19:57,  1.71it/s]
Train steps ... :  49%|████▉     | 48831/100000 [14:22:45<8:19:51,  1.71it/s]
Train steps ... :  49%|████▉     | 48832/100000 [14:22:45<8:20:00,  1.71it/s]
Train steps ... :  49%|████▉     | 48833/100000 [14:22:46<8:19:52,  1.71it/s]
Train steps ... :  49%|████▉     | 48834/100000 [14:22:47<8:22:17,  1.70it/s]
Train steps ... :  49%|████▉     | 48835/100000 [14:22:47<8:19:49,  1.71it/s]
Train steps ... :  49%|████▉     | 48836/100000 [14:22:48<8:19:27,  1.71it/s]
Train steps ... :  49%|████▉     | 48837/100000 [14:22:48<8:18:42,  1.71it/s]
Train steps ... :  49%|████▉     | 48838/100000 [14:22:49<8:18:38,  1.71it/s]
Train steps ... :  49%|████▉     | 48839/100000 [14:22:49<8:18:24,  1.71it/s]
Train steps ... :  49%|████▉     | 48840/100000 [14:22:50<8:18:53,  1.71it/s]
Train steps ... :  49%|████▉     | 48841/100000 [14:22:51<8:18:36,  1.71it/s]
Train steps ... :  49%|████▉     | 48842/100000 [14:22:51<8:19:42,  1.71it/s]
Train steps ... :  49%|████▉     | 48843/100000 [14:22:52<8:18:55,  1.71it/s]
Train steps ... :  49%|████▉     | 48844/100000 [14:22:52<8:19:01,  1.71it/s]
Train steps ... :  49%|████▉     | 48845/100000 [14:22:53<8:19:46,  1.71it/s]
Train steps ... :  49%|████▉     | 48846/100000 [14:22:54<8:19:19,  1.71it/s]
Train steps ... :  49%|████▉     | 48847/100000 [14:22:54<8:20:29,  1.70it/s]
Train steps ... :  49%|████▉     | 48848/100000 [14:22:55<8:19:32,  1.71it/s]
Train steps ... :  49%|████▉     | 48849/100000 [14:22:55<8:19:18,  1.71it/s]
Train steps ... :  49%|████▉     | 48850/100000 [14:22:56<8:20:43,  1.70it/s]Step... (48850 / 100000 | Loss: 1.0225844383239746, Learning Rate: 5.1407035175879405e-05)
+
                                                                             
Step... (48850 / 100000 | Loss: 0.890571117401123, Learning Rate: 5.1407035175879405e-05)
+
Train steps ... :  49%|████▉     | 48850/100000 [14:22:56<8:20:43,  1.70it/s]
Train steps ... :  49%|████▉     | 48851/100000 [14:22:57<8:21:50,  1.70it/s]
Train steps ... :  49%|████▉     | 48852/100000 [14:22:57<8:21:03,  1.70it/s]
Train steps ... :  49%|████▉     | 48853/100000 [14:22:58<8:20:00,  1.70it/s]
Train steps ... :  49%|████▉     | 48854/100000 [14:22:58<8:20:35,  1.70it/s]
Train steps ... :  49%|████▉     | 48855/100000 [14:22:59<8:19:21,  1.71it/s]
Train steps ... :  49%|████▉     | 48856/100000 [14:22:59<8:19:38,  1.71it/s]
Train steps ... :  49%|████▉     | 48857/100000 [14:23:00<8:19:38,  1.71it/s]
Train steps ... :  49%|████▉     | 48858/100000 [14:23:01<8:19:38,  1.71it/s]
Train steps ... :  49%|████▉     | 48859/100000 [14:23:01<8:19:53,  1.71it/s]
Train steps ... :  49%|████▉     | 48860/100000 [14:23:02<8:19:27,  1.71it/s]
Train steps ... :  49%|████▉     | 48861/100000 [14:23:02<8:20:33,  1.70it/s]
Train steps ... :  49%|████▉     | 48862/100000 [14:23:03<8:21:42,  1.70it/s]
Train steps ... :  49%|████▉     | 48863/100000 [14:23:04<8:22:12,  1.70it/s]
Train steps ... :  49%|████▉     | 48864/100000 [14:23:04<8:21:35,  1.70it/s]
Train steps ... :  49%|████▉     | 48865/100000 [14:23:05<8:20:06,  1.70it/s]
Train steps ... :  49%|████▉     | 48866/100000 [14:23:05<8:19:43,  1.71it/s]
Train steps ... :  49%|████▉     | 48867/100000 [14:23:06<8:19:53,  1.70it/s]
Train steps ... :  49%|████▉     | 48868/100000 [14:23:06<8:19:30,  1.71it/s]
Train steps ... :  49%|████▉     | 48869/100000 [14:23:07<8:19:47,  1.71it/s]
Train steps ... :  49%|████▉     | 48870/100000 [14:23:08<8:19:28,  1.71it/s]
Train steps ... :  49%|████▉     | 48871/100000 [14:23:08<8:19:15,  1.71it/s]
Train steps ... :  49%|████▉     | 48872/100000 [14:23:09<8:19:59,  1.70it/s]
Train steps ... :  49%|████▉     | 48873/100000 [14:23:09<8:19:14,  1.71it/s]
Train steps ... :  49%|████▉     | 48874/100000 [14:23:10<8:18:44,  1.71it/s]
Train steps ... :  49%|████▉     | 48875/100000 [14:23:11<8:19:51,  1.70it/s]Step... (48875 / 100000 | Loss: 0.7025719881057739, Learning Rate: 5.1381909547738695e-05)
+
                                                                             
Step... (48875 / 100000 | Loss: 0.6343509554862976, Learning Rate: 5.1381909547738695e-05)
+
Train steps ... :  49%|████▉     | 48875/100000 [14:23:11<8:19:51,  1.70it/s]
Train steps ... :  49%|████▉     | 48876/100000 [14:23:11<8:20:22,  1.70it/s]
Train steps ... :  49%|████▉     | 48877/100000 [14:23:12<8:20:41,  1.70it/s]
Train steps ... :  49%|████▉     | 48878/100000 [14:23:12<8:20:53,  1.70it/s]
Train steps ... :  49%|████▉     | 48879/100000 [14:23:13<8:19:44,  1.70it/s]
Train steps ... :  49%|████▉     | 48880/100000 [14:23:14<8:20:07,  1.70it/s]
Train steps ... :  49%|████▉     | 48881/100000 [14:23:14<8:19:46,  1.70it/s]
Train steps ... :  49%|████▉     | 48882/100000 [14:23:15<8:19:38,  1.71it/s]
Train steps ... :  49%|████▉     | 48883/100000 [14:23:15<8:19:50,  1.70it/s]
Train steps ... :  49%|████▉     | 48884/100000 [14:23:16<8:19:12,  1.71it/s]
Train steps ... :  49%|████▉     | 48885/100000 [14:23:16<8:19:11,  1.71it/s]
Train steps ... :  49%|████▉     | 48886/100000 [14:23:17<8:18:28,  1.71it/s]
Train steps ... :  49%|████▉     | 48887/100000 [14:23:18<8:18:20,  1.71it/s]
Train steps ... :  49%|████▉     | 48888/100000 [14:23:18<8:18:14,  1.71it/s]
Train steps ... :  49%|████▉     | 48889/100000 [14:23:19<8:18:38,  1.71it/s]
Train steps ... :  49%|████▉     | 48890/100000 [14:23:19<8:19:39,  1.70it/s]
Train steps ... :  49%|████▉     | 48891/100000 [14:23:20<8:19:57,  1.70it/s]
Train steps ... :  49%|████▉     | 48892/100000 [14:23:21<8:19:52,  1.70it/s]
Train steps ... :  49%|████▉     | 48893/100000 [14:23:21<8:19:37,  1.70it/s]
Train steps ... :  49%|████▉     | 48894/100000 [14:23:22<8:19:37,  1.70it/s]
Train steps ... :  49%|████▉     | 48895/100000 [14:23:22<8:19:26,  1.71it/s]
Train steps ... :  49%|████▉     | 48896/100000 [14:23:23<8:18:35,  1.71it/s]
Train steps ... :  49%|████▉     | 48897/100000 [14:23:23<8:18:15,  1.71it/s]
Train steps ... :  49%|████▉     | 48898/100000 [14:23:24<8:18:36,  1.71it/s]
Train steps ... :  49%|████▉     | 48899/100000 [14:23:25<8:18:50,  1.71it/s]
Train steps ... :  49%|████▉     | 48900/100000 [14:23:25<8:19:02,  1.71it/s]Step... (48900 / 100000 | Loss: 0.5826449394226074, Learning Rate: 5.135678391959799e-05)
+
                                                                             
Step... (48900 / 100000 | Loss: 0.7653329968452454, Learning Rate: 5.135678391959799e-05)
+
Train steps ... :  49%|████▉     | 48900/100000 [14:23:26<8:19:02,  1.71it/s]
Train steps ... :  49%|████▉     | 48901/100000 [14:23:26<8:18:35,  1.71it/s]
Train steps ... :  49%|████▉     | 48902/100000 [14:23:26<8:19:17,  1.71it/s]
Train steps ... :  49%|████▉     | 48903/100000 [14:23:27<8:19:05,  1.71it/s]
Train steps ... :  49%|████▉     | 48904/100000 [14:23:28<8:19:14,  1.71it/s]
Train steps ... :  49%|████▉     | 48905/100000 [14:23:28<8:18:27,  1.71it/s]
Train steps ... :  49%|████▉     | 48906/100000 [14:23:29<8:18:27,  1.71it/s]
Train steps ... :  49%|████▉     | 48907/100000 [14:23:29<8:19:18,  1.71it/s]
Train steps ... :  49%|████▉     | 48908/100000 [14:23:30<8:19:05,  1.71it/s]
Train steps ... :  49%|████▉     | 48909/100000 [14:23:31<8:19:11,  1.71it/s]
Train steps ... :  49%|████▉     | 48910/100000 [14:23:31<8:19:21,  1.71it/s]
Train steps ... :  49%|████▉     | 48911/100000 [14:23:32<8:18:53,  1.71it/s]
Train steps ... :  49%|████▉     | 48912/100000 [14:23:32<8:20:13,  1.70it/s]
Train steps ... :  49%|████▉     | 48913/100000 [14:23:33<8:20:15,  1.70it/s]
Train steps ... :  49%|████▉     | 48914/100000 [14:23:33<8:20:52,  1.70it/s]
Train steps ... :  49%|████▉     | 48915/100000 [14:23:34<8:20:11,  1.70it/s]
Train steps ... :  49%|████▉     | 48916/100000 [14:23:35<8:18:28,  1.71it/s]
Train steps ... :  49%|████▉     | 48917/100000 [14:23:35<8:18:04,  1.71it/s]
Train steps ... :  49%|████▉     | 48918/100000 [14:23:36<8:18:19,  1.71it/s]
Train steps ... :  49%|████▉     | 48919/100000 [14:23:36<8:18:32,  1.71it/s]
Train steps ... :  49%|████▉     | 48920/100000 [14:23:37<8:18:16,  1.71it/s]
Train steps ... :  49%|████▉     | 48921/100000 [14:23:38<8:18:15,  1.71it/s]
Train steps ... :  49%|████▉     | 48922/100000 [14:23:38<8:17:50,  1.71it/s]
Train steps ... :  49%|████▉     | 48923/100000 [14:23:39<8:17:34,  1.71it/s]
Train steps ... :  49%|████▉     | 48924/100000 [14:23:39<8:17:53,  1.71it/s]
Train steps ... :  49%|████▉     | 48925/100000 [14:23:40<8:18:03,  1.71it/s]Step... (48925 / 100000 | Loss: 0.7878304123878479, Learning Rate: 5.133165829145729e-05)
+
                                                                             
Step... (48925 / 100000 | Loss: 0.6592094302177429, Learning Rate: 5.133165829145729e-05)
+
Train steps ... :  49%|████▉     | 48925/100000 [14:23:40<8:18:03,  1.71it/s]
Train steps ... :  49%|████▉     | 48926/100000 [14:23:40<8:18:59,  1.71it/s]
Train steps ... :  49%|████▉     | 48927/100000 [14:23:41<8:19:18,  1.70it/s]
Train steps ... :  49%|████▉     | 48928/100000 [14:23:42<8:20:31,  1.70it/s]
Train steps ... :  49%|████▉     | 48929/100000 [14:23:42<8:18:38,  1.71it/s]
Train steps ... :  49%|████▉     | 48930/100000 [14:23:43<8:18:21,  1.71it/s]
Train steps ... :  49%|████▉     | 48931/100000 [14:23:43<8:18:41,  1.71it/s]
Train steps ... :  49%|████▉     | 48932/100000 [14:23:44<8:18:52,  1.71it/s]
Train steps ... :  49%|████▉     | 48933/100000 [14:23:45<8:18:45,  1.71it/s]
Train steps ... :  49%|████▉     | 48934/100000 [14:23:45<8:18:29,  1.71it/s]
Train steps ... :  49%|████▉     | 48935/100000 [14:23:46<8:18:45,  1.71it/s]
Train steps ... :  49%|████▉     | 48936/100000 [14:23:46<8:20:49,  1.70it/s]
Train steps ... :  49%|████▉     | 48937/100000 [14:23:47<8:19:08,  1.71it/s]
Train steps ... :  49%|████▉     | 48938/100000 [14:23:48<8:18:26,  1.71it/s]
Train steps ... :  49%|████▉     | 48939/100000 [14:23:48<8:18:10,  1.71it/s]
Train steps ... :  49%|████▉     | 48940/100000 [14:23:49<8:17:48,  1.71it/s]
Train steps ... :  49%|████▉     | 48941/100000 [14:23:49<8:17:23,  1.71it/s]
Train steps ... :  49%|████▉     | 48942/100000 [14:23:50<8:17:16,  1.71it/s]
Train steps ... :  49%|████▉     | 48943/100000 [14:23:50<8:17:41,  1.71it/s]
Train steps ... :  49%|████▉     | 48944/100000 [14:23:51<8:17:31,  1.71it/s]
Train steps ... :  49%|████▉     | 48945/100000 [14:23:52<8:17:56,  1.71it/s]
Train steps ... :  49%|████▉     | 48946/100000 [14:23:52<8:17:42,  1.71it/s]
Train steps ... :  49%|████▉     | 48947/100000 [14:23:53<8:18:28,  1.71it/s]
Train steps ... :  49%|████▉     | 48948/100000 [14:23:53<8:18:23,  1.71it/s]
Train steps ... :  49%|████▉     | 48949/100000 [14:23:54<8:18:17,  1.71it/s]
Train steps ... :  49%|████▉     | 48950/100000 [14:23:55<8:18:27,  1.71it/s]Step... (48950 / 100000 | Loss: 0.5748029947280884, Learning Rate: 5.1306532663316585e-05)
+
                                                                             
Step... (48950 / 100000 | Loss: 0.7248187065124512, Learning Rate: 5.1306532663316585e-05)
+
Train steps ... :  49%|████▉     | 48950/100000 [14:23:55<8:18:27,  1.71it/s]
Train steps ... :  49%|████▉     | 48951/100000 [14:23:55<8:18:52,  1.71it/s]
Train steps ... :  49%|████▉     | 48952/100000 [14:23:56<8:18:22,  1.71it/s]
Train steps ... :  49%|████▉     | 48953/100000 [14:23:56<8:17:46,  1.71it/s]
Train steps ... :  49%|████▉     | 48954/100000 [14:23:57<8:18:54,  1.71it/s]
Train steps ... :  49%|████▉     | 48955/100000 [14:23:57<8:19:03,  1.70it/s]
Train steps ... :  49%|████▉     | 48956/100000 [14:23:58<8:18:44,  1.71it/s]
Train steps ... :  49%|████▉     | 48957/100000 [14:23:59<8:18:53,  1.71it/s]
Train steps ... :  49%|████▉     | 48958/100000 [14:23:59<8:18:21,  1.71it/s]
Train steps ... :  49%|████▉     | 48959/100000 [14:24:00<8:18:26,  1.71it/s]
Train steps ... :  49%|████▉     | 48960/100000 [14:24:00<8:18:11,  1.71it/s]
Train steps ... :  49%|████▉     | 48961/100000 [14:24:01<8:18:10,  1.71it/s]
Train steps ... :  49%|████▉     | 48962/100000 [14:24:02<8:17:44,  1.71it/s]
Train steps ... :  49%|████▉     | 48963/100000 [14:24:02<8:17:44,  1.71it/s]
Train steps ... :  49%|████▉     | 48964/100000 [14:24:03<8:19:15,  1.70it/s]
Train steps ... :  49%|████▉     | 48965/100000 [14:24:03<8:17:58,  1.71it/s]
Train steps ... :  49%|████▉     | 48966/100000 [14:24:04<8:17:38,  1.71it/s]
Train steps ... :  49%|████▉     | 48967/100000 [14:24:04<8:17:36,  1.71it/s]
Train steps ... :  49%|████▉     | 48968/100000 [14:24:05<8:17:20,  1.71it/s]
Train steps ... :  49%|████▉     | 48969/100000 [14:24:06<8:18:21,  1.71it/s]
Train steps ... :  49%|████▉     | 48970/100000 [14:24:06<8:18:16,  1.71it/s]
Train steps ... :  49%|████▉     | 48971/100000 [14:24:07<8:17:24,  1.71it/s]
Train steps ... :  49%|████▉     | 48972/100000 [14:24:07<8:17:16,  1.71it/s]
Train steps ... :  49%|████▉     | 48973/100000 [14:24:08<8:17:38,  1.71it/s]
Train steps ... :  49%|████▉     | 48974/100000 [14:24:09<8:17:43,  1.71it/s]
Train steps ... :  49%|████▉     | 48975/100000 [14:24:09<8:18:07,  1.71it/s]Step... (48975 / 100000 | Loss: 0.7446731328964233, Learning Rate: 5.1281407035175875e-05)
+
                                                                             
Step... (48975 / 100000 | Loss: 0.8923284411430359, Learning Rate: 5.1281407035175875e-05)
+
Train steps ... :  49%|████▉     | 48975/100000 [14:24:09<8:18:07,  1.71it/s]
Train steps ... :  49%|████▉     | 48976/100000 [14:24:10<8:17:46,  1.71it/s]
Train steps ... :  49%|████▉     | 48977/100000 [14:24:10<8:17:50,  1.71it/s]
Train steps ... :  49%|████▉     | 48978/100000 [14:24:11<8:16:52,  1.71it/s]
Train steps ... :  49%|████▉     | 48979/100000 [14:24:12<8:17:04,  1.71it/s]
Train steps ... :  49%|████▉     | 48980/100000 [14:24:12<8:16:53,  1.71it/s]
Train steps ... :  49%|████▉     | 48981/100000 [14:24:13<8:16:28,  1.71it/s]
Train steps ... :  49%|████▉     | 48982/100000 [14:24:13<8:16:43,  1.71it/s]
Train steps ... :  49%|████▉     | 48983/100000 [14:24:14<8:17:18,  1.71it/s]
Train steps ... :  49%|████▉     | 48984/100000 [14:24:14<8:17:11,  1.71it/s]
Train steps ... :  49%|████▉     | 48985/100000 [14:24:15<8:18:17,  1.71it/s]
Train steps ... :  49%|████▉     | 48986/100000 [14:24:16<8:18:25,  1.71it/s]
Train steps ... :  49%|████▉     | 48987/100000 [14:24:16<8:17:11,  1.71it/s]
Train steps ... :  49%|████▉     | 48988/100000 [14:24:17<8:17:18,  1.71it/s]
Train steps ... :  49%|████▉     | 48989/100000 [14:24:17<8:16:40,  1.71it/s]
Train steps ... :  49%|████▉     | 48990/100000 [14:24:18<8:16:56,  1.71it/s]
Train steps ... :  49%|████▉     | 48991/100000 [14:24:19<8:16:45,  1.71it/s]
Train steps ... :  49%|████▉     | 48992/100000 [14:24:19<8:18:53,  1.70it/s]
Train steps ... :  49%|████▉     | 48993/100000 [14:24:20<8:19:23,  1.70it/s]
Train steps ... :  49%|████▉     | 48994/100000 [14:24:20<8:18:27,  1.71it/s]
Train steps ... :  49%|████▉     | 48995/100000 [14:24:21<8:17:43,  1.71it/s]
Train steps ... :  49%|████▉     | 48996/100000 [14:24:21<8:18:48,  1.70it/s]
Train steps ... :  49%|████▉     | 48997/100000 [14:24:22<8:18:22,  1.71it/s]
Train steps ... :  49%|████▉     | 48998/100000 [14:24:23<8:17:55,  1.71it/s]
Train steps ... :  49%|████▉     | 48999/100000 [14:24:23<8:18:26,  1.71it/s]
Train steps ... :  49%|████▉     | 49000/100000 [14:24:24<8:18:52,  1.70it/s]Step... (49000 / 100000 | Loss: 0.5379605293273926, Learning Rate: 5.125628140703518e-05)
+
                                                                             
Step... (49000 / 100000 | Loss: 0.8901501893997192, Learning Rate: 5.125628140703518e-05)
+
Train steps ... :  49%|████▉     | 49000/100000 [14:24:24<8:18:52,  1.70it/s]
Train steps ... :  49%|████▉     | 49001/100000 [14:24:24<8:18:58,  1.70it/s]
Train steps ... :  49%|████▉     | 49002/100000 [14:24:25<8:18:27,  1.71it/s]
Train steps ... :  49%|████▉     | 49003/100000 [14:24:26<8:20:00,  1.70it/s]
Train steps ... :  49%|████▉     | 49004/100000 [14:24:26<8:21:10,  1.70it/s]
Train steps ... :  49%|████▉     | 49005/100000 [14:24:27<8:19:31,  1.70it/s]
Train steps ... :  49%|████▉     | 49006/100000 [14:24:27<8:18:26,  1.71it/s]
Train steps ... :  49%|████▉     | 49007/100000 [14:24:28<8:18:33,  1.70it/s]
Train steps ... :  49%|████▉     | 49008/100000 [14:24:29<8:17:57,  1.71it/s]
Train steps ... :  49%|████▉     | 49009/100000 [14:24:29<8:18:12,  1.71it/s]
Train steps ... :  49%|████▉     | 49010/100000 [14:24:30<8:17:40,  1.71it/s]
Train steps ... :  49%|████▉     | 49011/100000 [14:24:30<8:17:34,  1.71it/s]
Train steps ... :  49%|████▉     | 49012/100000 [14:24:31<8:17:02,  1.71it/s]
Train steps ... :  49%|████▉     | 49013/100000 [14:24:31<8:16:47,  1.71it/s]
Train steps ... :  49%|████▉     | 49014/100000 [14:24:32<8:16:50,  1.71it/s]
Train steps ... :  49%|████▉     | 49015/100000 [14:24:33<8:17:25,  1.71it/s]
Train steps ... :  49%|████▉     | 49016/100000 [14:24:33<8:16:49,  1.71it/s]
Train steps ... :  49%|████▉     | 49017/100000 [14:24:34<8:17:43,  1.71it/s]
Train steps ... :  49%|████▉     | 49018/100000 [14:24:34<8:18:02,  1.71it/s]
Train steps ... :  49%|████▉     | 49019/100000 [14:24:35<8:17:42,  1.71it/s]
Train steps ... :  49%|████▉     | 49020/100000 [14:24:36<8:17:46,  1.71it/s]
Train steps ... :  49%|████▉     | 49021/100000 [14:24:36<8:17:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49022/100000 [14:24:37<8:18:03,  1.71it/s]
Train steps ... :  49%|████▉     | 49023/100000 [14:24:37<8:18:04,  1.71it/s]
Train steps ... :  49%|████▉     | 49024/100000 [14:24:38<8:18:53,  1.70it/s]
Train steps ... :  49%|████▉     | 49025/100000 [14:24:38<8:17:59,  1.71it/s]Step... (49025 / 100000 | Loss: 0.6232912540435791, Learning Rate: 5.123115577889448e-05)
+
                                                                             
Step... (49025 / 100000 | Loss: 1.0154913663864136, Learning Rate: 5.123115577889448e-05)
+
Train steps ... :  49%|████▉     | 49025/100000 [14:24:39<8:17:59,  1.71it/s]
Train steps ... :  49%|████▉     | 49026/100000 [14:24:39<8:17:15,  1.71it/s]
Train steps ... :  49%|████▉     | 49027/100000 [14:24:40<8:17:07,  1.71it/s]
Train steps ... :  49%|████▉     | 49028/100000 [14:24:40<8:16:42,  1.71it/s]
Train steps ... :  49%|████▉     | 49029/100000 [14:24:41<8:16:27,  1.71it/s]
Train steps ... :  49%|████▉     | 49030/100000 [14:24:41<8:17:42,  1.71it/s]
Train steps ... :  49%|████▉     | 49031/100000 [14:24:42<8:17:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49032/100000 [14:24:43<8:17:22,  1.71it/s]
Train steps ... :  49%|████▉     | 49033/100000 [14:24:43<8:17:59,  1.71it/s]
Train steps ... :  49%|████▉     | 49034/100000 [14:24:44<8:18:24,  1.70it/s]
Train steps ... :  49%|████▉     | 49035/100000 [14:24:44<8:18:39,  1.70it/s]
Train steps ... :  49%|████▉     | 49036/100000 [14:24:45<8:19:52,  1.70it/s]
Train steps ... :  49%|████▉     | 49037/100000 [14:24:45<8:17:32,  1.71it/s]
Train steps ... :  49%|████▉     | 49038/100000 [14:24:46<8:19:16,  1.70it/s]
Train steps ... :  49%|████▉     | 49039/100000 [14:24:47<8:19:35,  1.70it/s]
Train steps ... :  49%|████▉     | 49040/100000 [14:24:47<8:17:43,  1.71it/s]
Train steps ... :  49%|████▉     | 49041/100000 [14:24:48<8:18:16,  1.70it/s]
Train steps ... :  49%|████▉     | 49042/100000 [14:24:48<8:19:13,  1.70it/s]
Train steps ... :  49%|████▉     | 49043/100000 [14:24:49<8:17:48,  1.71it/s]
Train steps ... :  49%|████▉     | 49044/100000 [14:24:50<8:17:24,  1.71it/s]
Train steps ... :  49%|████▉     | 49045/100000 [14:24:50<8:18:02,  1.71it/s]
Train steps ... :  49%|████▉     | 49046/100000 [14:24:51<8:16:19,  1.71it/s]
Train steps ... :  49%|████▉     | 49047/100000 [14:24:51<8:17:19,  1.71it/s]
Train steps ... :  49%|████▉     | 49048/100000 [14:24:52<8:16:36,  1.71it/s]
Train steps ... :  49%|████▉     | 49049/100000 [14:24:53<8:18:07,  1.70it/s]
Train steps ... :  49%|████▉     | 49050/100000 [14:24:53<8:18:55,  1.70it/s]Step... (49050 / 100000 | Loss: 1.0785696506500244, Learning Rate: 5.120603015075377e-05)
+
                                                                             
Step... (49050 / 100000 | Loss: 0.7475906610488892, Learning Rate: 5.120603015075377e-05)
+
Train steps ... :  49%|████▉     | 49050/100000 [14:24:53<8:18:55,  1.70it/s]
Train steps ... :  49%|████▉     | 49051/100000 [14:24:54<8:17:32,  1.71it/s]
Train steps ... :  49%|████▉     | 49052/100000 [14:24:54<8:19:00,  1.70it/s]
Train steps ... :  49%|████▉     | 49053/100000 [14:24:55<8:18:18,  1.70it/s]
Train steps ... :  49%|████▉     | 49054/100000 [14:24:55<8:18:13,  1.70it/s]
Train steps ... :  49%|████▉     | 49055/100000 [14:24:56<8:17:34,  1.71it/s]
Train steps ... :  49%|████▉     | 49056/100000 [14:24:57<8:19:21,  1.70it/s]
Train steps ... :  49%|████▉     | 49057/100000 [14:24:57<8:17:35,  1.71it/s]
Train steps ... :  49%|████▉     | 49058/100000 [14:24:58<8:17:24,  1.71it/s]
Train steps ... :  49%|████▉     | 49059/100000 [14:24:58<8:18:25,  1.70it/s]
Train steps ... :  49%|████▉     | 49060/100000 [14:24:59<8:16:47,  1.71it/s]
Train steps ... :  49%|████▉     | 49061/100000 [14:25:00<8:19:01,  1.70it/s]
Train steps ... :  49%|████▉     | 49062/100000 [14:25:00<8:18:14,  1.70it/s]
Train steps ... :  49%|████▉     | 49063/100000 [14:25:01<8:17:31,  1.71it/s]
Train steps ... :  49%|████▉     | 49064/100000 [14:25:01<8:16:44,  1.71it/s]
Train steps ... :  49%|████▉     | 49065/100000 [14:25:02<8:17:24,  1.71it/s]
Train steps ... :  49%|████▉     | 49066/100000 [14:25:02<8:17:11,  1.71it/s]
Train steps ... :  49%|████▉     | 49067/100000 [14:25:03<8:17:14,  1.71it/s]
Train steps ... :  49%|████▉     | 49068/100000 [14:25:04<8:17:35,  1.71it/s]
Train steps ... :  49%|████▉     | 49069/100000 [14:25:04<8:17:38,  1.71it/s]
Train steps ... :  49%|████▉     | 49070/100000 [14:25:05<8:17:20,  1.71it/s]
Train steps ... :  49%|████▉     | 49071/100000 [14:25:05<8:16:29,  1.71it/s]
Train steps ... :  49%|████▉     | 49072/100000 [14:25:06<8:16:30,  1.71it/s]
Train steps ... :  49%|████▉     | 49073/100000 [14:25:07<8:17:13,  1.71it/s]
Train steps ... :  49%|████▉     | 49074/100000 [14:25:07<8:16:17,  1.71it/s]
Train steps ... :  49%|████▉     | 49075/100000 [14:25:08<8:16:28,  1.71it/s]Step... (49075 / 100000 | Loss: 0.6522468328475952, Learning Rate: 5.118090452261307e-05)
+
                                                                             
Step... (49075 / 100000 | Loss: 0.6703950762748718, Learning Rate: 5.118090452261307e-05)
+
Train steps ... :  49%|████▉     | 49075/100000 [14:25:08<8:16:28,  1.71it/s]
Train steps ... :  49%|████▉     | 49076/100000 [14:25:08<8:16:13,  1.71it/s]
Train steps ... :  49%|████▉     | 49077/100000 [14:25:09<8:16:15,  1.71it/s]
Train steps ... :  49%|████▉     | 49078/100000 [14:25:10<8:15:58,  1.71it/s]
Train steps ... :  49%|████▉     | 49079/100000 [14:25:10<8:16:03,  1.71it/s]
Train steps ... :  49%|████▉     | 49080/100000 [14:25:11<8:16:25,  1.71it/s]
Train steps ... :  49%|████▉     | 49081/100000 [14:25:11<8:16:25,  1.71it/s]
Train steps ... :  49%|████▉     | 49082/100000 [14:25:12<8:18:03,  1.70it/s]
Train steps ... :  49%|████▉     | 49083/100000 [14:25:12<8:17:40,  1.71it/s]
Train steps ... :  49%|████▉     | 49084/100000 [14:25:13<8:18:28,  1.70it/s]
Train steps ... :  49%|████▉     | 49085/100000 [14:25:14<8:17:25,  1.71it/s]
Train steps ... :  49%|████▉     | 49086/100000 [14:25:14<8:17:14,  1.71it/s]
Train steps ... :  49%|████▉     | 49087/100000 [14:25:15<8:16:34,  1.71it/s]
Train steps ... :  49%|████▉     | 49088/100000 [14:25:15<8:16:13,  1.71it/s]
Train steps ... :  49%|████▉     | 49089/100000 [14:25:16<8:17:03,  1.71it/s]
Train steps ... :  49%|████▉     | 49090/100000 [14:25:17<8:17:34,  1.71it/s]
Train steps ... :  49%|████▉     | 49091/100000 [14:25:17<8:16:42,  1.71it/s]
Train steps ... :  49%|████▉     | 49092/100000 [14:25:18<8:16:06,  1.71it/s]
Train steps ... :  49%|████▉     | 49093/100000 [14:25:18<8:16:30,  1.71it/s]
Train steps ... :  49%|████▉     | 49094/100000 [14:25:19<8:15:41,  1.71it/s]
Train steps ... :  49%|████▉     | 49095/100000 [14:25:19<8:15:46,  1.71it/s]
Train steps ... :  49%|████▉     | 49096/100000 [14:25:20<8:16:18,  1.71it/s]
Train steps ... :  49%|████▉     | 49097/100000 [14:25:21<8:16:01,  1.71it/s]
Train steps ... :  49%|████▉     | 49098/100000 [14:25:21<8:16:20,  1.71it/s]
Train steps ... :  49%|████▉     | 49099/100000 [14:25:22<8:16:23,  1.71it/s]
Train steps ... :  49%|████▉     | 49100/100000 [14:25:22<8:17:12,  1.71it/s]Step... (49100 / 100000 | Loss: 0.7320090532302856, Learning Rate: 5.1155778894472365e-05)
+
                                                                             
Step... (49100 / 100000 | Loss: 1.109973669052124, Learning Rate: 5.1155778894472365e-05)
+
Train steps ... :  49%|████▉     | 49100/100000 [14:25:23<8:17:12,  1.71it/s]
Train steps ... :  49%|████▉     | 49101/100000 [14:25:23<8:17:17,  1.71it/s]
Train steps ... :  49%|████▉     | 49102/100000 [14:25:24<8:17:41,  1.70it/s]
Train steps ... :  49%|████▉     | 49103/100000 [14:25:24<8:16:32,  1.71it/s]
Train steps ... :  49%|████▉     | 49104/100000 [14:25:25<8:17:28,  1.71it/s]
Train steps ... :  49%|████▉     | 49105/100000 [14:25:25<8:16:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49106/100000 [14:25:26<8:17:15,  1.71it/s]
Train steps ... :  49%|████▉     | 49107/100000 [14:25:27<8:16:56,  1.71it/s]
Train steps ... :  49%|████▉     | 49108/100000 [14:25:27<8:16:14,  1.71it/s]
Train steps ... :  49%|████▉     | 49109/100000 [14:25:28<8:16:49,  1.71it/s]
Train steps ... :  49%|████▉     | 49110/100000 [14:25:28<8:15:28,  1.71it/s]
Train steps ... :  49%|████▉     | 49111/100000 [14:25:29<8:17:35,  1.70it/s]
Train steps ... :  49%|████▉     | 49112/100000 [14:25:29<8:16:40,  1.71it/s]
Train steps ... :  49%|████▉     | 49113/100000 [14:25:30<8:16:20,  1.71it/s]
Train steps ... :  49%|████▉     | 49114/100000 [14:25:31<8:16:30,  1.71it/s]
Train steps ... :  49%|████▉     | 49115/100000 [14:25:31<8:17:57,  1.70it/s]
Train steps ... :  49%|████▉     | 49116/100000 [14:25:32<8:15:49,  1.71it/s]
Train steps ... :  49%|████▉     | 49117/100000 [14:25:32<8:16:28,  1.71it/s]
Train steps ... :  49%|████▉     | 49118/100000 [14:25:33<8:16:40,  1.71it/s]
Train steps ... :  49%|████▉     | 49119/100000 [14:25:34<8:17:36,  1.70it/s]
Train steps ... :  49%|████▉     | 49120/100000 [14:25:34<8:16:48,  1.71it/s]
Train steps ... :  49%|████▉     | 49121/100000 [14:25:35<8:16:09,  1.71it/s]
Train steps ... :  49%|████▉     | 49122/100000 [14:25:35<8:17:14,  1.71it/s]
Train steps ... :  49%|████▉     | 49123/100000 [14:25:36<8:16:31,  1.71it/s]
Train steps ... :  49%|████▉     | 49124/100000 [14:25:36<8:16:30,  1.71it/s]
Train steps ... :  49%|████▉     | 49125/100000 [14:25:37<8:16:10,  1.71it/s]Step... (49125 / 100000 | Loss: 0.7639655470848083, Learning Rate: 5.113065326633166e-05)
+
                                                                             
Step... (49125 / 100000 | Loss: 0.792054295539856, Learning Rate: 5.113065326633166e-05)
+
Train steps ... :  49%|████▉     | 49125/100000 [14:25:37<8:16:10,  1.71it/s]
Train steps ... :  49%|████▉     | 49126/100000 [14:25:38<8:15:58,  1.71it/s]
Train steps ... :  49%|████▉     | 49127/100000 [14:25:38<8:16:15,  1.71it/s]
Train steps ... :  49%|████▉     | 49128/100000 [14:25:39<8:16:29,  1.71it/s]
Train steps ... :  49%|████▉     | 49129/100000 [14:25:39<8:16:15,  1.71it/s]
Train steps ... :  49%|████▉     | 49130/100000 [14:25:40<8:17:16,  1.70it/s]
Train steps ... :  49%|████▉     | 49131/100000 [14:25:41<8:16:40,  1.71it/s]
Train steps ... :  49%|████▉     | 49132/100000 [14:25:41<8:16:13,  1.71it/s]
Train steps ... :  49%|████▉     | 49133/100000 [14:25:42<8:16:00,  1.71it/s]
Train steps ... :  49%|████▉     | 49134/100000 [14:25:42<8:16:17,  1.71it/s]
Train steps ... :  49%|████▉     | 49135/100000 [14:25:43<8:16:06,  1.71it/s]
Train steps ... :  49%|████▉     | 49136/100000 [14:25:43<8:16:27,  1.71it/s]
Train steps ... :  49%|████▉     | 49137/100000 [14:25:44<8:16:46,  1.71it/s]
Train steps ... :  49%|████▉     | 49138/100000 [14:25:45<8:16:13,  1.71it/s]
Train steps ... :  49%|████▉     | 49139/100000 [14:25:45<8:16:08,  1.71it/s]
Train steps ... :  49%|████▉     | 49140/100000 [14:25:46<8:17:45,  1.70it/s]
Train steps ... :  49%|████▉     | 49141/100000 [14:25:46<8:17:00,  1.71it/s]
Train steps ... :  49%|████▉     | 49142/100000 [14:25:47<8:16:38,  1.71it/s]
Train steps ... :  49%|████▉     | 49143/100000 [14:25:48<8:17:50,  1.70it/s]
Train steps ... :  49%|████▉     | 49144/100000 [14:25:48<8:16:27,  1.71it/s]
Train steps ... :  49%|████▉     | 49145/100000 [14:25:49<8:15:41,  1.71it/s]
Train steps ... :  49%|████▉     | 49146/100000 [14:25:49<8:15:29,  1.71it/s]
Train steps ... :  49%|████▉     | 49147/100000 [14:25:50<8:15:24,  1.71it/s]
Train steps ... :  49%|████▉     | 49148/100000 [14:25:51<8:16:23,  1.71it/s]
Train steps ... :  49%|████▉     | 49149/100000 [14:25:51<8:16:08,  1.71it/s]
Train steps ... :  49%|████▉     | 49150/100000 [14:25:52<8:16:40,  1.71it/s]Step... (49150 / 100000 | Loss: 0.6552569270133972, Learning Rate: 5.110552763819095e-05)
+
                                                                             
Step... (49150 / 100000 | Loss: 0.7713041305541992, Learning Rate: 5.110552763819095e-05)
+
Train steps ... :  49%|████▉     | 49150/100000 [14:25:52<8:16:40,  1.71it/s]
Train steps ... :  49%|████▉     | 49151/100000 [14:25:52<8:17:01,  1.71it/s]
Train steps ... :  49%|████▉     | 49152/100000 [14:25:53<8:16:27,  1.71it/s]
Train steps ... :  49%|████▉     | 49153/100000 [14:25:53<8:16:06,  1.71it/s]
Train steps ... :  49%|████▉     | 49154/100000 [14:25:54<8:16:17,  1.71it/s]
Train steps ... :  49%|████▉     | 49155/100000 [14:25:55<8:17:51,  1.70it/s]
Train steps ... :  49%|████▉     | 49156/100000 [14:25:55<8:16:22,  1.71it/s]
Train steps ... :  49%|████▉     | 49157/100000 [14:25:56<8:16:39,  1.71it/s]
Train steps ... :  49%|████▉     | 49158/100000 [14:25:56<8:17:22,  1.70it/s]
Train steps ... :  49%|████▉     | 49159/100000 [14:25:57<8:16:32,  1.71it/s]
Train steps ... :  49%|████▉     | 49160/100000 [14:25:58<8:15:59,  1.71it/s]
Train steps ... :  49%|████▉     | 49161/100000 [14:25:58<8:16:02,  1.71it/s]
Train steps ... :  49%|████▉     | 49162/100000 [14:25:59<8:15:50,  1.71it/s]
Train steps ... :  49%|████▉     | 49163/100000 [14:25:59<8:15:49,  1.71it/s]
Train steps ... :  49%|████▉     | 49164/100000 [14:26:00<8:16:12,  1.71it/s]
Train steps ... :  49%|████▉     | 49165/100000 [14:26:00<8:15:19,  1.71it/s]
Train steps ... :  49%|████▉     | 49166/100000 [14:26:01<8:15:34,  1.71it/s]
Train steps ... :  49%|████▉     | 49167/100000 [14:26:02<8:15:02,  1.71it/s]
Train steps ... :  49%|████▉     | 49168/100000 [14:26:02<8:15:14,  1.71it/s]
Train steps ... :  49%|████▉     | 49169/100000 [14:26:03<8:16:03,  1.71it/s]
Train steps ... :  49%|████▉     | 49170/100000 [14:26:03<8:16:20,  1.71it/s]
Train steps ... :  49%|████▉     | 49171/100000 [14:26:04<8:16:37,  1.71it/s]
Train steps ... :  49%|████▉     | 49172/100000 [14:26:05<8:15:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49173/100000 [14:26:05<8:16:10,  1.71it/s]
Train steps ... :  49%|████▉     | 49174/100000 [14:26:06<8:17:13,  1.70it/s]
Train steps ... :  49%|████▉     | 49175/100000 [14:26:06<8:16:08,  1.71it/s]Step... (49175 / 100000 | Loss: 0.7682570219039917, Learning Rate: 5.1080402010050254e-05)
+
                                                                             
Step... (49175 / 100000 | Loss: 0.6842295527458191, Learning Rate: 5.1080402010050254e-05)
+
Train steps ... :  49%|████▉     | 49175/100000 [14:26:07<8:16:08,  1.71it/s]
Train steps ... :  49%|████▉     | 49176/100000 [14:26:07<8:16:46,  1.71it/s]
Train steps ... :  49%|████▉     | 49177/100000 [14:26:07<8:15:29,  1.71it/s]
Train steps ... :  49%|████▉     | 49178/100000 [14:26:08<8:15:26,  1.71it/s]
Train steps ... :  49%|████▉     | 49179/100000 [14:26:09<8:15:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49180/100000 [14:26:09<8:15:38,  1.71it/s]
Train steps ... :  49%|████▉     | 49181/100000 [14:26:10<8:15:54,  1.71it/s]
Train steps ... :  49%|████▉     | 49182/100000 [14:26:10<8:15:02,  1.71it/s]
Train steps ... :  49%|████▉     | 49183/100000 [14:26:11<8:16:14,  1.71it/s]
Train steps ... :  49%|████▉     | 49184/100000 [14:26:12<8:17:17,  1.70it/s]
Train steps ... :  49%|████▉     | 49185/100000 [14:26:12<8:16:35,  1.71it/s]
Train steps ... :  49%|████▉     | 49186/100000 [14:26:13<8:15:36,  1.71it/s]
Train steps ... :  49%|████▉     | 49187/100000 [14:26:13<8:15:42,  1.71it/s]
Train steps ... :  49%|████▉     | 49188/100000 [14:26:14<8:16:59,  1.70it/s]
Train steps ... :  49%|████▉     | 49189/100000 [14:26:15<8:17:00,  1.70it/s]
Train steps ... :  49%|████▉     | 49190/100000 [14:26:15<8:16:57,  1.70it/s]
Train steps ... :  49%|████▉     | 49191/100000 [14:26:16<8:17:16,  1.70it/s]
Train steps ... :  49%|████▉     | 49192/100000 [14:26:16<8:16:39,  1.70it/s]
Train steps ... :  49%|████▉     | 49193/100000 [14:26:17<8:16:54,  1.70it/s]
Train steps ... :  49%|████▉     | 49194/100000 [14:26:17<8:16:48,  1.70it/s]
Train steps ... :  49%|████▉     | 49195/100000 [14:26:18<8:17:14,  1.70it/s]
Train steps ... :  49%|████▉     | 49196/100000 [14:26:19<8:17:31,  1.70it/s]
Train steps ... :  49%|████▉     | 49197/100000 [14:26:19<8:15:27,  1.71it/s]
Train steps ... :  49%|████▉     | 49198/100000 [14:26:20<8:15:47,  1.71it/s]
Train steps ... :  49%|████▉     | 49199/100000 [14:26:20<8:16:18,  1.71it/s]
Train steps ... :  49%|████▉     | 49200/100000 [14:26:21<8:15:43,  1.71it/s]Step... (49200 / 100000 | Loss: 0.8960851430892944, Learning Rate: 5.1055276381909544e-05)
+
                                                                             
Step... (49200 / 100000 | Loss: 1.021690011024475, Learning Rate: 5.1055276381909544e-05)
+
Train steps ... :  49%|████▉     | 49200/100000 [14:26:21<8:15:43,  1.71it/s]
Train steps ... :  49%|████▉     | 49201/100000 [14:26:22<8:15:09,  1.71it/s]
Train steps ... :  49%|████▉     | 49202/100000 [14:26:22<8:15:18,  1.71it/s]
Train steps ... :  49%|████▉     | 49203/100000 [14:26:23<8:15:54,  1.71it/s]
Train steps ... :  49%|████▉     | 49204/100000 [14:26:23<8:15:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49205/100000 [14:26:24<8:16:29,  1.71it/s]
Train steps ... :  49%|████▉     | 49206/100000 [14:26:24<8:15:44,  1.71it/s]
Train steps ... :  49%|████▉     | 49207/100000 [14:26:25<8:15:29,  1.71it/s]
Train steps ... :  49%|████▉     | 49208/100000 [14:26:26<8:15:48,  1.71it/s]
Train steps ... :  49%|████▉     | 49209/100000 [14:26:26<8:15:54,  1.71it/s]
Train steps ... :  49%|████▉     | 49210/100000 [14:26:27<8:16:44,  1.70it/s]
Train steps ... :  49%|████▉     | 49211/100000 [14:26:27<8:16:22,  1.71it/s]
Train steps ... :  49%|████▉     | 49212/100000 [14:26:28<8:15:21,  1.71it/s]
Train steps ... :  49%|████▉     | 49213/100000 [14:26:29<8:16:14,  1.71it/s]
Train steps ... :  49%|████▉     | 49214/100000 [14:26:29<8:14:39,  1.71it/s]
Train steps ... :  49%|████▉     | 49215/100000 [14:26:30<8:16:26,  1.70it/s]
Train steps ... :  49%|████▉     | 49216/100000 [14:26:30<8:15:47,  1.71it/s]
Train steps ... :  49%|████▉     | 49217/100000 [14:26:31<8:15:58,  1.71it/s]
Train steps ... :  49%|████▉     | 49218/100000 [14:26:32<8:15:32,  1.71it/s]
Train steps ... :  49%|████▉     | 49219/100000 [14:26:32<8:15:54,  1.71it/s]
Train steps ... :  49%|████▉     | 49220/100000 [14:26:33<8:16:21,  1.71it/s]
Train steps ... :  49%|████▉     | 49221/100000 [14:26:33<8:15:47,  1.71it/s]
Train steps ... :  49%|████▉     | 49222/100000 [14:26:34<8:16:22,  1.70it/s]
Train steps ... :  49%|████▉     | 49223/100000 [14:26:34<8:14:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49224/100000 [14:26:35<8:15:21,  1.71it/s]
Train steps ... :  49%|████▉     | 49225/100000 [14:26:36<8:14:51,  1.71it/s]Step... (49225 / 100000 | Loss: 1.0204899311065674, Learning Rate: 5.103015075376885e-05)
+
                                                                             
Step... (49225 / 100000 | Loss: 0.8616944551467896, Learning Rate: 5.103015075376885e-05)
+
Train steps ... :  49%|████▉     | 49225/100000 [14:26:36<8:14:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49226/100000 [14:26:36<8:15:27,  1.71it/s]
Train steps ... :  49%|████▉     | 49227/100000 [14:26:37<8:15:35,  1.71it/s]
Train steps ... :  49%|████▉     | 49228/100000 [14:26:37<8:16:08,  1.71it/s]
Train steps ... :  49%|████▉     | 49229/100000 [14:26:38<8:15:31,  1.71it/s]
Train steps ... :  49%|████▉     | 49230/100000 [14:26:39<8:15:28,  1.71it/s]
Train steps ... :  49%|████▉     | 49231/100000 [14:26:39<8:15:16,  1.71it/s]
Train steps ... :  49%|████▉     | 49232/100000 [14:26:40<8:15:20,  1.71it/s]
Train steps ... :  49%|████▉     | 49233/100000 [14:26:40<8:15:30,  1.71it/s]
Train steps ... :  49%|████▉     | 49234/100000 [14:26:41<8:15:22,  1.71it/s]
Train steps ... :  49%|████▉     | 49235/100000 [14:26:41<8:14:57,  1.71it/s]
Train steps ... :  49%|████▉     | 49236/100000 [14:26:42<8:15:36,  1.71it/s]
Train steps ... :  49%|████▉     | 49237/100000 [14:26:43<8:15:09,  1.71it/s]
Train steps ... :  49%|████▉     | 49238/100000 [14:26:43<8:15:33,  1.71it/s]
Train steps ... :  49%|████▉     | 49239/100000 [14:26:44<8:16:09,  1.71it/s]
Train steps ... :  49%|████▉     | 49240/100000 [14:26:44<8:15:19,  1.71it/s]
Train steps ... :  49%|████▉     | 49241/100000 [14:26:45<8:15:31,  1.71it/s]
Train steps ... :  49%|████▉     | 49242/100000 [14:26:46<8:15:25,  1.71it/s]
Train steps ... :  49%|████▉     | 49243/100000 [14:26:46<8:14:54,  1.71it/s]
Train steps ... :  49%|████▉     | 49244/100000 [14:26:47<8:15:02,  1.71it/s]
Train steps ... :  49%|████▉     | 49245/100000 [14:26:47<8:15:23,  1.71it/s]
Train steps ... :  49%|████▉     | 49246/100000 [14:26:48<8:16:04,  1.71it/s]
Train steps ... :  49%|████▉     | 49247/100000 [14:26:49<8:15:44,  1.71it/s]
Train steps ... :  49%|████▉     | 49248/100000 [14:26:49<8:16:30,  1.70it/s]
Train steps ... :  49%|████▉     | 49249/100000 [14:26:50<8:15:15,  1.71it/s]
Train steps ... :  49%|████▉     | 49250/100000 [14:26:50<8:14:44,  1.71it/s]Step... (49250 / 100000 | Loss: 0.7141449451446533, Learning Rate: 5.1005025125628144e-05)
+
                                                                             
Step... (49250 / 100000 | Loss: 0.9828423261642456, Learning Rate: 5.1005025125628144e-05)
+
Train steps ... :  49%|████▉     | 49250/100000 [14:26:51<8:14:44,  1.71it/s]
Train steps ... :  49%|████▉     | 49251/100000 [14:26:51<8:14:42,  1.71it/s]
Train steps ... :  49%|████▉     | 49252/100000 [14:26:51<8:14:32,  1.71it/s]
Train steps ... :  49%|████▉     | 49253/100000 [14:26:52<8:14:58,  1.71it/s]
Train steps ... :  49%|████▉     | 49254/100000 [14:26:53<8:15:02,  1.71it/s]
Train steps ... :  49%|████▉     | 49255/100000 [14:26:53<8:15:32,  1.71it/s]
Train steps ... :  49%|████▉     | 49256/100000 [14:26:54<8:14:50,  1.71it/s]
Train steps ... :  49%|████▉     | 49257/100000 [14:26:54<8:14:46,  1.71it/s]
Train steps ... :  49%|████▉     | 49258/100000 [14:26:55<8:14:34,  1.71it/s]
Train steps ... :  49%|████▉     | 49259/100000 [14:26:56<8:14:03,  1.71it/s]
Train steps ... :  49%|████▉     | 49260/100000 [14:26:56<8:14:05,  1.71it/s]
Train steps ... :  49%|████▉     | 49261/100000 [14:26:57<8:14:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49262/100000 [14:26:57<8:14:55,  1.71it/s]
Train steps ... :  49%|████▉     | 49263/100000 [14:26:58<8:14:52,  1.71it/s]
Train steps ... :  49%|████▉     | 49264/100000 [14:26:58<8:16:04,  1.70it/s]
Train steps ... :  49%|████▉     | 49265/100000 [14:26:59<8:16:46,  1.70it/s]
Train steps ... :  49%|████▉     | 49266/100000 [14:27:00<8:16:24,  1.70it/s]
Train steps ... :  49%|████▉     | 49267/100000 [14:27:00<8:15:36,  1.71it/s]
Train steps ... :  49%|████▉     | 49268/100000 [14:27:01<8:16:40,  1.70it/s]
Train steps ... :  49%|████▉     | 49269/100000 [14:27:01<8:15:57,  1.70it/s]
Train steps ... :  49%|████▉     | 49270/100000 [14:27:02<8:16:03,  1.70it/s]
Train steps ... :  49%|████▉     | 49271/100000 [14:27:03<8:16:02,  1.70it/s]
Train steps ... :  49%|████▉     | 49272/100000 [14:27:03<8:15:49,  1.71it/s]
Train steps ... :  49%|████▉     | 49273/100000 [14:27:04<8:16:10,  1.70it/s]
Train steps ... :  49%|████▉     | 49274/100000 [14:27:04<8:14:54,  1.71it/s]
Train steps ... :  49%|████▉     | 49275/100000 [14:27:05<8:14:10,  1.71it/s]Step... (49275 / 100000 | Loss: 0.9127416610717773, Learning Rate: 5.097989949748744e-05)
+
                                                                             
Step... (49275 / 100000 | Loss: 0.8026109337806702, Learning Rate: 5.097989949748744e-05)
+
Train steps ... :  49%|████▉     | 49275/100000 [14:27:05<8:14:10,  1.71it/s]
Train steps ... :  49%|████▉     | 49276/100000 [14:27:05<8:15:18,  1.71it/s]
Train steps ... :  49%|████▉     | 49277/100000 [14:27:06<8:14:18,  1.71it/s]
Train steps ... :  49%|████▉     | 49278/100000 [14:27:07<8:14:52,  1.71it/s]
Train steps ... :  49%|████▉     | 49279/100000 [14:27:07<8:15:14,  1.71it/s]
Train steps ... :  49%|████▉     | 49280/100000 [14:27:08<8:14:50,  1.71it/s]
Train steps ... :  49%|████▉     | 49281/100000 [14:27:08<8:13:45,  1.71it/s]
Train steps ... :  49%|████▉     | 49282/100000 [14:27:09<8:13:55,  1.71it/s]
Train steps ... :  49%|████▉     | 49283/100000 [14:27:10<8:14:14,  1.71it/s]
Train steps ... :  49%|████▉     | 49284/100000 [14:27:10<8:14:38,  1.71it/s]
Train steps ... :  49%|████▉     | 49285/100000 [14:27:11<8:15:28,  1.71it/s]
Train steps ... :  49%|████▉     | 49286/100000 [14:27:11<8:15:45,  1.70it/s]
Train steps ... :  49%|████▉     | 49287/100000 [14:27:12<8:15:25,  1.71it/s]
Train steps ... :  49%|████▉     | 49288/100000 [14:27:13<8:15:25,  1.71it/s]
Train steps ... :  49%|████▉     | 49289/100000 [14:27:13<8:14:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49290/100000 [14:27:14<8:15:27,  1.71it/s]
Train steps ... :  49%|████▉     | 49291/100000 [14:27:14<8:15:06,  1.71it/s]
Train steps ... :  49%|████▉     | 49292/100000 [14:27:15<8:15:07,  1.71it/s]
Train steps ... :  49%|████▉     | 49293/100000 [14:27:15<8:14:19,  1.71it/s]
Train steps ... :  49%|████▉     | 49294/100000 [14:27:16<8:14:21,  1.71it/s]
Train steps ... :  49%|████▉     | 49295/100000 [14:27:17<8:14:48,  1.71it/s]
Train steps ... :  49%|████▉     | 49296/100000 [14:27:17<8:14:55,  1.71it/s]
Train steps ... :  49%|████▉     | 49297/100000 [14:27:18<8:15:39,  1.70it/s]
Train steps ... :  49%|████▉     | 49298/100000 [14:27:18<8:15:21,  1.71it/s]
Train steps ... :  49%|████▉     | 49299/100000 [14:27:19<8:16:09,  1.70it/s]
Train steps ... :  49%|████▉     | 49300/100000 [14:27:20<8:15:12,  1.71it/s]Step... (49300 / 100000 | Loss: 0.6077392101287842, Learning Rate: 5.095477386934674e-05)
+
                                                                             
Step... (49300 / 100000 | Loss: 0.6488946080207825, Learning Rate: 5.095477386934674e-05)
+
Train steps ... :  49%|████▉     | 49300/100000 [14:27:20<8:15:12,  1.71it/s]
Train steps ... :  49%|████▉     | 49301/100000 [14:27:20<8:14:40,  1.71it/s]
Train steps ... :  49%|████▉     | 49302/100000 [14:27:21<8:14:02,  1.71it/s]
Train steps ... :  49%|████▉     | 49303/100000 [14:27:21<8:14:02,  1.71it/s]
Train steps ... :  49%|████▉     | 49304/100000 [14:27:22<8:14:05,  1.71it/s]
Train steps ... :  49%|████▉     | 49305/100000 [14:27:22<8:14:22,  1.71it/s]
Train steps ... :  49%|████▉     | 49306/100000 [14:27:23<8:14:29,  1.71it/s]
Train steps ... :  49%|████▉     | 49307/100000 [14:27:24<8:13:26,  1.71it/s]
Train steps ... :  49%|████▉     | 49308/100000 [14:27:24<8:14:03,  1.71it/s]
Train steps ... :  49%|████▉     | 49309/100000 [14:27:25<8:14:38,  1.71it/s]
Train steps ... :  49%|████▉     | 49310/100000 [14:27:25<8:15:21,  1.71it/s]
Train steps ... :  49%|████▉     | 49311/100000 [14:27:26<8:15:08,  1.71it/s]
Train steps ... :  49%|████▉     | 49312/100000 [14:27:27<8:14:09,  1.71it/s]
Train steps ... :  49%|████▉     | 49313/100000 [14:27:27<8:14:20,  1.71it/s]
Train steps ... :  49%|████▉     | 49314/100000 [14:27:28<8:14:36,  1.71it/s]
Train steps ... :  49%|████▉     | 49315/100000 [14:27:28<8:14:50,  1.71it/s]
Train steps ... :  49%|████▉     | 49316/100000 [14:27:29<8:14:28,  1.71it/s]
Train steps ... :  49%|████▉     | 49317/100000 [14:27:29<8:15:19,  1.71it/s]
Train steps ... :  49%|████▉     | 49318/100000 [14:27:30<8:14:24,  1.71it/s]
Train steps ... :  49%|████▉     | 49319/100000 [14:27:31<8:15:05,  1.71it/s]
Train steps ... :  49%|████▉     | 49320/100000 [14:27:31<8:15:18,  1.71it/s]
Train steps ... :  49%|████▉     | 49321/100000 [14:27:32<8:16:04,  1.70it/s]
Train steps ... :  49%|████▉     | 49322/100000 [14:27:32<8:15:58,  1.70it/s]
Train steps ... :  49%|████▉     | 49323/100000 [14:27:33<8:14:36,  1.71it/s]
Train steps ... :  49%|████▉     | 49324/100000 [14:27:34<8:14:17,  1.71it/s]
Train steps ... :  49%|████▉     | 49325/100000 [14:27:34<8:14:28,  1.71it/s]Step... (49325 / 100000 | Loss: 0.7677697539329529, Learning Rate: 5.092964824120603e-05)
+
                                                                             
Step... (49325 / 100000 | Loss: 0.6874836683273315, Learning Rate: 5.092964824120603e-05)
+
Train steps ... :  49%|████▉     | 49325/100000 [14:27:35<8:14:28,  1.71it/s]
Train steps ... :  49%|████▉     | 49326/100000 [14:27:35<8:14:18,  1.71it/s]
Train steps ... :  49%|████▉     | 49327/100000 [14:27:35<8:14:07,  1.71it/s]
Train steps ... :  49%|████▉     | 49328/100000 [14:27:36<8:15:19,  1.70it/s]
Train steps ... :  49%|████▉     | 49329/100000 [14:27:37<8:13:53,  1.71it/s]
Train steps ... :  49%|████▉     | 49330/100000 [14:27:37<8:13:41,  1.71it/s]
Train steps ... :  49%|████▉     | 49331/100000 [14:27:38<8:14:34,  1.71it/s]
Train steps ... :  49%|████▉     | 49332/100000 [14:27:38<8:14:13,  1.71it/s]
Train steps ... :  49%|████▉     | 49333/100000 [14:27:39<8:13:49,  1.71it/s]
Train steps ... :  49%|████▉     | 49334/100000 [14:27:39<8:13:30,  1.71it/s]
Train steps ... :  49%|████▉     | 49335/100000 [14:27:40<8:13:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49336/100000 [14:27:41<8:13:26,  1.71it/s]
Train steps ... :  49%|████▉     | 49337/100000 [14:27:41<8:13:40,  1.71it/s]
Train steps ... :  49%|████▉     | 49338/100000 [14:27:42<8:14:37,  1.71it/s]
Train steps ... :  49%|████▉     | 49339/100000 [14:27:42<8:15:05,  1.71it/s]
Train steps ... :  49%|████▉     | 49340/100000 [14:27:43<8:15:16,  1.70it/s]
Train steps ... :  49%|████▉     | 49341/100000 [14:27:44<8:15:30,  1.70it/s]
Train steps ... :  49%|████▉     | 49342/100000 [14:27:44<8:15:28,  1.70it/s]
Train steps ... :  49%|████▉     | 49343/100000 [14:27:45<8:15:37,  1.70it/s]
Train steps ... :  49%|████▉     | 49344/100000 [14:27:45<8:14:43,  1.71it/s]
Train steps ... :  49%|████▉     | 49345/100000 [14:27:46<8:14:26,  1.71it/s]
Train steps ... :  49%|████▉     | 49346/100000 [14:27:46<8:14:03,  1.71it/s]
Train steps ... :  49%|████▉     | 49347/100000 [14:27:47<8:15:17,  1.70it/s]
Train steps ... :  49%|████▉     | 49348/100000 [14:27:48<8:15:13,  1.70it/s]
Train steps ... :  49%|████▉     | 49349/100000 [14:27:48<8:15:13,  1.70it/s]
Train steps ... :  49%|████▉     | 49350/100000 [14:27:49<8:15:08,  1.70it/s]Step... (49350 / 100000 | Loss: 1.2484339475631714, Learning Rate: 5.090452261306533e-05)
+
                                                                             
Step... (49350 / 100000 | Loss: 0.6766984462738037, Learning Rate: 5.090452261306533e-05)
+
Train steps ... :  49%|████▉     | 49350/100000 [14:27:49<8:15:08,  1.70it/s]
Train steps ... :  49%|████▉     | 49351/100000 [14:27:49<8:14:12,  1.71it/s]
Train steps ... :  49%|████▉     | 49352/100000 [14:27:50<8:15:07,  1.70it/s]
Train steps ... :  49%|████▉     | 49353/100000 [14:27:51<8:14:34,  1.71it/s]
Train steps ... :  49%|████▉     | 49354/100000 [14:27:51<8:14:49,  1.71it/s]
Train steps ... :  49%|████▉     | 49355/100000 [14:27:52<8:14:23,  1.71it/s]
Train steps ... :  49%|████▉     | 49356/100000 [14:27:52<8:14:19,  1.71it/s]
Train steps ... :  49%|████▉     | 49357/100000 [14:27:53<8:13:57,  1.71it/s]
Train steps ... :  49%|████▉     | 49358/100000 [14:27:54<8:15:17,  1.70it/s]
Train steps ... :  49%|████▉     | 49359/100000 [14:27:54<8:14:05,  1.71it/s]
Train steps ... :  49%|████▉     | 49360/100000 [14:27:55<8:14:25,  1.71it/s]
Train steps ... :  49%|████▉     | 49361/100000 [14:27:55<8:14:10,  1.71it/s]
Train steps ... :  49%|████▉     | 49362/100000 [14:27:56<8:13:40,  1.71it/s]
Train steps ... :  49%|████▉     | 49363/100000 [14:27:56<8:14:09,  1.71it/s]
Train steps ... :  49%|████▉     | 49364/100000 [14:27:57<8:13:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49365/100000 [14:27:58<8:13:48,  1.71it/s]
Train steps ... :  49%|████▉     | 49366/100000 [14:27:58<8:13:49,  1.71it/s]
Train steps ... :  49%|████▉     | 49367/100000 [14:27:59<8:15:42,  1.70it/s]
Train steps ... :  49%|████▉     | 49368/100000 [14:27:59<8:15:15,  1.70it/s]
Train steps ... :  49%|████▉     | 49369/100000 [14:28:00<8:14:32,  1.71it/s]
Train steps ... :  49%|████▉     | 49370/100000 [14:28:01<8:14:28,  1.71it/s]
Train steps ... :  49%|████▉     | 49371/100000 [14:28:01<8:13:55,  1.71it/s]
Train steps ... :  49%|████▉     | 49372/100000 [14:28:02<8:14:21,  1.71it/s]
Train steps ... :  49%|████▉     | 49373/100000 [14:28:02<8:13:43,  1.71it/s]
Train steps ... :  49%|████▉     | 49374/100000 [14:28:03<8:13:13,  1.71it/s]
Train steps ... :  49%|████▉     | 49375/100000 [14:28:03<8:13:14,  1.71it/s]Step... (49375 / 100000 | Loss: 0.82861328125, Learning Rate: 5.087939698492462e-05)
+
                                                                             
Step... (49375 / 100000 | Loss: 0.8573071360588074, Learning Rate: 5.087939698492462e-05)
+
Train steps ... :  49%|████▉     | 49375/100000 [14:28:04<8:13:14,  1.71it/s]
Train steps ... :  49%|████▉     | 49376/100000 [14:28:04<8:12:58,  1.71it/s]
Train steps ... :  49%|████▉     | 49377/100000 [14:28:05<8:12:55,  1.71it/s]
Train steps ... :  49%|████▉     | 49378/100000 [14:28:05<8:13:35,  1.71it/s]
Train steps ... :  49%|████▉     | 49379/100000 [14:28:06<8:12:53,  1.71it/s]
Train steps ... :  49%|████▉     | 49380/100000 [14:28:06<8:13:28,  1.71it/s]
Train steps ... :  49%|████▉     | 49381/100000 [14:28:07<8:14:04,  1.71it/s]
Train steps ... :  49%|████▉     | 49382/100000 [14:28:08<8:13:44,  1.71it/s]
Train steps ... :  49%|████▉     | 49383/100000 [14:28:08<8:14:13,  1.71it/s]
Train steps ... :  49%|████▉     | 49384/100000 [14:28:09<8:14:24,  1.71it/s]
Train steps ... :  49%|████▉     | 49385/100000 [14:28:09<8:13:53,  1.71it/s]
Train steps ... :  49%|████▉     | 49386/100000 [14:28:10<8:14:33,  1.71it/s]
Train steps ... :  49%|████▉     | 49387/100000 [14:28:10<8:13:45,  1.71it/s]
Train steps ... :  49%|████▉     | 49388/100000 [14:28:11<8:13:05,  1.71it/s]
Train steps ... :  49%|████▉     | 49389/100000 [14:28:12<8:13:03,  1.71it/s]
Train steps ... :  49%|████▉     | 49390/100000 [14:28:12<8:13:13,  1.71it/s]
Train steps ... :  49%|████▉     | 49391/100000 [14:28:13<8:13:17,  1.71it/s]
Train steps ... :  49%|████▉     | 49392/100000 [14:28:13<8:13:23,  1.71it/s]
Train steps ... :  49%|████▉     | 49393/100000 [14:28:14<8:15:02,  1.70it/s]
Train steps ... :  49%|████▉     | 49394/100000 [14:28:15<8:14:00,  1.71it/s]
Train steps ... :  49%|████▉     | 49395/100000 [14:28:15<8:13:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49396/100000 [14:28:16<8:14:43,  1.70it/s]
Train steps ... :  49%|████▉     | 49397/100000 [14:28:16<8:14:33,  1.71it/s]
Train steps ... :  49%|████▉     | 49398/100000 [14:28:17<8:14:21,  1.71it/s]
Train steps ... :  49%|████▉     | 49399/100000 [14:28:18<8:14:40,  1.70it/s]
Train steps ... :  49%|████▉     | 49400/100000 [14:28:18<8:14:15,  1.71it/s]Step... (49400 / 100000 | Loss: 1.0793272256851196, Learning Rate: 5.0854271356783924e-05)
+
                                                                             
Step... (49400 / 100000 | Loss: 0.9194129705429077, Learning Rate: 5.0854271356783924e-05)
+
Train steps ... :  49%|████▉     | 49400/100000 [14:28:18<8:14:15,  1.71it/s]
Train steps ... :  49%|████▉     | 49401/100000 [14:28:19<8:15:22,  1.70it/s]
Train steps ... :  49%|████▉     | 49402/100000 [14:28:19<8:15:11,  1.70it/s]
Train steps ... :  49%|████▉     | 49403/100000 [14:28:20<8:16:28,  1.70it/s]
Train steps ... :  49%|████▉     | 49404/100000 [14:28:20<8:14:16,  1.71it/s]
Train steps ... :  49%|████▉     | 49405/100000 [14:28:21<8:13:32,  1.71it/s]
Train steps ... :  49%|████▉     | 49406/100000 [14:28:22<8:13:18,  1.71it/s]
Train steps ... :  49%|████▉     | 49407/100000 [14:28:22<8:13:03,  1.71it/s]
Train steps ... :  49%|████▉     | 49408/100000 [14:28:23<8:12:47,  1.71it/s]
Train steps ... :  49%|████▉     | 49409/100000 [14:28:23<8:13:16,  1.71it/s]
Train steps ... :  49%|████▉     | 49410/100000 [14:28:24<8:14:23,  1.71it/s]
Train steps ... :  49%|████▉     | 49411/100000 [14:28:25<8:13:18,  1.71it/s]
Train steps ... :  49%|████▉     | 49412/100000 [14:28:25<8:13:11,  1.71it/s]
Train steps ... :  49%|████▉     | 49413/100000 [14:28:26<8:13:32,  1.71it/s]
Train steps ... :  49%|████▉     | 49414/100000 [14:28:26<8:13:08,  1.71it/s]
Train steps ... :  49%|████▉     | 49415/100000 [14:28:27<8:12:54,  1.71it/s]
Train steps ... :  49%|████▉     | 49416/100000 [14:28:27<8:13:09,  1.71it/s]
Train steps ... :  49%|████▉     | 49417/100000 [14:28:28<8:13:06,  1.71it/s]
Train steps ... :  49%|████▉     | 49418/100000 [14:28:29<8:12:38,  1.71it/s]
Train steps ... :  49%|████▉     | 49419/100000 [14:28:29<8:13:07,  1.71it/s]
Train steps ... :  49%|████▉     | 49420/100000 [14:28:30<8:14:26,  1.70it/s]
Train steps ... :  49%|████▉     | 49421/100000 [14:28:30<8:14:40,  1.70it/s]
Train steps ... :  49%|████▉     | 49422/100000 [14:28:31<8:15:09,  1.70it/s]
Train steps ... :  49%|████▉     | 49423/100000 [14:28:32<8:14:58,  1.70it/s]
Train steps ... :  49%|████▉     | 49424/100000 [14:28:32<8:14:51,  1.70it/s]
Train steps ... :  49%|████▉     | 49425/100000 [14:28:33<8:14:20,  1.71it/s]Step... (49425 / 100000 | Loss: 0.7880310416221619, Learning Rate: 5.082914572864322e-05)
+
                                                                             
Step... (49425 / 100000 | Loss: 1.051181674003601, Learning Rate: 5.082914572864322e-05)
+
Train steps ... :  49%|████▉     | 49425/100000 [14:28:33<8:14:20,  1.71it/s]
Train steps ... :  49%|████▉     | 49426/100000 [14:28:33<8:15:53,  1.70it/s]
Train steps ... :  49%|████▉     | 49427/100000 [14:28:34<8:14:21,  1.71it/s]
Train steps ... :  49%|████▉     | 49428/100000 [14:28:35<8:14:20,  1.71it/s]
Train steps ... :  49%|████▉     | 49429/100000 [14:28:35<8:14:31,  1.70it/s]
Train steps ... :  49%|████▉     | 49430/100000 [14:28:36<8:14:36,  1.70it/s]
Train steps ... :  49%|████▉     | 49431/100000 [14:28:36<8:13:31,  1.71it/s]
Train steps ... :  49%|████▉     | 49432/100000 [14:28:37<8:16:49,  1.70it/s]
Train steps ... :  49%|████▉     | 49433/100000 [14:28:37<8:15:09,  1.70it/s]
Train steps ... :  49%|████▉     | 49434/100000 [14:28:38<8:15:02,  1.70it/s]
Train steps ... :  49%|████▉     | 49435/100000 [14:28:39<8:15:11,  1.70it/s]
Train steps ... :  49%|████▉     | 49436/100000 [14:28:39<8:16:01,  1.70it/s]
Train steps ... :  49%|████▉     | 49437/100000 [14:28:40<8:16:44,  1.70it/s]
Train steps ... :  49%|████▉     | 49438/100000 [14:28:40<8:14:19,  1.70it/s]
Train steps ... :  49%|████▉     | 49439/100000 [14:28:41<8:14:21,  1.70it/s]
Train steps ... :  49%|████▉     | 49440/100000 [14:28:42<8:13:26,  1.71it/s]
Train steps ... :  49%|████▉     | 49441/100000 [14:28:42<8:14:46,  1.70it/s]
Train steps ... :  49%|████▉     | 49442/100000 [14:28:43<8:15:20,  1.70it/s]
Train steps ... :  49%|████▉     | 49443/100000 [14:28:43<8:16:34,  1.70it/s]
Train steps ... :  49%|████▉     | 49444/100000 [14:28:44<8:16:17,  1.70it/s]
Train steps ... :  49%|████▉     | 49445/100000 [14:28:45<8:15:03,  1.70it/s]
Train steps ... :  49%|████▉     | 49446/100000 [14:28:45<8:16:04,  1.70it/s]
Train steps ... :  49%|████▉     | 49447/100000 [14:28:46<8:13:58,  1.71it/s]
Train steps ... :  49%|████▉     | 49448/100000 [14:28:46<8:13:57,  1.71it/s]
Train steps ... :  49%|████▉     | 49449/100000 [14:28:47<8:14:58,  1.70it/s]
Train steps ... :  49%|████▉     | 49450/100000 [14:28:47<8:13:48,  1.71it/s]Step... (49450 / 100000 | Loss: 0.6393687725067139, Learning Rate: 5.080402010050252e-05)
+
                                                                             
Step... (49450 / 100000 | Loss: 0.5777607560157776, Learning Rate: 5.080402010050252e-05)
+
Train steps ... :  49%|████▉     | 49450/100000 [14:28:48<8:13:48,  1.71it/s]
Train steps ... :  49%|████▉     | 49451/100000 [14:28:48<8:13:48,  1.71it/s]
Train steps ... :  49%|████▉     | 49452/100000 [14:28:49<8:13:42,  1.71it/s]
Train steps ... :  49%|████▉     | 49453/100000 [14:28:49<8:12:31,  1.71it/s]
Train steps ... :  49%|████▉     | 49454/100000 [14:28:50<8:12:47,  1.71it/s]
Train steps ... :  49%|████▉     | 49455/100000 [14:28:50<8:13:40,  1.71it/s]
Train steps ... :  49%|████▉     | 49456/100000 [14:28:51<8:13:45,  1.71it/s]
Train steps ... :  49%|████▉     | 49457/100000 [14:28:52<8:13:18,  1.71it/s]
Train steps ... :  49%|████▉     | 49458/100000 [14:28:52<8:13:33,  1.71it/s]
Train steps ... :  49%|████▉     | 49459/100000 [14:28:53<8:13:12,  1.71it/s]
Train steps ... :  49%|████▉     | 49460/100000 [14:28:53<8:13:42,  1.71it/s]
Train steps ... :  49%|████▉     | 49461/100000 [14:28:54<8:14:04,  1.70it/s]
Train steps ... :  49%|████▉     | 49462/100000 [14:28:54<8:14:11,  1.70it/s]
Train steps ... :  49%|████▉     | 49463/100000 [14:28:55<8:13:43,  1.71it/s]
Train steps ... :  49%|████▉     | 49464/100000 [14:28:56<8:13:42,  1.71it/s]
Train steps ... :  49%|████▉     | 49465/100000 [14:28:56<8:14:00,  1.70it/s]
Train steps ... :  49%|████▉     | 49466/100000 [14:28:57<8:13:07,  1.71it/s]
Train steps ... :  49%|████▉     | 49467/100000 [14:28:57<8:14:27,  1.70it/s]
Train steps ... :  49%|████▉     | 49468/100000 [14:28:58<8:13:19,  1.71it/s]
Train steps ... :  49%|████▉     | 49469/100000 [14:28:59<8:13:23,  1.71it/s]
Train steps ... :  49%|████▉     | 49470/100000 [14:28:59<8:13:43,  1.71it/s]
Train steps ... :  49%|████▉     | 49471/100000 [14:29:00<8:14:11,  1.70it/s]
Train steps ... :  49%|████▉     | 49472/100000 [14:29:00<8:14:32,  1.70it/s]
Train steps ... :  49%|████▉     | 49473/100000 [14:29:01<8:14:15,  1.70it/s]
Train steps ... :  49%|████▉     | 49474/100000 [14:29:02<8:13:47,  1.71it/s]
Train steps ... :  49%|████▉     | 49475/100000 [14:29:02<8:14:03,  1.70it/s]Step... (49475 / 100000 | Loss: 0.8187398910522461, Learning Rate: 5.0778894472361814e-05)
+
                                                                             
Step... (49475 / 100000 | Loss: 0.9030907154083252, Learning Rate: 5.0778894472361814e-05)
+
Train steps ... :  49%|████▉     | 49475/100000 [14:29:02<8:14:03,  1.70it/s]
Train steps ... :  49%|████▉     | 49476/100000 [14:29:03<8:14:31,  1.70it/s]
Train steps ... :  49%|████▉     | 49477/100000 [14:29:03<8:14:20,  1.70it/s]
Train steps ... :  49%|████▉     | 49478/100000 [14:29:04<8:13:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49479/100000 [14:29:04<8:14:09,  1.70it/s]
Train steps ... :  49%|████▉     | 49480/100000 [14:29:05<8:13:08,  1.71it/s]
Train steps ... :  49%|████▉     | 49481/100000 [14:29:06<8:13:07,  1.71it/s]
Train steps ... :  49%|████▉     | 49482/100000 [14:29:06<8:13:42,  1.71it/s]
Train steps ... :  49%|████▉     | 49483/100000 [14:29:07<8:12:51,  1.71it/s]
Train steps ... :  49%|████▉     | 49484/100000 [14:29:07<8:12:56,  1.71it/s]
Train steps ... :  49%|████▉     | 49485/100000 [14:29:08<8:12:57,  1.71it/s]
Train steps ... :  49%|████▉     | 49486/100000 [14:29:09<8:13:00,  1.71it/s]
Train steps ... :  49%|████▉     | 49487/100000 [14:29:09<8:13:26,  1.71it/s]
Train steps ... :  49%|████▉     | 49488/100000 [14:29:10<8:14:22,  1.70it/s]
Train steps ... :  49%|████▉     | 49489/100000 [14:29:10<8:14:16,  1.70it/s]
Train steps ... :  49%|████▉     | 49490/100000 [14:29:11<8:14:51,  1.70it/s]
Train steps ... :  49%|████▉     | 49491/100000 [14:29:11<8:14:22,  1.70it/s]
Train steps ... :  49%|████▉     | 49492/100000 [14:29:12<8:13:35,  1.71it/s]
Train steps ... :  49%|████▉     | 49493/100000 [14:29:13<8:12:52,  1.71it/s]
Train steps ... :  49%|████▉     | 49494/100000 [14:29:13<8:13:01,  1.71it/s]
Train steps ... :  49%|████▉     | 49495/100000 [14:29:14<8:12:52,  1.71it/s]
Train steps ... :  49%|████▉     | 49496/100000 [14:29:14<8:13:56,  1.70it/s]
Train steps ... :  49%|████▉     | 49497/100000 [14:29:15<8:12:31,  1.71it/s]
Train steps ... :  49%|████▉     | 49498/100000 [14:29:16<8:12:04,  1.71it/s]
Train steps ... :  49%|████▉     | 49499/100000 [14:29:16<8:12:46,  1.71it/s]
Train steps ... :  50%|████▉     | 49500/100000 [14:29:17<8:13:14,  1.71it/s]Step... (49500 / 100000 | Loss: 0.7462140321731567, Learning Rate: 5.0753768844221104e-05)
+
                                                                             
Step... (49500 / 100000 | Loss: 0.8600215315818787, Learning Rate: 5.0753768844221104e-05)
+
Train steps ... :  50%|████▉     | 49500/100000 [14:29:17<8:13:14,  1.71it/s]
Train steps ... :  50%|████▉     | 49501/100000 [14:29:17<8:13:15,  1.71it/s]
Train steps ... :  50%|████▉     | 49502/100000 [14:29:18<8:12:20,  1.71it/s]
Train steps ... :  50%|████▉     | 49503/100000 [14:29:18<8:12:15,  1.71it/s]
Train steps ... :  50%|████▉     | 49504/100000 [14:29:19<8:11:44,  1.71it/s]
Train steps ... :  50%|████▉     | 49505/100000 [14:29:20<8:11:55,  1.71it/s]
Train steps ... :  50%|████▉     | 49506/100000 [14:29:20<8:12:36,  1.71it/s]
Train steps ... :  50%|████▉     | 49507/100000 [14:29:21<8:11:34,  1.71it/s]
Train steps ... :  50%|████▉     | 49508/100000 [14:29:21<8:12:46,  1.71it/s]
Train steps ... :  50%|████▉     | 49509/100000 [14:29:22<8:13:23,  1.71it/s]
Train steps ... :  50%|████▉     | 49510/100000 [14:29:23<8:12:51,  1.71it/s]
Train steps ... :  50%|████▉     | 49511/100000 [14:29:23<8:12:52,  1.71it/s]
Train steps ... :  50%|████▉     | 49512/100000 [14:29:24<8:13:07,  1.71it/s]
Train steps ... :  50%|████▉     | 49513/100000 [14:29:24<8:13:40,  1.70it/s]
Train steps ... :  50%|████▉     | 49514/100000 [14:29:25<8:13:27,  1.71it/s]
Train steps ... :  50%|████▉     | 49515/100000 [14:29:26<8:13:30,  1.70it/s]
Train steps ... :  50%|████▉     | 49516/100000 [14:29:26<8:13:14,  1.71it/s]
Train steps ... :  50%|████▉     | 49517/100000 [14:29:27<8:13:01,  1.71it/s]
Train steps ... :  50%|████▉     | 49518/100000 [14:29:27<8:13:02,  1.71it/s]
Train steps ... :  50%|████▉     | 49519/100000 [14:29:28<8:12:15,  1.71it/s]
Train steps ... :  50%|████▉     | 49520/100000 [14:29:28<8:13:44,  1.70it/s]
Train steps ... :  50%|████▉     | 49521/100000 [14:29:29<8:13:09,  1.71it/s]
Train steps ... :  50%|████▉     | 49522/100000 [14:29:30<8:13:05,  1.71it/s]
Train steps ... :  50%|████▉     | 49523/100000 [14:29:30<8:13:34,  1.70it/s]
Train steps ... :  50%|████▉     | 49524/100000 [14:29:31<8:11:58,  1.71it/s]
Train steps ... :  50%|████▉     | 49525/100000 [14:29:31<8:12:19,  1.71it/s]Step... (49525 / 100000 | Loss: 1.1974087953567505, Learning Rate: 5.072864321608041e-05)
+
                                                                             
Step... (49525 / 100000 | Loss: 0.6595790386199951, Learning Rate: 5.072864321608041e-05)
+
Train steps ... :  50%|████▉     | 49525/100000 [14:29:32<8:12:19,  1.71it/s]
Train steps ... :  50%|████▉     | 49526/100000 [14:29:32<8:12:07,  1.71it/s]
Train steps ... :  50%|████▉     | 49527/100000 [14:29:33<8:12:19,  1.71it/s]
Train steps ... :  50%|████▉     | 49528/100000 [14:29:33<8:12:35,  1.71it/s]
Train steps ... :  50%|████▉     | 49529/100000 [14:29:34<8:13:14,  1.71it/s]
Train steps ... :  50%|████▉     | 49530/100000 [14:29:34<8:12:27,  1.71it/s]
Train steps ... :  50%|████▉     | 49531/100000 [14:29:35<8:11:44,  1.71it/s]
Train steps ... :  50%|████▉     | 49532/100000 [14:29:35<8:11:38,  1.71it/s]
Train steps ... :  50%|████▉     | 49533/100000 [14:29:36<8:12:37,  1.71it/s]
Train steps ... :  50%|████▉     | 49534/100000 [14:29:37<8:11:47,  1.71it/s]
Train steps ... :  50%|████▉     | 49535/100000 [14:29:37<8:11:59,  1.71it/s]
Train steps ... :  50%|████▉     | 49536/100000 [14:29:38<8:11:52,  1.71it/s]
Train steps ... :  50%|████▉     | 49537/100000 [14:29:38<8:11:29,  1.71it/s]
Train steps ... :  50%|████▉     | 49538/100000 [14:29:39<8:11:40,  1.71it/s]
Train steps ... :  50%|████▉     | 49539/100000 [14:29:40<8:11:23,  1.71it/s]
Train steps ... :  50%|████▉     | 49540/100000 [14:29:40<8:11:44,  1.71it/s]
Train steps ... :  50%|████▉     | 49541/100000 [14:29:41<8:12:20,  1.71it/s]
Train steps ... :  50%|████▉     | 49542/100000 [14:29:41<8:11:45,  1.71it/s]
Train steps ... :  50%|████▉     | 49543/100000 [14:29:42<8:12:12,  1.71it/s]
Train steps ... :  50%|████▉     | 49544/100000 [14:29:42<8:11:31,  1.71it/s]
Train steps ... :  50%|████▉     | 49545/100000 [14:29:43<8:12:51,  1.71it/s]
Train steps ... :  50%|████▉     | 49546/100000 [14:29:44<8:13:06,  1.71it/s]
Train steps ... :  50%|████▉     | 49547/100000 [14:29:44<8:12:49,  1.71it/s]
Train steps ... :  50%|████▉     | 49548/100000 [14:29:45<8:12:35,  1.71it/s]
Train steps ... :  50%|████▉     | 49549/100000 [14:29:45<8:12:50,  1.71it/s]
Train steps ... :  50%|████▉     | 49550/100000 [14:29:46<8:12:24,  1.71it/s]Step... (49550 / 100000 | Loss: 1.0690832138061523, Learning Rate: 5.07035175879397e-05)
+
                                                                             
Step... (49550 / 100000 | Loss: 0.700640082359314, Learning Rate: 5.07035175879397e-05)
+
Train steps ... :  50%|████▉     | 49550/100000 [14:29:46<8:12:24,  1.71it/s]
Train steps ... :  50%|████▉     | 49551/100000 [14:29:47<8:11:51,  1.71it/s]
Train steps ... :  50%|████▉     | 49552/100000 [14:29:47<8:12:16,  1.71it/s]
Train steps ... :  50%|████▉     | 49553/100000 [14:29:48<8:12:08,  1.71it/s]
Train steps ... :  50%|████▉     | 49554/100000 [14:29:48<8:11:48,  1.71it/s]
Train steps ... :  50%|████▉     | 49555/100000 [14:29:49<8:12:45,  1.71it/s]
Train steps ... :  50%|████▉     | 49556/100000 [14:29:50<8:13:44,  1.70it/s]
Train steps ... :  50%|████▉     | 49557/100000 [14:29:50<8:13:52,  1.70it/s]
Train steps ... :  50%|████▉     | 49558/100000 [14:29:51<8:12:59,  1.71it/s]
Train steps ... :  50%|████▉     | 49559/100000 [14:29:51<8:13:30,  1.70it/s]
Train steps ... :  50%|████▉     | 49560/100000 [14:29:52<8:14:55,  1.70it/s]
Train steps ... :  50%|████▉     | 49561/100000 [14:29:52<8:14:23,  1.70it/s]
Train steps ... :  50%|████▉     | 49562/100000 [14:29:53<8:14:21,  1.70it/s]
Train steps ... :  50%|████▉     | 49563/100000 [14:29:54<8:14:10,  1.70it/s]
Train steps ... :  50%|████▉     | 49564/100000 [14:29:54<8:14:26,  1.70it/s]
Train steps ... :  50%|████▉     | 49565/100000 [14:29:55<8:15:01,  1.70it/s]
Train steps ... :  50%|████▉     | 49566/100000 [14:29:55<8:14:34,  1.70it/s]
Train steps ... :  50%|████▉     | 49567/100000 [14:29:56<8:15:46,  1.70it/s]
Train steps ... :  50%|████▉     | 49568/100000 [14:29:57<8:13:12,  1.70it/s]
Train steps ... :  50%|████▉     | 49569/100000 [14:29:57<8:13:22,  1.70it/s]
Train steps ... :  50%|████▉     | 49570/100000 [14:29:58<8:13:05,  1.70it/s]
Train steps ... :  50%|████▉     | 49571/100000 [14:29:58<8:14:01,  1.70it/s]
Train steps ... :  50%|████▉     | 49572/100000 [14:29:59<8:13:04,  1.70it/s]
Train steps ... :  50%|████▉     | 49573/100000 [14:30:00<8:13:56,  1.70it/s]
Train steps ... :  50%|████▉     | 49574/100000 [14:30:00<8:15:04,  1.70it/s]
Train steps ... :  50%|████▉     | 49575/100000 [14:30:01<8:15:05,  1.70it/s]Step... (49575 / 100000 | Loss: 0.7091140151023865, Learning Rate: 5.0678391959799e-05)
+
                                                                             
Step... (49575 / 100000 | Loss: 0.8451637029647827, Learning Rate: 5.0678391959799e-05)
+
Train steps ... :  50%|████▉     | 49575/100000 [14:30:01<8:15:05,  1.70it/s]
Train steps ... :  50%|████▉     | 49576/100000 [14:30:01<8:14:25,  1.70it/s]
Train steps ... :  50%|████▉     | 49577/100000 [14:30:02<8:13:34,  1.70it/s]
Train steps ... :  50%|████▉     | 49578/100000 [14:30:02<8:12:58,  1.70it/s]
Train steps ... :  50%|████▉     | 49579/100000 [14:30:03<8:13:04,  1.70it/s]
Train steps ... :  50%|████▉     | 49580/100000 [14:30:04<8:11:56,  1.71it/s]
Train steps ... :  50%|████▉     | 49581/100000 [14:30:04<8:12:49,  1.71it/s]
Train steps ... :  50%|████▉     | 49582/100000 [14:30:05<8:12:27,  1.71it/s]
Train steps ... :  50%|████▉     | 49583/100000 [14:30:05<8:12:32,  1.71it/s]
Train steps ... :  50%|████▉     | 49584/100000 [14:30:06<8:12:18,  1.71it/s]
Train steps ... :  50%|████▉     | 49585/100000 [14:30:07<8:11:10,  1.71it/s]
Train steps ... :  50%|████▉     | 49586/100000 [14:30:07<8:11:57,  1.71it/s]
Train steps ... :  50%|████▉     | 49587/100000 [14:30:08<8:11:22,  1.71it/s]
Train steps ... :  50%|████▉     | 49588/100000 [14:30:08<8:11:46,  1.71it/s]
Train steps ... :  50%|████▉     | 49589/100000 [14:30:09<8:11:56,  1.71it/s]
Train steps ... :  50%|████▉     | 49590/100000 [14:30:09<8:11:44,  1.71it/s]
Train steps ... :  50%|████▉     | 49591/100000 [14:30:10<8:13:06,  1.70it/s]
Train steps ... :  50%|████▉     | 49592/100000 [14:30:11<8:12:36,  1.71it/s]
Train steps ... :  50%|████▉     | 49593/100000 [14:30:11<8:12:32,  1.71it/s]
Train steps ... :  50%|████▉     | 49594/100000 [14:30:12<8:13:30,  1.70it/s]
Train steps ... :  50%|████▉     | 49595/100000 [14:30:12<8:12:12,  1.71it/s]
Train steps ... :  50%|████▉     | 49596/100000 [14:30:13<8:12:13,  1.71it/s]
Train steps ... :  50%|████▉     | 49597/100000 [14:30:14<8:12:11,  1.71it/s]
Train steps ... :  50%|████▉     | 49598/100000 [14:30:14<8:11:54,  1.71it/s]
Train steps ... :  50%|████▉     | 49599/100000 [14:30:15<8:11:38,  1.71it/s]
Train steps ... :  50%|████▉     | 49600/100000 [14:30:15<8:11:27,  1.71it/s]Step... (49600 / 100000 | Loss: 0.9105246067047119, Learning Rate: 5.065326633165829e-05)
+
                                                                             
Step... (49600 / 100000 | Loss: 0.6148005723953247, Learning Rate: 5.065326633165829e-05)
+
Train steps ... :  50%|████▉     | 49600/100000 [14:30:16<8:11:27,  1.71it/s]
Train steps ... :  50%|████▉     | 49601/100000 [14:30:16<8:11:26,  1.71it/s]
Train steps ... :  50%|████▉     | 49602/100000 [14:30:17<8:13:13,  1.70it/s]
Train steps ... :  50%|████▉     | 49603/100000 [14:30:17<8:11:33,  1.71it/s]
Train steps ... :  50%|████▉     | 49604/100000 [14:30:18<8:12:02,  1.71it/s]
Train steps ... :  50%|████▉     | 49605/100000 [14:30:18<8:13:17,  1.70it/s]
Train steps ... :  50%|████▉     | 49606/100000 [14:30:19<8:11:38,  1.71it/s]
Train steps ... :  50%|████▉     | 49607/100000 [14:30:19<8:11:28,  1.71it/s]
Train steps ... :  50%|████▉     | 49608/100000 [14:30:20<8:11:10,  1.71it/s]
Train steps ... :  50%|████▉     | 49609/100000 [14:30:21<8:11:08,  1.71it/s]
Train steps ... :  50%|████▉     | 49610/100000 [14:30:21<8:12:21,  1.71it/s]
Train steps ... :  50%|████▉     | 49611/100000 [14:30:22<8:12:16,  1.71it/s]
Train steps ... :  50%|████▉     | 49612/100000 [14:30:22<8:11:56,  1.71it/s]
Train steps ... :  50%|████▉     | 49613/100000 [14:30:23<8:11:31,  1.71it/s]
Train steps ... :  50%|████▉     | 49614/100000 [14:30:24<8:12:10,  1.71it/s]
Train steps ... :  50%|████▉     | 49615/100000 [14:30:24<8:11:38,  1.71it/s]
Train steps ... :  50%|████▉     | 49616/100000 [14:30:25<8:12:02,  1.71it/s]
Train steps ... :  50%|████▉     | 49617/100000 [14:30:25<8:11:43,  1.71it/s]
Train steps ... :  50%|████▉     | 49618/100000 [14:30:26<8:11:20,  1.71it/s]
Train steps ... :  50%|████▉     | 49619/100000 [14:30:26<8:11:12,  1.71it/s]
Train steps ... :  50%|████▉     | 49620/100000 [14:30:27<8:11:25,  1.71it/s]
Train steps ... :  50%|████▉     | 49621/100000 [14:30:28<8:11:12,  1.71it/s]
Train steps ... :  50%|████▉     | 49622/100000 [14:30:28<8:11:04,  1.71it/s]
Train steps ... :  50%|████▉     | 49623/100000 [14:30:29<8:11:49,  1.71it/s]
Train steps ... :  50%|████▉     | 49624/100000 [14:30:29<8:12:15,  1.71it/s]
Train steps ... :  50%|████▉     | 49625/100000 [14:30:30<8:13:41,  1.70it/s]Step... (49625 / 100000 | Loss: 0.7596248984336853, Learning Rate: 5.0628140703517594e-05)
+
                                                                             
Step... (49625 / 100000 | Loss: 0.9648942947387695, Learning Rate: 5.0628140703517594e-05)
+
Train steps ... :  50%|████▉     | 49625/100000 [14:30:30<8:13:41,  1.70it/s]
Train steps ... :  50%|████▉     | 49626/100000 [14:30:31<8:13:23,  1.70it/s]
Train steps ... :  50%|████▉     | 49627/100000 [14:30:31<8:12:15,  1.71it/s]
Train steps ... :  50%|████▉     | 49628/100000 [14:30:32<8:13:01,  1.70it/s]
Train steps ... :  50%|████▉     | 49629/100000 [14:30:32<8:12:56,  1.70it/s]
Train steps ... :  50%|████▉     | 49630/100000 [14:30:33<8:12:15,  1.71it/s]
Train steps ... :  50%|████▉     | 49631/100000 [14:30:34<8:12:05,  1.71it/s]
Train steps ... :  50%|████▉     | 49632/100000 [14:30:34<8:12:12,  1.71it/s]
Train steps ... :  50%|████▉     | 49633/100000 [14:30:35<8:12:31,  1.70it/s]
Train steps ... :  50%|████▉     | 49634/100000 [14:30:35<8:12:40,  1.70it/s]
Train steps ... :  50%|████▉     | 49635/100000 [14:30:36<8:13:22,  1.70it/s]
Train steps ... :  50%|████▉     | 49636/100000 [14:30:36<8:13:31,  1.70it/s]
Train steps ... :  50%|████▉     | 49637/100000 [14:30:37<8:11:11,  1.71it/s]
Train steps ... :  50%|████▉     | 49638/100000 [14:30:38<8:10:42,  1.71it/s]
Train steps ... :  50%|████▉     | 49639/100000 [14:30:38<8:10:45,  1.71it/s]
Train steps ... :  50%|████▉     | 49640/100000 [14:30:39<8:10:30,  1.71it/s]
Train steps ... :  50%|████▉     | 49641/100000 [14:30:39<8:11:11,  1.71it/s]
Train steps ... :  50%|████▉     | 49642/100000 [14:30:40<8:10:27,  1.71it/s]
Train steps ... :  50%|████▉     | 49643/100000 [14:30:41<8:11:40,  1.71it/s]
Train steps ... :  50%|████▉     | 49644/100000 [14:30:41<8:11:45,  1.71it/s]
Train steps ... :  50%|████▉     | 49645/100000 [14:30:42<8:12:17,  1.70it/s]
Train steps ... :  50%|████▉     | 49646/100000 [14:30:42<8:12:14,  1.70it/s]
Train steps ... :  50%|████▉     | 49647/100000 [14:30:43<8:12:00,  1.71it/s]
Train steps ... :  50%|████▉     | 49648/100000 [14:30:43<8:12:18,  1.70it/s]
Train steps ... :  50%|████▉     | 49649/100000 [14:30:44<8:10:47,  1.71it/s]
Train steps ... :  50%|████▉     | 49650/100000 [14:30:45<8:11:05,  1.71it/s]Step... (49650 / 100000 | Loss: 0.7938195466995239, Learning Rate: 5.060301507537689e-05)
+
                                                                             
Step... (49650 / 100000 | Loss: 0.6772032380104065, Learning Rate: 5.060301507537689e-05)
+
Train steps ... :  50%|████▉     | 49650/100000 [14:30:45<8:11:05,  1.71it/s]
Train steps ... :  50%|████▉     | 49651/100000 [14:30:45<8:11:14,  1.71it/s]
Train steps ... :  50%|████▉     | 49652/100000 [14:30:46<8:10:43,  1.71it/s]
Train steps ... :  50%|████▉     | 49653/100000 [14:30:46<8:10:31,  1.71it/s]
Train steps ... :  50%|████▉     | 49654/100000 [14:30:47<8:11:04,  1.71it/s]
Train steps ... :  50%|████▉     | 49655/100000 [14:30:48<8:10:29,  1.71it/s]
Train steps ... :  50%|████▉     | 49656/100000 [14:30:48<8:12:27,  1.70it/s]
Train steps ... :  50%|████▉     | 49657/100000 [14:30:49<8:13:14,  1.70it/s]
Train steps ... :  50%|████▉     | 49658/100000 [14:30:49<8:13:16,  1.70it/s]
Train steps ... :  50%|████▉     | 49659/100000 [14:30:50<8:11:47,  1.71it/s]
Train steps ... :  50%|████▉     | 49660/100000 [14:30:51<8:12:25,  1.70it/s]
Train steps ... :  50%|████▉     | 49661/100000 [14:30:51<8:12:21,  1.70it/s]
Train steps ... :  50%|████▉     | 49662/100000 [14:30:52<8:12:24,  1.70it/s]
Train steps ... :  50%|████▉     | 49663/100000 [14:30:52<8:11:40,  1.71it/s]
Train steps ... :  50%|████▉     | 49664/100000 [14:30:53<8:11:04,  1.71it/s]
Train steps ... :  50%|████▉     | 49665/100000 [14:30:53<8:11:26,  1.71it/s]
Train steps ... :  50%|████▉     | 49666/100000 [14:30:54<8:11:28,  1.71it/s]
Train steps ... :  50%|████▉     | 49667/100000 [14:30:55<8:11:46,  1.71it/s]
Train steps ... :  50%|████▉     | 49668/100000 [14:30:55<8:11:42,  1.71it/s]
Train steps ... :  50%|████▉     | 49669/100000 [14:30:56<8:11:05,  1.71it/s]
Train steps ... :  50%|████▉     | 49670/100000 [14:30:56<8:11:06,  1.71it/s]
Train steps ... :  50%|████▉     | 49671/100000 [14:30:57<8:11:17,  1.71it/s]
Train steps ... :  50%|████▉     | 49672/100000 [14:30:58<8:11:17,  1.71it/s]
Train steps ... :  50%|████▉     | 49673/100000 [14:30:58<8:12:24,  1.70it/s]
Train steps ... :  50%|████▉     | 49674/100000 [14:30:59<8:12:23,  1.70it/s]
Train steps ... :  50%|████▉     | 49675/100000 [14:30:59<8:11:03,  1.71it/s]Step... (49675 / 100000 | Loss: 0.9456632733345032, Learning Rate: 5.057788944723618e-05)
+
                                                                             
Step... (49675 / 100000 | Loss: 0.8799840211868286, Learning Rate: 5.057788944723618e-05)
+
Train steps ... :  50%|████▉     | 49675/100000 [14:31:00<8:11:03,  1.71it/s]
Train steps ... :  50%|████▉     | 49676/100000 [14:31:00<8:11:25,  1.71it/s]
Train steps ... :  50%|████▉     | 49677/100000 [14:31:00<8:11:08,  1.71it/s]
Train steps ... :  50%|████▉     | 49678/100000 [14:31:01<8:11:10,  1.71it/s]
Train steps ... :  50%|████▉     | 49679/100000 [14:31:02<8:11:02,  1.71it/s]
Train steps ... :  50%|████▉     | 49680/100000 [14:31:02<8:11:23,  1.71it/s]
Train steps ... :  50%|████▉     | 49681/100000 [14:31:03<8:11:49,  1.71it/s]
Train steps ... :  50%|████▉     | 49682/100000 [14:31:03<8:10:28,  1.71it/s]
Train steps ... :  50%|████▉     | 49683/100000 [14:31:04<8:11:08,  1.71it/s]
Train steps ... :  50%|████▉     | 49684/100000 [14:31:05<8:10:28,  1.71it/s]
Train steps ... :  50%|████▉     | 49685/100000 [14:31:05<8:12:05,  1.70it/s]
Train steps ... :  50%|████▉     | 49686/100000 [14:31:06<8:12:25,  1.70it/s]
Train steps ... :  50%|████▉     | 49687/100000 [14:31:06<8:12:15,  1.70it/s]
Train steps ... :  50%|████▉     | 49688/100000 [14:31:07<8:11:31,  1.71it/s]
Train steps ... :  50%|████▉     | 49689/100000 [14:31:08<8:12:53,  1.70it/s]
Train steps ... :  50%|████▉     | 49690/100000 [14:31:08<8:12:18,  1.70it/s]
Train steps ... :  50%|████▉     | 49691/100000 [14:31:09<8:12:18,  1.70it/s]
Train steps ... :  50%|████▉     | 49692/100000 [14:31:09<8:12:14,  1.70it/s]
Train steps ... :  50%|████▉     | 49693/100000 [14:31:10<8:12:12,  1.70it/s]
Train steps ... :  50%|████▉     | 49694/100000 [14:31:10<8:13:00,  1.70it/s]
Train steps ... :  50%|████▉     | 49695/100000 [14:31:11<8:11:56,  1.70it/s]
Train steps ... :  50%|████▉     | 49696/100000 [14:31:12<8:12:27,  1.70it/s]
Train steps ... :  50%|████▉     | 49697/100000 [14:31:12<8:11:22,  1.71it/s]
Train steps ... :  50%|████▉     | 49698/100000 [14:31:13<8:14:04,  1.70it/s]
Train steps ... :  50%|████▉     | 49699/100000 [14:31:13<8:13:22,  1.70it/s]
Train steps ... :  50%|████▉     | 49700/100000 [14:31:14<8:13:29,  1.70it/s]Step... (49700 / 100000 | Loss: 0.9616508483886719, Learning Rate: 5.0552763819095484e-05)
+
                                                                             
Step... (49700 / 100000 | Loss: 0.8214985132217407, Learning Rate: 5.0552763819095484e-05)
+
Train steps ... :  50%|████▉     | 49700/100000 [14:31:14<8:13:29,  1.70it/s]
Train steps ... :  50%|████▉     | 49701/100000 [14:31:15<8:12:10,  1.70it/s]
Train steps ... :  50%|████▉     | 49702/100000 [14:31:15<8:11:56,  1.70it/s]
Train steps ... :  50%|████▉     | 49703/100000 [14:31:16<8:11:43,  1.70it/s]
Train steps ... :  50%|████▉     | 49704/100000 [14:31:16<8:11:56,  1.70it/s]
Train steps ... :  50%|████▉     | 49705/100000 [14:31:17<8:10:58,  1.71it/s]
Train steps ... :  50%|████▉     | 49706/100000 [14:31:17<8:11:09,  1.71it/s]
Train steps ... :  50%|████▉     | 49707/100000 [14:31:18<8:12:46,  1.70it/s]
Train steps ... :  50%|████▉     | 49708/100000 [14:31:19<8:11:30,  1.71it/s]
Train steps ... :  50%|████▉     | 49709/100000 [14:31:19<8:10:37,  1.71it/s]
Train steps ... :  50%|████▉     | 49710/100000 [14:31:20<8:10:31,  1.71it/s]
Train steps ... :  50%|████▉     | 49711/100000 [14:31:20<8:11:04,  1.71it/s]
Train steps ... :  50%|████▉     | 49712/100000 [14:31:21<8:10:34,  1.71it/s]
Train steps ... :  50%|████▉     | 49713/100000 [14:31:22<8:10:33,  1.71it/s]
Train steps ... :  50%|████▉     | 49714/100000 [14:31:22<8:11:28,  1.71it/s]
Train steps ... :  50%|████▉     | 49715/100000 [14:31:23<8:10:58,  1.71it/s]
Train steps ... :  50%|████▉     | 49716/100000 [14:31:23<8:10:46,  1.71it/s]
Train steps ... :  50%|████▉     | 49717/100000 [14:31:24<8:10:20,  1.71it/s]
Train steps ... :  50%|████▉     | 49718/100000 [14:31:25<8:11:29,  1.71it/s]
Train steps ... :  50%|████▉     | 49719/100000 [14:31:25<8:11:09,  1.71it/s]
Train steps ... :  50%|████▉     | 49720/100000 [14:31:26<8:10:57,  1.71it/s]
Train steps ... :  50%|████▉     | 49721/100000 [14:31:26<8:12:26,  1.70it/s]
Train steps ... :  50%|████▉     | 49722/100000 [14:31:27<8:11:29,  1.70it/s]
Train steps ... :  50%|████▉     | 49723/100000 [14:31:27<8:10:39,  1.71it/s]
Train steps ... :  50%|████▉     | 49724/100000 [14:31:28<8:10:57,  1.71it/s]
Train steps ... :  50%|████▉     | 49725/100000 [14:31:29<8:11:16,  1.71it/s]Step... (49725 / 100000 | Loss: 0.6777148842811584, Learning Rate: 5.052763819095477e-05)
+
                                                                             
Step... (49725 / 100000 | Loss: 0.6471072435379028, Learning Rate: 5.052763819095477e-05)
+
Train steps ... :  50%|████▉     | 49725/100000 [14:31:29<8:11:16,  1.71it/s]
Train steps ... :  50%|████▉     | 49726/100000 [14:31:29<8:11:09,  1.71it/s]
Train steps ... :  50%|████▉     | 49727/100000 [14:31:30<8:11:41,  1.70it/s]
Train steps ... :  50%|████▉     | 49728/100000 [14:31:30<8:10:53,  1.71it/s]
Train steps ... :  50%|████▉     | 49729/100000 [14:31:31<8:11:17,  1.71it/s]
Train steps ... :  50%|████▉     | 49730/100000 [14:31:32<8:11:20,  1.71it/s]
Train steps ... :  50%|████▉     | 49731/100000 [14:31:32<8:11:00,  1.71it/s]
Train steps ... :  50%|████▉     | 49732/100000 [14:31:33<8:11:12,  1.71it/s]
Train steps ... :  50%|████▉     | 49733/100000 [14:31:33<8:11:11,  1.71it/s]
Train steps ... :  50%|████▉     | 49734/100000 [14:31:34<8:10:33,  1.71it/s]
Train steps ... :  50%|████▉     | 49735/100000 [14:31:34<8:10:49,  1.71it/s]
Train steps ... :  50%|████▉     | 49736/100000 [14:31:35<8:12:03,  1.70it/s]
Train steps ... :  50%|████▉     | 49737/100000 [14:31:36<8:11:33,  1.70it/s]
Train steps ... :  50%|████▉     | 49738/100000 [14:31:36<8:10:44,  1.71it/s]
Train steps ... :  50%|████▉     | 49739/100000 [14:31:37<8:11:10,  1.71it/s]
Train steps ... :  50%|████▉     | 49740/100000 [14:31:37<8:10:36,  1.71it/s]
Train steps ... :  50%|████▉     | 49741/100000 [14:31:38<8:11:30,  1.70it/s]
Train steps ... :  50%|████▉     | 49742/100000 [14:31:39<8:12:23,  1.70it/s]
Train steps ... :  50%|████▉     | 49743/100000 [14:31:39<8:10:03,  1.71it/s]
Train steps ... :  50%|████▉     | 49744/100000 [14:31:40<8:10:08,  1.71it/s]
Train steps ... :  50%|████▉     | 49745/100000 [14:31:40<8:10:47,  1.71it/s]
Train steps ... :  50%|████▉     | 49746/100000 [14:31:41<8:09:52,  1.71it/s]
Train steps ... :  50%|████▉     | 49747/100000 [14:31:42<8:10:56,  1.71it/s]
Train steps ... :  50%|████▉     | 49748/100000 [14:31:42<8:10:36,  1.71it/s]
Train steps ... :  50%|████▉     | 49749/100000 [14:31:43<8:10:36,  1.71it/s]
Train steps ... :  50%|████▉     | 49750/100000 [14:31:43<8:10:24,  1.71it/s]Step... (49750 / 100000 | Loss: 0.8734097480773926, Learning Rate: 5.050251256281408e-05)
+
                                                                             
Step... (49750 / 100000 | Loss: 0.7344032526016235, Learning Rate: 5.050251256281408e-05)
+
Train steps ... :  50%|████▉     | 49750/100000 [14:31:44<8:10:24,  1.71it/s]
Train steps ... :  50%|████▉     | 49751/100000 [14:31:44<8:10:28,  1.71it/s]
Train steps ... :  50%|████▉     | 49752/100000 [14:31:44<8:10:51,  1.71it/s]
Train steps ... :  50%|████▉     | 49753/100000 [14:31:45<8:10:26,  1.71it/s]
Train steps ... :  50%|████▉     | 49754/100000 [14:31:46<8:10:30,  1.71it/s]
Train steps ... :  50%|████▉     | 49755/100000 [14:31:46<8:10:33,  1.71it/s]
Train steps ... :  50%|████▉     | 49756/100000 [14:31:47<8:11:17,  1.70it/s]
Train steps ... :  50%|████▉     | 49757/100000 [14:31:47<8:11:23,  1.70it/s]
Train steps ... :  50%|████▉     | 49758/100000 [14:31:48<8:10:47,  1.71it/s]
Train steps ... :  50%|████▉     | 49759/100000 [14:31:49<8:11:41,  1.70it/s]
Train steps ... :  50%|████▉     | 49760/100000 [14:31:49<8:10:25,  1.71it/s]
Train steps ... :  50%|████▉     | 49761/100000 [14:31:50<8:10:17,  1.71it/s]
Train steps ... :  50%|████▉     | 49762/100000 [14:31:50<8:10:38,  1.71it/s]
Train steps ... :  50%|████▉     | 49763/100000 [14:31:51<8:10:29,  1.71it/s]
Train steps ... :  50%|████▉     | 49764/100000 [14:31:51<8:09:57,  1.71it/s]
Train steps ... :  50%|████▉     | 49765/100000 [14:31:52<8:09:44,  1.71it/s]
Train steps ... :  50%|████▉     | 49766/100000 [14:31:53<8:09:23,  1.71it/s]
Train steps ... :  50%|████▉     | 49767/100000 [14:31:53<8:10:13,  1.71it/s]
Train steps ... :  50%|████▉     | 49768/100000 [14:31:54<8:10:18,  1.71it/s]
Train steps ... :  50%|████▉     | 49769/100000 [14:31:54<8:10:17,  1.71it/s]
Train steps ... :  50%|████▉     | 49770/100000 [14:31:55<8:10:20,  1.71it/s]
Train steps ... :  50%|████▉     | 49771/100000 [14:31:56<8:10:27,  1.71it/s]
Train steps ... :  50%|████▉     | 49772/100000 [14:31:56<8:10:00,  1.71it/s]
Train steps ... :  50%|████▉     | 49773/100000 [14:31:57<8:10:54,  1.71it/s]
Train steps ... :  50%|████▉     | 49774/100000 [14:31:57<8:10:36,  1.71it/s]
Train steps ... :  50%|████▉     | 49775/100000 [14:31:58<8:11:18,  1.70it/s]Step... (49775 / 100000 | Loss: 1.014575719833374, Learning Rate: 5.0477386934673367e-05)
+
                                                                             
Step... (49775 / 100000 | Loss: 0.7533925771713257, Learning Rate: 5.0477386934673367e-05)
+
Train steps ... :  50%|████▉     | 49775/100000 [14:31:58<8:11:18,  1.70it/s]
Train steps ... :  50%|████▉     | 49776/100000 [14:31:59<8:11:58,  1.70it/s]
Train steps ... :  50%|████▉     | 49777/100000 [14:31:59<8:11:31,  1.70it/s]
Train steps ... :  50%|████▉     | 49778/100000 [14:32:00<8:12:11,  1.70it/s]
Train steps ... :  50%|████▉     | 49779/100000 [14:32:00<8:12:03,  1.70it/s]
Train steps ... :  50%|████▉     | 49780/100000 [14:32:01<8:11:59,  1.70it/s]
Train steps ... :  50%|████▉     | 49781/100000 [14:32:01<8:12:00,  1.70it/s]
Train steps ... :  50%|████▉     | 49782/100000 [14:32:02<8:11:21,  1.70it/s]
Train steps ... :  50%|████▉     | 49783/100000 [14:32:03<8:10:20,  1.71it/s]
Train steps ... :  50%|████▉     | 49784/100000 [14:32:03<8:10:10,  1.71it/s]
Train steps ... :  50%|████▉     | 49785/100000 [14:32:04<8:10:07,  1.71it/s]
Train steps ... :  50%|████▉     | 49786/100000 [14:32:04<8:10:59,  1.70it/s]
Train steps ... :  50%|████▉     | 49787/100000 [14:32:05<8:11:45,  1.70it/s]
Train steps ... :  50%|████▉     | 49788/100000 [14:32:06<8:10:58,  1.70it/s]
Train steps ... :  50%|████▉     | 49789/100000 [14:32:06<8:10:47,  1.71it/s]
Train steps ... :  50%|████▉     | 49790/100000 [14:32:07<8:11:15,  1.70it/s]
Train steps ... :  50%|████▉     | 49791/100000 [14:32:07<8:11:02,  1.70it/s]
Train steps ... :  50%|████▉     | 49792/100000 [14:32:08<8:10:44,  1.71it/s]
Train steps ... :  50%|████▉     | 49793/100000 [14:32:08<8:10:06,  1.71it/s]
Train steps ... :  50%|████▉     | 49794/100000 [14:32:09<8:09:50,  1.71it/s]
Train steps ... :  50%|████▉     | 49795/100000 [14:32:10<8:09:42,  1.71it/s]
Train steps ... :  50%|████▉     | 49796/100000 [14:32:10<8:09:52,  1.71it/s]
Train steps ... :  50%|████▉     | 49797/100000 [14:32:11<8:09:47,  1.71it/s]
Train steps ... :  50%|████▉     | 49798/100000 [14:32:11<8:09:12,  1.71it/s]
Train steps ... :  50%|████▉     | 49799/100000 [14:32:12<8:10:22,  1.71it/s]
Train steps ... :  50%|████▉     | 49800/100000 [14:32:13<8:10:20,  1.71it/s]Step... (49800 / 100000 | Loss: 0.798861026763916, Learning Rate: 5.045226130653266e-05)
+
                                                                             
Step... (49800 / 100000 | Loss: 0.758658766746521, Learning Rate: 5.045226130653266e-05)
+
Train steps ... :  50%|████▉     | 49800/100000 [14:32:13<8:10:20,  1.71it/s]
Train steps ... :  50%|████▉     | 49801/100000 [14:32:13<8:11:25,  1.70it/s]
Train steps ... :  50%|████▉     | 49802/100000 [14:32:14<8:10:56,  1.70it/s]
Train steps ... :  50%|████▉     | 49803/100000 [14:32:14<8:10:41,  1.70it/s]
Train steps ... :  50%|████▉     | 49804/100000 [14:32:15<8:10:55,  1.70it/s]
Train steps ... :  50%|████▉     | 49805/100000 [14:32:16<8:10:51,  1.70it/s]
Train steps ... :  50%|████▉     | 49806/100000 [14:32:16<8:11:47,  1.70it/s]
Train steps ... :  50%|████▉     | 49807/100000 [14:32:17<8:12:06,  1.70it/s]
Train steps ... :  50%|████▉     | 49808/100000 [14:32:17<8:11:31,  1.70it/s]
Train steps ... :  50%|████▉     | 49809/100000 [14:32:18<8:10:56,  1.70it/s]
Train steps ... :  50%|████▉     | 49810/100000 [14:32:18<8:10:15,  1.71it/s]
Train steps ... :  50%|████▉     | 49811/100000 [14:32:19<8:10:07,  1.71it/s]
Train steps ... :  50%|████▉     | 49812/100000 [14:32:20<8:10:08,  1.71it/s]
Train steps ... :  50%|████▉     | 49813/100000 [14:32:20<8:09:16,  1.71it/s]
Train steps ... :  50%|████▉     | 49814/100000 [14:32:21<8:10:14,  1.71it/s]
Train steps ... :  50%|████▉     | 49815/100000 [14:32:21<8:10:38,  1.70it/s]
Train steps ... :  50%|████▉     | 49816/100000 [14:32:22<8:11:40,  1.70it/s]
Train steps ... :  50%|████▉     | 49817/100000 [14:32:23<8:09:55,  1.71it/s]
Train steps ... :  50%|████▉     | 49818/100000 [14:32:23<8:11:17,  1.70it/s]
Train steps ... :  50%|████▉     | 49819/100000 [14:32:24<8:10:57,  1.70it/s]
Train steps ... :  50%|████▉     | 49820/100000 [14:32:24<8:09:49,  1.71it/s]
Train steps ... :  50%|████▉     | 49821/100000 [14:32:25<8:09:35,  1.71it/s]
Train steps ... :  50%|████▉     | 49822/100000 [14:32:25<8:10:05,  1.71it/s]
Train steps ... :  50%|████▉     | 49823/100000 [14:32:26<8:10:19,  1.71it/s]
Train steps ... :  50%|████▉     | 49824/100000 [14:32:27<8:09:48,  1.71it/s]
Train steps ... :  50%|████▉     | 49825/100000 [14:32:27<8:10:28,  1.70it/s]Step... (49825 / 100000 | Loss: 0.8689455986022949, Learning Rate: 5.042713567839196e-05)
+
                                                                             
Step... (49825 / 100000 | Loss: 1.0094190835952759, Learning Rate: 5.042713567839196e-05)
+
Train steps ... :  50%|████▉     | 49825/100000 [14:32:28<8:10:28,  1.70it/s]
Train steps ... :  50%|████▉     | 49826/100000 [14:32:28<8:10:33,  1.70it/s]
Train steps ... :  50%|████▉     | 49827/100000 [14:32:28<8:09:48,  1.71it/s]
Train steps ... :  50%|████▉     | 49828/100000 [14:32:29<8:10:43,  1.70it/s]
Train steps ... :  50%|████▉     | 49829/100000 [14:32:30<8:11:36,  1.70it/s]
Train steps ... :  50%|████▉     | 49830/100000 [14:32:30<8:09:41,  1.71it/s]
Train steps ... :  50%|████▉     | 49831/100000 [14:32:31<8:09:44,  1.71it/s]
Train steps ... :  50%|████▉     | 49832/100000 [14:32:31<8:09:36,  1.71it/s]
Train steps ... :  50%|████▉     | 49833/100000 [14:32:32<8:09:38,  1.71it/s]
Train steps ... :  50%|████▉     | 49834/100000 [14:32:33<8:09:22,  1.71it/s]
Train steps ... :  50%|████▉     | 49835/100000 [14:32:33<8:11:16,  1.70it/s]
Train steps ... :  50%|████▉     | 49836/100000 [14:32:34<8:10:11,  1.71it/s]
Train steps ... :  50%|████▉     | 49837/100000 [14:32:34<8:09:12,  1.71it/s]
Train steps ... :  50%|████▉     | 49838/100000 [14:32:35<8:10:45,  1.70it/s]
Train steps ... :  50%|████▉     | 49839/100000 [14:32:35<8:10:27,  1.70it/s]
Train steps ... :  50%|████▉     | 49840/100000 [14:32:36<8:09:59,  1.71it/s]
Train steps ... :  50%|████▉     | 49841/100000 [14:32:37<8:09:11,  1.71it/s]
Train steps ... :  50%|████▉     | 49842/100000 [14:32:37<8:10:01,  1.71it/s]
Train steps ... :  50%|████▉     | 49843/100000 [14:32:38<8:08:34,  1.71it/s]
Train steps ... :  50%|████▉     | 49844/100000 [14:32:38<8:08:33,  1.71it/s]
Train steps ... :  50%|████▉     | 49845/100000 [14:32:39<8:09:04,  1.71it/s]
Train steps ... :  50%|████▉     | 49846/100000 [14:32:40<8:08:55,  1.71it/s]
Train steps ... :  50%|████▉     | 49847/100000 [14:32:40<8:09:21,  1.71it/s]
Train steps ... :  50%|████▉     | 49848/100000 [14:32:41<8:09:47,  1.71it/s]
Train steps ... :  50%|████▉     | 49849/100000 [14:32:41<8:10:35,  1.70it/s]
Train steps ... :  50%|████▉     | 49850/100000 [14:32:42<8:10:18,  1.70it/s]Step... (49850 / 100000 | Loss: 0.5541105270385742, Learning Rate: 5.0402010050251256e-05)
+
                                                                             
Step... (49850 / 100000 | Loss: 0.7987469434738159, Learning Rate: 5.0402010050251256e-05)
+
Train steps ... :  50%|████▉     | 49850/100000 [14:32:42<8:10:18,  1.70it/s]
Train steps ... :  50%|████▉     | 49851/100000 [14:32:42<8:11:08,  1.70it/s]
Train steps ... :  50%|████▉     | 49852/100000 [14:32:43<8:09:00,  1.71it/s]
Train steps ... :  50%|████▉     | 49853/100000 [14:32:44<8:08:37,  1.71it/s]
Train steps ... :  50%|████▉     | 49854/100000 [14:32:44<8:09:04,  1.71it/s]
Train steps ... :  50%|████▉     | 49855/100000 [14:32:45<8:08:56,  1.71it/s]
Train steps ... :  50%|████▉     | 49856/100000 [14:32:45<8:09:41,  1.71it/s]
Train steps ... :  50%|████▉     | 49857/100000 [14:32:46<8:10:38,  1.70it/s]
Train steps ... :  50%|████▉     | 49858/100000 [14:32:47<8:09:58,  1.71it/s]
Train steps ... :  50%|████▉     | 49859/100000 [14:32:47<8:10:33,  1.70it/s]
Train steps ... :  50%|████▉     | 49860/100000 [14:32:48<8:10:21,  1.70it/s]
Train steps ... :  50%|████▉     | 49861/100000 [14:32:48<8:10:47,  1.70it/s]
Train steps ... :  50%|████▉     | 49862/100000 [14:32:49<8:10:06,  1.70it/s]
Train steps ... :  50%|████▉     | 49863/100000 [14:32:50<8:09:36,  1.71it/s]
Train steps ... :  50%|████▉     | 49864/100000 [14:32:50<8:09:12,  1.71it/s]
Train steps ... :  50%|████▉     | 49865/100000 [14:32:51<8:11:33,  1.70it/s]
Train steps ... :  50%|████▉     | 49866/100000 [14:32:51<8:09:14,  1.71it/s]
Train steps ... :  50%|████▉     | 49867/100000 [14:32:52<8:10:26,  1.70it/s]
Train steps ... :  50%|████▉     | 49868/100000 [14:32:52<8:08:59,  1.71it/s]
Train steps ... :  50%|████▉     | 49869/100000 [14:32:53<8:11:34,  1.70it/s]
Train steps ... :  50%|████▉     | 49870/100000 [14:32:54<8:11:49,  1.70it/s]
Train steps ... :  50%|████▉     | 49871/100000 [14:32:54<8:10:04,  1.70it/s]
Train steps ... :  50%|████▉     | 49872/100000 [14:32:55<8:09:54,  1.71it/s]
Train steps ... :  50%|████▉     | 49873/100000 [14:32:55<8:09:44,  1.71it/s]
Train steps ... :  50%|████▉     | 49874/100000 [14:32:56<8:09:16,  1.71it/s]
Train steps ... :  50%|████▉     | 49875/100000 [14:32:57<8:10:06,  1.70it/s]Step... (49875 / 100000 | Loss: 0.7217815518379211, Learning Rate: 5.037688442211056e-05)
+
                                                                             
Step... (49875 / 100000 | Loss: 0.7219710946083069, Learning Rate: 5.037688442211056e-05)
+
Train steps ... :  50%|████▉     | 49875/100000 [14:32:57<8:10:06,  1.70it/s]
Train steps ... :  50%|████▉     | 49876/100000 [14:32:57<8:08:55,  1.71it/s]
Train steps ... :  50%|████▉     | 49877/100000 [14:32:58<8:08:25,  1.71it/s]
Train steps ... :  50%|████▉     | 49878/100000 [14:32:58<8:08:42,  1.71it/s]
Train steps ... :  50%|████▉     | 49879/100000 [14:32:59<8:08:26,  1.71it/s]
Train steps ... :  50%|████▉     | 49880/100000 [14:32:59<8:11:38,  1.70it/s]
Train steps ... :  50%|████▉     | 49881/100000 [14:33:00<8:09:31,  1.71it/s]
Train steps ... :  50%|████▉     | 49882/100000 [14:33:01<8:09:30,  1.71it/s]
Train steps ... :  50%|████▉     | 49883/100000 [14:33:01<8:08:48,  1.71it/s]
Train steps ... :  50%|████▉     | 49884/100000 [14:33:02<8:09:28,  1.71it/s]
Train steps ... :  50%|████▉     | 49885/100000 [14:33:02<8:08:41,  1.71it/s]
Train steps ... :  50%|████▉     | 49886/100000 [14:33:03<8:08:33,  1.71it/s]
Train steps ... :  50%|████▉     | 49887/100000 [14:33:04<8:09:12,  1.71it/s]
Train steps ... :  50%|████▉     | 49888/100000 [14:33:04<8:09:17,  1.71it/s]
Train steps ... :  50%|████▉     | 49889/100000 [14:33:05<8:09:25,  1.71it/s]
Train steps ... :  50%|████▉     | 49890/100000 [14:33:05<8:09:54,  1.70it/s]
Train steps ... :  50%|████▉     | 49891/100000 [14:33:06<8:09:48,  1.71it/s]
Train steps ... :  50%|████▉     | 49892/100000 [14:33:07<8:08:42,  1.71it/s]
Train steps ... :  50%|████▉     | 49893/100000 [14:33:07<8:09:22,  1.71it/s]
Train steps ... :  50%|████▉     | 49894/100000 [14:33:08<8:08:49,  1.71it/s]
Train steps ... :  50%|████▉     | 49895/100000 [14:33:08<8:08:25,  1.71it/s]
Train steps ... :  50%|████▉     | 49896/100000 [14:33:09<8:09:12,  1.71it/s]
Train steps ... :  50%|████▉     | 49897/100000 [14:33:09<8:08:49,  1.71it/s]
Train steps ... :  50%|████▉     | 49898/100000 [14:33:10<8:08:33,  1.71it/s]
Train steps ... :  50%|████▉     | 49899/100000 [14:33:11<8:08:53,  1.71it/s]
Train steps ... :  50%|████▉     | 49900/100000 [14:33:11<8:09:06,  1.71it/s]Step... (49900 / 100000 | Loss: 0.8494250774383545, Learning Rate: 5.035175879396985e-05)
+
                                                                             
Step... (49900 / 100000 | Loss: 1.0488642454147339, Learning Rate: 5.035175879396985e-05)
+
Train steps ... :  50%|████▉     | 49900/100000 [14:33:12<8:09:06,  1.71it/s]
Train steps ... :  50%|████▉     | 49901/100000 [14:33:12<8:09:46,  1.70it/s]
Train steps ... :  50%|████▉     | 49902/100000 [14:33:12<8:09:38,  1.71it/s]
Train steps ... :  50%|████▉     | 49903/100000 [14:33:13<8:09:50,  1.70it/s]
Train steps ... :  50%|████▉     | 49904/100000 [14:33:14<8:09:12,  1.71it/s]
Train steps ... :  50%|████▉     | 49905/100000 [14:33:14<8:09:48,  1.70it/s]
Train steps ... :  50%|████▉     | 49906/100000 [14:33:15<8:10:04,  1.70it/s]
Train steps ... :  50%|████▉     | 49907/100000 [14:33:15<8:10:01,  1.70it/s]
Train steps ... :  50%|████▉     | 49908/100000 [14:33:16<8:09:57,  1.70it/s]
Train steps ... :  50%|████▉     | 49909/100000 [14:33:16<8:10:22,  1.70it/s]
Train steps ... :  50%|████▉     | 49910/100000 [14:33:17<8:08:49,  1.71it/s]
Train steps ... :  50%|████▉     | 49911/100000 [14:33:18<8:09:08,  1.71it/s]
Train steps ... :  50%|████▉     | 49912/100000 [14:33:18<8:09:04,  1.71it/s]
Train steps ... :  50%|████▉     | 49913/100000 [14:33:19<8:08:40,  1.71it/s]
Train steps ... :  50%|████▉     | 49914/100000 [14:33:19<8:08:30,  1.71it/s]
Train steps ... :  50%|████▉     | 49915/100000 [14:33:20<8:08:36,  1.71it/s]
Train steps ... :  50%|████▉     | 49916/100000 [14:33:21<8:09:57,  1.70it/s]
Train steps ... :  50%|████▉     | 49917/100000 [14:33:21<8:09:14,  1.71it/s]
Train steps ... :  50%|████▉     | 49918/100000 [14:33:22<8:09:13,  1.71it/s]
Train steps ... :  50%|████▉     | 49919/100000 [14:33:22<8:10:08,  1.70it/s]
Train steps ... :  50%|████▉     | 49920/100000 [14:33:23<8:09:13,  1.71it/s]
Train steps ... :  50%|████▉     | 49921/100000 [14:33:24<8:09:14,  1.71it/s]
Train steps ... :  50%|████▉     | 49922/100000 [14:33:24<8:09:54,  1.70it/s]
Train steps ... :  50%|████▉     | 49923/100000 [14:33:25<8:09:16,  1.71it/s]
Train steps ... :  50%|████▉     | 49924/100000 [14:33:25<8:08:35,  1.71it/s]
Train steps ... :  50%|████▉     | 49925/100000 [14:33:26<8:09:24,  1.71it/s]Step... (49925 / 100000 | Loss: 0.930310070514679, Learning Rate: 5.032663316582915e-05)
+
                                                                             
Step... (49925 / 100000 | Loss: 1.107692837715149, Learning Rate: 5.032663316582915e-05)
+
Train steps ... :  50%|████▉     | 49925/100000 [14:33:26<8:09:24,  1.71it/s]
Train steps ... :  50%|████▉     | 49926/100000 [14:33:26<8:09:16,  1.71it/s]
Train steps ... :  50%|████▉     | 49927/100000 [14:33:27<8:09:06,  1.71it/s]
Train steps ... :  50%|████▉     | 49928/100000 [14:33:28<8:09:49,  1.70it/s]
Train steps ... :  50%|████▉     | 49929/100000 [14:33:28<8:09:44,  1.70it/s]
Train steps ... :  50%|████▉     | 49930/100000 [14:33:29<8:09:29,  1.70it/s]
Train steps ... :  50%|████▉     | 49931/100000 [14:33:29<8:08:54,  1.71it/s]
Train steps ... :  50%|████▉     | 49932/100000 [14:33:30<8:10:00,  1.70it/s]
Train steps ... :  50%|████▉     | 49933/100000 [14:33:31<8:08:57,  1.71it/s]
Train steps ... :  50%|████▉     | 49934/100000 [14:33:31<8:08:48,  1.71it/s]
Train steps ... :  50%|████▉     | 49935/100000 [14:33:32<8:08:20,  1.71it/s]
Train steps ... :  50%|████▉     | 49936/100000 [14:33:32<8:09:23,  1.70it/s]
Train steps ... :  50%|████▉     | 49937/100000 [14:33:33<8:08:46,  1.71it/s]
Train steps ... :  50%|████▉     | 49938/100000 [14:33:33<8:09:20,  1.71it/s]
Train steps ... :  50%|████▉     | 49939/100000 [14:33:34<8:08:58,  1.71it/s]
Train steps ... :  50%|████▉     | 49940/100000 [14:33:35<8:08:03,  1.71it/s]
Train steps ... :  50%|████▉     | 49941/100000 [14:33:35<8:07:42,  1.71it/s]
Train steps ... :  50%|████▉     | 49942/100000 [14:33:36<8:07:36,  1.71it/s]
Train steps ... :  50%|████▉     | 49943/100000 [14:33:36<8:07:59,  1.71it/s]
Train steps ... :  50%|████▉     | 49944/100000 [14:33:37<8:10:17,  1.70it/s]
Train steps ... :  50%|████▉     | 49945/100000 [14:33:38<8:13:13,  1.69it/s]
Train steps ... :  50%|████▉     | 49946/100000 [14:33:38<8:14:05,  1.69it/s]
Train steps ... :  50%|████▉     | 49947/100000 [14:33:39<8:10:15,  1.70it/s]
Train steps ... :  50%|████▉     | 49948/100000 [14:33:39<8:09:41,  1.70it/s]
Train steps ... :  50%|████▉     | 49949/100000 [14:33:40<8:09:40,  1.70it/s]
Train steps ... :  50%|████▉     | 49950/100000 [14:33:41<8:08:27,  1.71it/s]Step... (49950 / 100000 | Loss: 0.7691114544868469, Learning Rate: 5.030150753768844e-05)
+
                                                                             
Step... (49950 / 100000 | Loss: 0.970625102519989, Learning Rate: 5.030150753768844e-05)
+
Train steps ... :  50%|████▉     | 49950/100000 [14:33:41<8:08:27,  1.71it/s]
Train steps ... :  50%|��███▉     | 49951/100000 [14:33:41<8:09:13,  1.71it/s]
Train steps ... :  50%|████▉     | 49952/100000 [14:33:42<8:07:39,  1.71it/s]
Train steps ... :  50%|████▉     | 49953/100000 [14:33:42<8:07:45,  1.71it/s]
Train steps ... :  50%|████▉     | 49954/100000 [14:33:43<8:08:29,  1.71it/s]
Train steps ... :  50%|████▉     | 49955/100000 [14:33:43<8:08:48,  1.71it/s]
Train steps ... :  50%|████▉     | 49956/100000 [14:33:44<8:08:39,  1.71it/s]
Train steps ... :  50%|████▉     | 49957/100000 [14:33:45<8:08:01,  1.71it/s]
Train steps ... :  50%|████▉     | 49958/100000 [14:33:45<8:08:21,  1.71it/s]
Train steps ... :  50%|████▉     | 49959/100000 [14:33:46<8:08:02,  1.71it/s]
Train steps ... :  50%|████▉     | 49960/100000 [14:33:46<8:08:11,  1.71it/s]
Train steps ... :  50%|████▉     | 49961/100000 [14:33:47<8:07:36,  1.71it/s]
Train steps ... :  50%|████▉     | 49962/100000 [14:33:48<8:07:35,  1.71it/s]
Train steps ... :  50%|████▉     | 49963/100000 [14:33:48<8:07:00,  1.71it/s]
Train steps ... :  50%|████▉     | 49964/100000 [14:33:49<8:07:10,  1.71it/s]
Train steps ... :  50%|████▉     | 49965/100000 [14:33:49<8:07:13,  1.71it/s]
Train steps ... :  50%|████▉     | 49966/100000 [14:33:50<8:07:30,  1.71it/s]
Train steps ... :  50%|████▉     | 49967/100000 [14:33:50<8:07:52,  1.71it/s]
Train steps ... :  50%|████▉     | 49968/100000 [14:33:51<8:07:50,  1.71it/s]
Train steps ... :  50%|████▉     | 49969/100000 [14:33:52<8:07:37,  1.71it/s]
Train steps ... :  50%|████▉     | 49970/100000 [14:33:52<8:07:35,  1.71it/s]
Train steps ... :  50%|████▉     | 49971/100000 [14:33:53<8:07:54,  1.71it/s]
Train steps ... :  50%|████▉     | 49972/100000 [14:33:53<8:07:11,  1.71it/s]
Train steps ... :  50%|████▉     | 49973/100000 [14:33:54<8:07:13,  1.71it/s]
Train steps ... :  50%|████▉     | 49974/100000 [14:33:55<8:07:16,  1.71it/s]
Train steps ... :  50%|████▉     | 49975/100000 [14:33:55<8:06:44,  1.71it/s]Step... (49975 / 100000 | Loss: 0.9665374755859375, Learning Rate: 5.027638190954774e-05)
+
                                                                             
Step... (49975 / 100000 | Loss: 0.9111475944519043, Learning Rate: 5.027638190954774e-05)
+
Train steps ... :  50%|████▉     | 49975/100000 [14:33:55<8:06:44,  1.71it/s]
Train steps ... :  50%|████▉     | 49976/100000 [14:33:56<8:06:51,  1.71it/s]
Train steps ... :  50%|████▉     | 49977/100000 [14:33:56<8:07:00,  1.71it/s]
Train steps ... :  50%|████▉     | 49978/100000 [14:33:57<8:06:33,  1.71it/s]
Train steps ... :  50%|████▉     | 49979/100000 [14:33:57<8:06:28,  1.71it/s]
Train steps ... :  50%|████▉     | 49980/100000 [14:33:58<8:06:49,  1.71it/s]
Train steps ... :  50%|████▉     | 49981/100000 [14:33:59<8:06:55,  1.71it/s]
Train steps ... :  50%|████▉     | 49982/100000 [14:33:59<8:07:10,  1.71it/s]
Train steps ... :  50%|████▉     | 49983/100000 [14:34:00<8:06:57,  1.71it/s]
Train steps ... :  50%|████▉     | 49984/100000 [14:34:00<8:07:09,  1.71it/s]
Train steps ... :  50%|████▉     | 49985/100000 [14:34:01<8:07:11,  1.71it/s]
Train steps ... :  50%|████▉     | 49986/100000 [14:34:02<8:07:04,  1.71it/s]
Train steps ... :  50%|████▉     | 49987/100000 [14:34:02<8:07:03,  1.71it/s]
Train steps ... :  50%|████▉     | 49988/100000 [14:34:03<8:07:13,  1.71it/s]
Train steps ... :  50%|████▉     | 49989/100000 [14:34:03<8:08:04,  1.71it/s]
Train steps ... :  50%|████▉     | 49990/100000 [14:34:04<8:07:36,  1.71it/s]
Train steps ... :  50%|████▉     | 49991/100000 [14:34:04<8:07:45,  1.71it/s]
Train steps ... :  50%|████▉     | 49992/100000 [14:34:05<8:09:00,  1.70it/s]
Train steps ... :  50%|████▉     | 49993/100000 [14:34:06<8:08:26,  1.71it/s]
Train steps ... :  50%|████▉     | 49994/100000 [14:34:06<8:09:03,  1.70it/s]
Train steps ... :  50%|████▉     | 49995/100000 [14:34:07<8:08:11,  1.71it/s]
Train steps ... :  50%|████▉     | 49996/100000 [14:34:07<8:08:43,  1.71it/s]
Train steps ... :  50%|████▉     | 49997/100000 [14:34:08<8:08:21,  1.71it/s]
Train steps ... :  50%|████▉     | 49998/100000 [14:34:09<8:07:45,  1.71it/s]
Train steps ... :  50%|████▉     | 49999/100000 [14:34:09<8:08:27,  1.71it/s]
Train steps ... :  50%|█████     | 50000/100000 [14:34:10<8:07:44,  1.71it/s]Step... (50000 / 100000 | Loss: 0.894769549369812, Learning Rate: 5.0251256281407036e-05)
+
                                                                             
Step... (50000 / 100000 | Loss: 1.0980583429336548, Learning Rate: 5.0251256281407036e-05)
+
Train steps ... :  50%|█████     | 50000/100000 [14:34:10<8:07:44,  1.71it/s]06/18/2024 06:28:37 - INFO - accelerate.accelerator - Saving current state to ./checkpoint-50000-epoch-2
+06/18/2024 06:28:37 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/18/2024 06:28:40 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-50000-epoch-2/model.safetensors
+06/18/2024 06:28:40 - WARNING - accelerate.utils.other - Removed shared tensor {'proj_out.weight'} while saving. This should be OK, but check by verifying that you don't receive any warning while reloading
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Model weights saved in checkpoint-50000-epoch-2/model_1.safetensors
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Optimizer state saved in checkpoint-50000-epoch-2/optimizer.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Scheduler state saved in checkpoint-50000-epoch-2/scheduler.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 0 saved in checkpoint-50000-epoch-2/sampler.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 1 saved in checkpoint-50000-epoch-2/sampler_1.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 2 saved in checkpoint-50000-epoch-2/sampler_2.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 3 saved in checkpoint-50000-epoch-2/sampler_3.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 4 saved in checkpoint-50000-epoch-2/sampler_4.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 5 saved in checkpoint-50000-epoch-2/sampler_5.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 6 saved in checkpoint-50000-epoch-2/sampler_6.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 7 saved in checkpoint-50000-epoch-2/sampler_7.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 8 saved in checkpoint-50000-epoch-2/sampler_8.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 9 saved in checkpoint-50000-epoch-2/sampler_9.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 10 saved in checkpoint-50000-epoch-2/sampler_10.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Sampler state for dataloader 11 saved in checkpoint-50000-epoch-2/sampler_11.bin
+06/18/2024 06:28:45 - INFO - accelerate.checkpointing - Random states saved in checkpoint-50000-epoch-2/random_states_0.pkl
+06/18/2024 06:28:45 - INFO - __main__ - Deleting older checkpoint [checkpoint-25000-epoch-1] due to args.save_total_limit
+
+
  0%|          | 0/5 [00:00<?, ?it/s]
+
 20%|██        | 1/5 [01:44<06:59, 104.90s/it]
+
 40%|████      | 2/5 [02:18<03:09, 63.04s/it] 
+
 60%|██████    | 3/5 [02:19<01:09, 34.52s/it]
+
 80%|████████  | 4/5 [02:19<00:21, 21.13s/it]
+
100%|██████████| 5/5 [02:20<00:00, 13.70s/it]
100%|██████████| 5/5 [02:20<00:00, 28.07s/it]