sedrickkeh commited on
Commit
45bcf88
·
verified ·
1 Parent(s): 7d6731b

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cc07ca4eaa36fa2e130e174e67e36a2a41b1d0d83dc7d9d9ff8e3afc08dc069
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9008db9c6183128e0de8c1fa17ad5496c1de295196f71d0af9c586cc46f3e55
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6330d8b41fd9ab420074c18eed53d08b2801f0b10db6d2c1409de3e5000731b6
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:876c9f32161d4acbbeb1b7785eb32a3b01059a1dc5349b7f41aa1a8e9ae6ebdf
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:225d62253a6b0eccc296902ae8454e5157249dce2a61cbefe1a41beb9c928681
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e13d7cab83211929682313011b94113b3aa0278a6ebe16eeea1de8ae1deb55fa
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:220cb9557bef435798047779b99525e63d64617bcb6986cdb4ea6b91cb47a15d
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:024c0736eb440621c642149e5b2d40af8d387dbb67625b8808a55c3428358faf
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -88,3 +88,47 @@
88
  {"current_steps": 870, "total_steps": 1320, "loss": 0.5865, "lr": 5e-06, "epoch": 1.974468085106383, "percentage": 65.91, "elapsed_time": "7:58:00", "remaining_time": "4:07:14"}
89
  {"current_steps": 880, "total_steps": 1320, "loss": 0.5869, "lr": 5e-06, "epoch": 1.9971631205673759, "percentage": 66.67, "elapsed_time": "8:03:23", "remaining_time": "4:01:41"}
90
  {"current_steps": 881, "total_steps": 1320, "eval_loss": 0.63065505027771, "epoch": 1.9994326241134752, "percentage": 66.74, "elapsed_time": "8:08:57", "remaining_time": "4:03:38"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  {"current_steps": 870, "total_steps": 1320, "loss": 0.5865, "lr": 5e-06, "epoch": 1.974468085106383, "percentage": 65.91, "elapsed_time": "7:58:00", "remaining_time": "4:07:14"}
89
  {"current_steps": 880, "total_steps": 1320, "loss": 0.5869, "lr": 5e-06, "epoch": 1.9971631205673759, "percentage": 66.67, "elapsed_time": "8:03:23", "remaining_time": "4:01:41"}
90
  {"current_steps": 881, "total_steps": 1320, "eval_loss": 0.63065505027771, "epoch": 1.9994326241134752, "percentage": 66.74, "elapsed_time": "8:08:57", "remaining_time": "4:03:38"}
91
+ {"current_steps": 890, "total_steps": 1320, "loss": 0.5575, "lr": 5e-06, "epoch": 2.0198581560283686, "percentage": 67.42, "elapsed_time": "8:15:00", "remaining_time": "3:59:09"}
92
+ {"current_steps": 900, "total_steps": 1320, "loss": 0.5333, "lr": 5e-06, "epoch": 2.0425531914893615, "percentage": 68.18, "elapsed_time": "8:20:26", "remaining_time": "3:53:32"}
93
+ {"current_steps": 910, "total_steps": 1320, "loss": 0.5281, "lr": 5e-06, "epoch": 2.0652482269503545, "percentage": 68.94, "elapsed_time": "8:25:54", "remaining_time": "3:47:56"}
94
+ {"current_steps": 920, "total_steps": 1320, "loss": 0.5307, "lr": 5e-06, "epoch": 2.0879432624113474, "percentage": 69.7, "elapsed_time": "8:31:20", "remaining_time": "3:42:19"}
95
+ {"current_steps": 930, "total_steps": 1320, "loss": 0.5253, "lr": 5e-06, "epoch": 2.1106382978723404, "percentage": 70.45, "elapsed_time": "8:36:45", "remaining_time": "3:36:42"}
96
+ {"current_steps": 940, "total_steps": 1320, "loss": 0.5321, "lr": 5e-06, "epoch": 2.1333333333333333, "percentage": 71.21, "elapsed_time": "8:42:11", "remaining_time": "3:31:05"}
97
+ {"current_steps": 950, "total_steps": 1320, "loss": 0.5327, "lr": 5e-06, "epoch": 2.1560283687943262, "percentage": 71.97, "elapsed_time": "8:47:37", "remaining_time": "3:25:29"}
98
+ {"current_steps": 960, "total_steps": 1320, "loss": 0.5283, "lr": 5e-06, "epoch": 2.178723404255319, "percentage": 72.73, "elapsed_time": "8:53:03", "remaining_time": "3:19:53"}
99
+ {"current_steps": 970, "total_steps": 1320, "loss": 0.5312, "lr": 5e-06, "epoch": 2.201418439716312, "percentage": 73.48, "elapsed_time": "8:58:29", "remaining_time": "3:14:17"}
100
+ {"current_steps": 980, "total_steps": 1320, "loss": 0.5281, "lr": 5e-06, "epoch": 2.224113475177305, "percentage": 74.24, "elapsed_time": "9:03:53", "remaining_time": "3:08:41"}
101
+ {"current_steps": 990, "total_steps": 1320, "loss": 0.5287, "lr": 5e-06, "epoch": 2.246808510638298, "percentage": 75.0, "elapsed_time": "9:09:19", "remaining_time": "3:03:06"}
102
+ {"current_steps": 1000, "total_steps": 1320, "loss": 0.5349, "lr": 5e-06, "epoch": 2.269503546099291, "percentage": 75.76, "elapsed_time": "9:14:45", "remaining_time": "2:57:31"}
103
+ {"current_steps": 1010, "total_steps": 1320, "loss": 0.5295, "lr": 5e-06, "epoch": 2.2921985815602834, "percentage": 76.52, "elapsed_time": "9:20:10", "remaining_time": "2:51:56"}
104
+ {"current_steps": 1020, "total_steps": 1320, "loss": 0.5323, "lr": 5e-06, "epoch": 2.3148936170212764, "percentage": 77.27, "elapsed_time": "9:25:36", "remaining_time": "2:46:21"}
105
+ {"current_steps": 1030, "total_steps": 1320, "loss": 0.5277, "lr": 5e-06, "epoch": 2.3375886524822693, "percentage": 78.03, "elapsed_time": "9:31:02", "remaining_time": "2:40:46"}
106
+ {"current_steps": 1040, "total_steps": 1320, "loss": 0.5276, "lr": 5e-06, "epoch": 2.3602836879432623, "percentage": 78.79, "elapsed_time": "9:36:28", "remaining_time": "2:35:12"}
107
+ {"current_steps": 1050, "total_steps": 1320, "loss": 0.5295, "lr": 5e-06, "epoch": 2.382978723404255, "percentage": 79.55, "elapsed_time": "9:41:55", "remaining_time": "2:29:38"}
108
+ {"current_steps": 1060, "total_steps": 1320, "loss": 0.5328, "lr": 5e-06, "epoch": 2.405673758865248, "percentage": 80.3, "elapsed_time": "9:47:21", "remaining_time": "2:24:04"}
109
+ {"current_steps": 1070, "total_steps": 1320, "loss": 0.534, "lr": 5e-06, "epoch": 2.428368794326241, "percentage": 81.06, "elapsed_time": "9:52:46", "remaining_time": "2:18:29"}
110
+ {"current_steps": 1080, "total_steps": 1320, "loss": 0.5356, "lr": 5e-06, "epoch": 2.451063829787234, "percentage": 81.82, "elapsed_time": "9:58:13", "remaining_time": "2:12:56"}
111
+ {"current_steps": 1090, "total_steps": 1320, "loss": 0.5306, "lr": 5e-06, "epoch": 2.473758865248227, "percentage": 82.58, "elapsed_time": "10:03:39", "remaining_time": "2:07:22"}
112
+ {"current_steps": 1100, "total_steps": 1320, "loss": 0.5307, "lr": 5e-06, "epoch": 2.49645390070922, "percentage": 83.33, "elapsed_time": "10:09:04", "remaining_time": "2:01:48"}
113
+ {"current_steps": 1110, "total_steps": 1320, "loss": 0.5331, "lr": 5e-06, "epoch": 2.519148936170213, "percentage": 84.09, "elapsed_time": "10:14:28", "remaining_time": "1:56:15"}
114
+ {"current_steps": 1120, "total_steps": 1320, "loss": 0.5363, "lr": 5e-06, "epoch": 2.541843971631206, "percentage": 84.85, "elapsed_time": "10:19:51", "remaining_time": "1:50:41"}
115
+ {"current_steps": 1130, "total_steps": 1320, "loss": 0.5391, "lr": 5e-06, "epoch": 2.5645390070921987, "percentage": 85.61, "elapsed_time": "10:25:12", "remaining_time": "1:45:07"}
116
+ {"current_steps": 1140, "total_steps": 1320, "loss": 0.5299, "lr": 5e-06, "epoch": 2.5872340425531917, "percentage": 86.36, "elapsed_time": "10:30:35", "remaining_time": "1:39:34"}
117
+ {"current_steps": 1150, "total_steps": 1320, "loss": 0.5374, "lr": 5e-06, "epoch": 2.6099290780141846, "percentage": 87.12, "elapsed_time": "10:35:59", "remaining_time": "1:34:01"}
118
+ {"current_steps": 1160, "total_steps": 1320, "loss": 0.5309, "lr": 5e-06, "epoch": 2.6326241134751776, "percentage": 87.88, "elapsed_time": "10:41:23", "remaining_time": "1:28:28"}
119
+ {"current_steps": 1170, "total_steps": 1320, "loss": 0.5293, "lr": 5e-06, "epoch": 2.65531914893617, "percentage": 88.64, "elapsed_time": "10:46:47", "remaining_time": "1:22:55"}
120
+ {"current_steps": 1180, "total_steps": 1320, "loss": 0.5316, "lr": 5e-06, "epoch": 2.678014184397163, "percentage": 89.39, "elapsed_time": "10:52:10", "remaining_time": "1:17:22"}
121
+ {"current_steps": 1190, "total_steps": 1320, "loss": 0.5347, "lr": 5e-06, "epoch": 2.700709219858156, "percentage": 90.15, "elapsed_time": "10:57:36", "remaining_time": "1:11:50"}
122
+ {"current_steps": 1200, "total_steps": 1320, "loss": 0.5339, "lr": 5e-06, "epoch": 2.723404255319149, "percentage": 90.91, "elapsed_time": "11:03:01", "remaining_time": "1:06:18"}
123
+ {"current_steps": 1210, "total_steps": 1320, "loss": 0.5346, "lr": 5e-06, "epoch": 2.746099290780142, "percentage": 91.67, "elapsed_time": "11:08:26", "remaining_time": "1:00:46"}
124
+ {"current_steps": 1220, "total_steps": 1320, "loss": 0.5303, "lr": 5e-06, "epoch": 2.7687943262411348, "percentage": 92.42, "elapsed_time": "11:13:51", "remaining_time": "0:55:14"}
125
+ {"current_steps": 1230, "total_steps": 1320, "loss": 0.5315, "lr": 5e-06, "epoch": 2.7914893617021277, "percentage": 93.18, "elapsed_time": "11:19:16", "remaining_time": "0:49:42"}
126
+ {"current_steps": 1240, "total_steps": 1320, "loss": 0.5367, "lr": 5e-06, "epoch": 2.8141843971631206, "percentage": 93.94, "elapsed_time": "11:24:42", "remaining_time": "0:44:10"}
127
+ {"current_steps": 1250, "total_steps": 1320, "loss": 0.5346, "lr": 5e-06, "epoch": 2.8368794326241136, "percentage": 94.7, "elapsed_time": "11:30:07", "remaining_time": "0:38:38"}
128
+ {"current_steps": 1260, "total_steps": 1320, "loss": 0.5376, "lr": 5e-06, "epoch": 2.8595744680851065, "percentage": 95.45, "elapsed_time": "11:35:32", "remaining_time": "0:33:07"}
129
+ {"current_steps": 1270, "total_steps": 1320, "loss": 0.5294, "lr": 5e-06, "epoch": 2.8822695035460995, "percentage": 96.21, "elapsed_time": "11:40:57", "remaining_time": "0:27:35"}
130
+ {"current_steps": 1280, "total_steps": 1320, "loss": 0.5309, "lr": 5e-06, "epoch": 2.904964539007092, "percentage": 96.97, "elapsed_time": "11:46:22", "remaining_time": "0:22:04"}
131
+ {"current_steps": 1290, "total_steps": 1320, "loss": 0.5359, "lr": 5e-06, "epoch": 2.927659574468085, "percentage": 97.73, "elapsed_time": "11:51:47", "remaining_time": "0:16:33"}
132
+ {"current_steps": 1300, "total_steps": 1320, "loss": 0.531, "lr": 5e-06, "epoch": 2.950354609929078, "percentage": 98.48, "elapsed_time": "11:57:11", "remaining_time": "0:11:02"}
133
+ {"current_steps": 1310, "total_steps": 1320, "loss": 0.5348, "lr": 5e-06, "epoch": 2.9730496453900708, "percentage": 99.24, "elapsed_time": "12:02:37", "remaining_time": "0:05:30"}
134
+ {"current_steps": 1320, "total_steps": 1320, "loss": 0.5325, "lr": 5e-06, "epoch": 2.9957446808510637, "percentage": 100.0, "elapsed_time": "12:08:03", "remaining_time": "0:00:00"}