Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9624baae22c6a192630e8a79071cc4573b4d3cdbcbe8fb33ff72e7b036e6a3bc
+oid sha256:2f4a026c404bc969a7ffd9525e0e09f9ad754bfcdeba16852957bbdd14730316
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a60061a0f9927e1abec1ad90f101effd4a1d73e3d90370b16eee0a742e4960c0
+oid sha256:6d702e73bb6d69b2d6b0a8852dc34a13a9608e5996d840e6028047834f0a1239
 size 71878612

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53b22ccf68cf7aeba6831c521ae4a4a13d9c2feebe608646bb1a22bc9c8467fa
+oid sha256:1367b8da29b12685f3bda94ca45888728f5ec292d5a5ea26009c61e70ba58a2f
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d82963982d21a0217568b4d88915d6d3130fbcc819e6338d0582480e6a19d218
+oid sha256:7813d1f99bc12180249da90693d4a4c2ebcc71aa89e5da0bd27656d407a2d6e9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74a78e6c3d187db1eff1bb7655a5b88602d2edf8541cb97dceb37c12fcb9c792
+oid sha256:4ed4c5b74982bf25fcc59931e6203269f1af04b76488bde5a9d7b431179b3a1e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fff8ca150e754088cce9700a48f2dee877ea176d00af0e7332af58c1fcdffc34
+oid sha256:9ece86263796cfb8bacb59b98b1d336e7aa8ee68ed68db948a3ebe9408609b46
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5288701057434082,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4048582995951417,
+  "best_metric": 1.4314173460006714,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8097165991902834,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 294.854,
       "eval_steps_per_second": 9.236,
       "step": 25
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.0969359874725342,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.3448,
+      "step": 26
+    },
+    {
+      "epoch": 0.43724696356275305,
+      "grad_norm": 1.16632878780365,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.3496,
+      "step": 27
+    },
+    {
+      "epoch": 0.4534412955465587,
+      "grad_norm": 1.0668652057647705,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.1761,
+      "step": 28
+    },
+    {
+      "epoch": 0.46963562753036436,
+      "grad_norm": 0.9689870476722717,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.109,
+      "step": 29
+    },
+    {
+      "epoch": 0.48582995951417,
+      "grad_norm": 0.9078288674354553,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.8696,
+      "step": 30
+    },
+    {
+      "epoch": 0.5020242914979757,
+      "grad_norm": 1.026144027709961,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.6314,
+      "step": 31
+    },
+    {
+      "epoch": 0.5182186234817814,
+      "grad_norm": 1.445268154144287,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8089,
+      "step": 32
+    },
+    {
+      "epoch": 0.5344129554655871,
+      "grad_norm": 1.7678817510604858,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.4337,
+      "step": 33
+    },
+    {
+      "epoch": 0.5506072874493927,
+      "grad_norm": 2.1613621711730957,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.3891,
+      "step": 34
+    },
+    {
+      "epoch": 0.5668016194331984,
+      "grad_norm": 2.175659656524658,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3807,
+      "step": 35
+    },
+    {
+      "epoch": 0.582995951417004,
+      "grad_norm": 1.0014805793762207,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.6756,
+      "step": 36
+    },
+    {
+      "epoch": 0.5991902834008097,
+      "grad_norm": 0.9872593879699707,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.3493,
+      "step": 37
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.8853523135185242,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.1145,
+      "step": 38
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.8329710960388184,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.3212,
+      "step": 39
+    },
+    {
+      "epoch": 0.6477732793522267,
+      "grad_norm": 0.774543285369873,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.265,
+      "step": 40
+    },
+    {
+      "epoch": 0.6639676113360324,
+      "grad_norm": 0.7718155980110168,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.1585,
+      "step": 41
+    },
+    {
+      "epoch": 0.680161943319838,
+      "grad_norm": 0.758331298828125,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.9219,
+      "step": 42
+    },
+    {
+      "epoch": 0.6963562753036437,
+      "grad_norm": 0.8226709365844727,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.8131,
+      "step": 43
+    },
+    {
+      "epoch": 0.7125506072874493,
+      "grad_norm": 0.9785775542259216,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.8923,
+      "step": 44
+    },
+    {
+      "epoch": 0.728744939271255,
+      "grad_norm": 1.1432104110717773,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.6488,
+      "step": 45
+    },
+    {
+      "epoch": 0.7449392712550608,
+      "grad_norm": 1.4502125978469849,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.3185,
+      "step": 46
+    },
+    {
+      "epoch": 0.7611336032388664,
+      "grad_norm": 1.425331950187683,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.2999,
+      "step": 47
+    },
+    {
+      "epoch": 0.7773279352226721,
+      "grad_norm": 0.8650718927383423,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.3693,
+      "step": 48
+    },
+    {
+      "epoch": 0.7935222672064778,
+      "grad_norm": 0.8605427145957947,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.4871,
+      "step": 49
+    },
+    {
+      "epoch": 0.8097165991902834,
+      "grad_norm": 0.8215957283973694,
+      "learning_rate": 0.0,
+      "loss": 1.3633,
+      "step": 50
+    },
+    {
+      "epoch": 0.8097165991902834,
+      "eval_loss": 1.4314173460006714,
+      "eval_runtime": 1.4157,
+      "eval_samples_per_second": 293.137,
+      "eval_steps_per_second": 9.183,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7052240216915968.0,
+  "total_flos": 1.409481984442368e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null