Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72812eb4a2663fa8500c7a5809ba3d8d1217fa71da08a4104ac84b2c4baffe49
+oid sha256:c651d278253319c1b93c3b131fc31165efa751e16ffe94eb310a7b4bdfe01084
 size 6425529112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcb53afe4d66917c9a3fdf0d2fb1683d61488399a5c074f28626c3ba952ecd8f
+oid sha256:a43fa5ae43e347ff1e2a0cdec05688f22dd267a5acf33ab37f021f044220db69
 size 12851224679

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d816652875af5b096437609afdf7a105e45a5aed127110ed63352bdde6ad2657
+oid sha256:c8a0161fb643893b4bd0a9724aa51736729cc07ff0a3f386f1ba978002596386
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.78125,
+  "epoch": 1.171875,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -208,6 +208,106 @@
       "mean_token_accuracy": 0.9924442365765571,
       "num_tokens": 5099714.0,
       "step": 1000
+    },
+    {
+      "entropy": 0.032110756486654284,
+      "epoch": 0.8203125,
+      "grad_norm": 0.171875,
+      "learning_rate": 1.3116319444444446e-05,
+      "loss": 0.023927602767944336,
+      "mean_token_accuracy": 0.992151814699173,
+      "num_tokens": 5353934.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.03357607708312571,
+      "epoch": 0.859375,
+      "grad_norm": 0.220703125,
+      "learning_rate": 1.2682291666666669e-05,
+      "loss": 0.024996912479400633,
+      "mean_token_accuracy": 0.9920313712954522,
+      "num_tokens": 5610229.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.03356592872180045,
+      "epoch": 0.8984375,
+      "grad_norm": 0.203125,
+      "learning_rate": 1.2248263888888889e-05,
+      "loss": 0.025175034999847412,
+      "mean_token_accuracy": 0.9921249234676361,
+      "num_tokens": 5862791.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.031079287379980086,
+      "epoch": 0.9375,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 1.1814236111111112e-05,
+      "loss": 0.022713756561279295,
+      "mean_token_accuracy": 0.9926198759675026,
+      "num_tokens": 6121431.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.02976180042140186,
+      "epoch": 0.9765625,
+      "grad_norm": 0.154296875,
+      "learning_rate": 1.1380208333333333e-05,
+      "loss": 0.02123898983001709,
+      "mean_token_accuracy": 0.992766418159008,
+      "num_tokens": 6379675.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.030388496736995875,
+      "epoch": 1.015625,
+      "grad_norm": 0.1650390625,
+      "learning_rate": 1.0946180555555556e-05,
+      "loss": 0.021283388137817383,
+      "mean_token_accuracy": 0.9927816662192345,
+      "num_tokens": 6635287.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.029865577281452716,
+      "epoch": 1.0546875,
+      "grad_norm": 0.265625,
+      "learning_rate": 1.0512152777777778e-05,
+      "loss": 0.021030676364898682,
+      "mean_token_accuracy": 0.9929129666090012,
+      "num_tokens": 6888440.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.031085506100207567,
+      "epoch": 1.09375,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 1.0078125000000001e-05,
+      "loss": 0.02215445041656494,
+      "mean_token_accuracy": 0.9926813915371895,
+      "num_tokens": 7143446.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.03091464822180569,
+      "epoch": 1.1328125,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 9.644097222222222e-06,
+      "loss": 0.022361652851104738,
+      "mean_token_accuracy": 0.9926716023683548,
+      "num_tokens": 7400487.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.029652795745059846,
+      "epoch": 1.171875,
+      "grad_norm": 0.130859375,
+      "learning_rate": 9.210069444444446e-06,
+      "loss": 0.02084646940231323,
+      "mean_token_accuracy": 0.9928994616866111,
+      "num_tokens": 7655674.0,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -227,7 +327,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.663810471217152e+16,
+  "total_flos": 1.453331385078866e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null