Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:227bd2c8b80ed08bd506caf9f8974b149298b2a35c6a99afe695e26b35f7d1ac
+oid sha256:609808d671cf456621d681c77d38f06ef2e18d180fc6620fbf118a53fa336f02
 size 7642181896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c941c0825d68bc50d8fae93abe1fb393ac6d578efef4e1282d9c22797bde6341
+oid sha256:ed7d148862736c7d09fc73ca8d372ff265e692804b954fd181b0e60d469d8d46
 size 15284491207

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": 0.9913999313116073,
       "num_tokens": 6276792.0,
       "step": 1000
+    },
+    {
+      "entropy": 0.0340632925927639,
+      "epoch": 0.8203125,
+      "grad_norm": 0.2080078125,
+      "learning_rate": 1.3116319444444446e-05,
+      "loss": 0.02685004711151123,
+      "mean_token_accuracy": 0.991002170741558,
+      "num_tokens": 6589624.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.035379888685420156,
+      "epoch": 0.859375,
+      "grad_norm": 0.2314453125,
+      "learning_rate": 1.2682291666666669e-05,
+      "loss": 0.027915542125701905,
+      "mean_token_accuracy": 0.9909049591422081,
+      "num_tokens": 6903486.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.03475771216675639,
+      "epoch": 0.8984375,
+      "grad_norm": 0.2353515625,
+      "learning_rate": 1.2248263888888889e-05,
+      "loss": 0.02780653476715088,
+      "mean_token_accuracy": 0.990822182893753,
+      "num_tokens": 7213801.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.03110354512464255,
+      "epoch": 0.9375,
+      "grad_norm": 0.142578125,
+      "learning_rate": 1.1814236111111112e-05,
+      "loss": 0.0244008731842041,
+      "mean_token_accuracy": 0.9916224616765976,
+      "num_tokens": 7528923.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.029425571556203067,
+      "epoch": 0.9765625,
+      "grad_norm": 0.203125,
+      "learning_rate": 1.1380208333333333e-05,
+      "loss": 0.022673423290252685,
+      "mean_token_accuracy": 0.9917887037992478,
+      "num_tokens": 7844272.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.029285581400617957,
+      "epoch": 1.015625,
+      "grad_norm": 0.1982421875,
+      "learning_rate": 1.0946180555555556e-05,
+      "loss": 0.022388596534729004,
+      "mean_token_accuracy": 0.9920673790574074,
+      "num_tokens": 8158883.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.02909859223291278,
+      "epoch": 1.0546875,
+      "grad_norm": 0.2158203125,
+      "learning_rate": 1.0512152777777778e-05,
+      "loss": 0.02216202974319458,
+      "mean_token_accuracy": 0.992148505449295,
+      "num_tokens": 8469055.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.030532640991732477,
+      "epoch": 1.09375,
+      "grad_norm": 0.201171875,
+      "learning_rate": 1.0078125000000001e-05,
+      "loss": 0.023409726619720458,
+      "mean_token_accuracy": 0.9918863570690155,
+      "num_tokens": 8783298.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.030662614218890667,
+      "epoch": 1.1328125,
+      "grad_norm": 0.181640625,
+      "learning_rate": 9.644097222222222e-06,
+      "loss": 0.02406394958496094,
+      "mean_token_accuracy": 0.9918859106302261,
+      "num_tokens": 9098339.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.028511196416802706,
+      "epoch": 1.171875,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 9.210069444444446e-06,
+      "loss": 0.02161515474319458,
+      "mean_token_accuracy": 0.992187882065773,
+      "num_tokens": 9411914.0,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -227,7 +327,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.541804792451195e+17,
+  "total_flos": 2.313945243981988e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null