Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:526cd145d38b5d607d81e63c85c7c52896c874f2136eda50a3ad728915bc0888
+oid sha256:b7e85d31a9400a3e476e57eb02f66875fe02d94a2e7f0498f6daf9772ea3cabf
 size 5228717512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3610d93c47c718418200139666d3cd598641c899018a9797d1f7478a99919c
+oid sha256:795383d344f81ffeed9736876921ab7c34ee1e1e8f7ae853b548fbe86125a4d4
 size 10457622711

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a0161fb643893b4bd0a9724aa51736729cc07ff0a3f386f1ba978002596386
+oid sha256:7949a82b4956d6dc1683588213cba80de08632b440866c7377566d6b5ddef0f6
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.171875,
+  "epoch": 1.5625,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -308,6 +308,106 @@
       "mean_token_accuracy": 0.9931734573841094,
       "num_tokens": 8601406.0,
       "step": 1500
+    },
+    {
+      "entropy": 0.01845017326530069,
+      "epoch": 1.2109375,
+      "grad_norm": 0.087890625,
+      "learning_rate": 8.776041666666667e-06,
+      "loss": 0.017589352130889892,
+      "mean_token_accuracy": 0.9928986424207688,
+      "num_tokens": 8887025.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.016624693870544435,
+      "epoch": 1.25,
+      "grad_norm": 0.138671875,
+      "learning_rate": 8.342013888888889e-06,
+      "loss": 0.015853718519210816,
+      "mean_token_accuracy": 0.9933998480439186,
+      "num_tokens": 9173407.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.018500901735387744,
+      "epoch": 1.2890625,
+      "grad_norm": 0.1142578125,
+      "learning_rate": 7.907986111111112e-06,
+      "loss": 0.017626932859420776,
+      "mean_token_accuracy": 0.9930863061547279,
+      "num_tokens": 9454970.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.01800002105999738,
+      "epoch": 1.328125,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 7.473958333333334e-06,
+      "loss": 0.017116209268569948,
+      "mean_token_accuracy": 0.9930115470290184,
+      "num_tokens": 9739610.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.017908857897855342,
+      "epoch": 1.3671875,
+      "grad_norm": 0.1064453125,
+      "learning_rate": 7.039930555555556e-06,
+      "loss": 0.017099602222442625,
+      "mean_token_accuracy": 0.9931422612071037,
+      "num_tokens": 10028723.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.017319361912086606,
+      "epoch": 1.40625,
+      "grad_norm": 0.14453125,
+      "learning_rate": 6.605902777777779e-06,
+      "loss": 0.016603636741638183,
+      "mean_token_accuracy": 0.9933136883378029,
+      "num_tokens": 10313957.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.017652450683526694,
+      "epoch": 1.4453125,
+      "grad_norm": 0.11572265625,
+      "learning_rate": 6.171875e-06,
+      "loss": 0.01667865037918091,
+      "mean_token_accuracy": 0.9932633358240127,
+      "num_tokens": 10597623.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.01626451033167541,
+      "epoch": 1.484375,
+      "grad_norm": 0.119140625,
+      "learning_rate": 5.737847222222222e-06,
+      "loss": 0.015588784217834472,
+      "mean_token_accuracy": 0.993659851551056,
+      "num_tokens": 10887482.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.016533851716667415,
+      "epoch": 1.5234375,
+      "grad_norm": 0.1630859375,
+      "learning_rate": 5.303819444444445e-06,
+      "loss": 0.01556604504585266,
+      "mean_token_accuracy": 0.9936296039819718,
+      "num_tokens": 11176455.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.017771934717893602,
+      "epoch": 1.5625,
+      "grad_norm": 0.11572265625,
+      "learning_rate": 4.869791666666667e-06,
+      "loss": 0.017040348052978514,
+      "mean_token_accuracy": 0.9932206523418426,
+      "num_tokens": 11462052.0,
+      "step": 2000
     }
   ],
   "logging_steps": 50,
@@ -327,7 +427,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.167079738487593e+17,
+  "total_flos": 1.5546599214235546e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null