Training in progress, step 9850, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52fa49c9aee53eccacfc20fa0a53e81c66a2d9d79fadbf39a861f03d505a8dc4
+oid sha256:67368ddbf8acaee4b2e60cc9ba051abf07b5d10e051dcc5182ce50369b432dfe
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c16a6ae3dbdee2c3d74d8c96a643a478a246c38052a582fabe164c53a454d5b0
+oid sha256:54f5cdb890790a8f1f38ce61319d076a5cdd3cfeecff92d19d4ab2ef594e650d
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f8d076674adacf33d6e96dcffeac08e85cb7bfeb9c3481b82797b68933114a
+oid sha256:42ddc652bb0436a0cd163a32dd0eb325e68cb34ddcfcb9b1bf0806c257f0cc63
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 75.6923076923077,
+  "epoch": 75.76923076923077,
   "eval_steps": 500,
-  "global_step": 9840,
+  "global_step": 9850,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17720,6 +17720,24 @@
       "mean_token_accuracy": 0.657978093624115,
       "num_tokens": 35886399.0,
       "step": 9840
+    },
+    {
+      "epoch": 75.73076923076923,
+      "grad_norm": 0.0,
+      "learning_rate": 7.8e-07,
+      "loss": 1.7547,
+      "mean_token_accuracy": 0.6459228157997131,
+      "num_tokens": 35904125.0,
+      "step": 9845
+    },
+    {
+      "epoch": 75.76923076923077,
+      "grad_norm": 0.0,
+      "learning_rate": 7.550000000000001e-07,
+      "loss": 1.7782,
+      "mean_token_accuracy": 0.6488775163888931,
+      "num_tokens": 35921829.0,
+      "step": 9850
     }
   ],
   "logging_steps": 5,
@@ -17739,7 +17757,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8198268608990413e+18,
+  "total_flos": 1.821597089600471e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null