Training in progress, step 10000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afefba1d1a51b0c0c5707c5f0d300dff53e678f1bc0b7cae11abdff5b79cefc0
+oid sha256:0de1f5ec1859679a6d81fbe1f7f9bdaf927977eadf9526856493884330fc7c63
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0986320cbe90e75478c532523b0c234fa347d4a4e211046c052aa2086a23dbd2
+oid sha256:2d7ce1e92bdefe35b91b462f44530714b2b86d47908ce3f4713dd413a98a911b
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6103aa69cb523c885f825e3681c3fc82e661052d714c68ca14488001d0b4c231
+oid sha256:5aafa6f75f83dd9e16a017cacae3f09f91ebc664481f1f07d0ced4fb6a26dbd1
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 76.84615384615384,
+  "epoch": 76.92307692307692,
   "eval_steps": 500,
-  "global_step": 9990,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17990,6 +17990,24 @@
       "mean_token_accuracy": 0.6518869757652282,
       "num_tokens": 36274207.0,
       "step": 9990
+    },
+    {
+      "epoch": 76.88461538461539,
+      "grad_norm": 0.0,
+      "learning_rate": 3e-08,
+      "loss": 1.8157,
+      "mean_token_accuracy": 0.6466015040874481,
+      "num_tokens": 36292135.0,
+      "step": 9995
+    },
+    {
+      "epoch": 76.92307692307692,
+      "grad_norm": 0.0,
+      "learning_rate": 5e-09,
+      "loss": 1.7624,
+      "mean_token_accuracy": 0.6548141956329345,
+      "num_tokens": 36310917.0,
+      "step": 10000
     }
   ],
   "logging_steps": 5,
@@ -18004,12 +18022,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.0364275750485197e+18,
+  "total_flos": 1.0374575860589691e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null