Training in progress, step 9900, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a56ec06dc34cee7dd39d3feb8b68551051c585ab18d67cdd7e55a5bf68feca81
+oid sha256:1bdd30d40fdc2f9ac50eab793f3110ea573c3a4adfe8b977d60752b4b983f47b
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c05818830d152bb21342a2f47225b1ba3da4f5c057a0251e0399bfcc2b8fd27a
+oid sha256:0610da09a40af0fe728bae3b4a3e71cfa910e3c97ca88c05b2bfd8ff6648b6e0
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00adfad39dc29a8ba99da9222898e93d32ae9aefabae1129b73b2933a1864c2c
+oid sha256:fe8c49bf0ee0f969c8d0d2f9f2875e6bf6dd6d5801501cf21d7dc7ce760bcbdd
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 76.07692307692308,
+  "epoch": 76.15384615384616,
   "eval_steps": 500,
-  "global_step": 9890,
+  "global_step": 9900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17810,6 +17810,24 @@
       "mean_token_accuracy": 0.6479182183742523,
       "num_tokens": 36069596.0,
       "step": 9890
+    },
+    {
+      "epoch": 76.11538461538461,
+      "grad_norm": 0.0,
+      "learning_rate": 5.3e-07,
+      "loss": 1.8029,
+      "mean_token_accuracy": 0.6407642930746078,
+      "num_tokens": 36087230.0,
+      "step": 9895
+    },
+    {
+      "epoch": 76.15384615384616,
+      "grad_norm": 0.0,
+      "learning_rate": 5.05e-07,
+      "loss": 1.7748,
+      "mean_token_accuracy": 0.6411665916442871,
+      "num_tokens": 36105433.0,
+      "step": 9900
     }
   ],
   "logging_steps": 5,
@@ -17829,7 +17847,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.829078127854715e+18,
+  "total_flos": 1.830894878845993e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null