Training in progress, step 9890, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fec2e4937aab544bc4a7a289c34393ecd56103032bc0d0d26b02e58276b1dbbc
+oid sha256:a56ec06dc34cee7dd39d3feb8b68551051c585ab18d67cdd7e55a5bf68feca81
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ec370349279813f830889071811ab5efe4b9e7cff1f539189d3d3eccba3be68
+oid sha256:c05818830d152bb21342a2f47225b1ba3da4f5c057a0251e0399bfcc2b8fd27a
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75fb6279d7a90f2eb40ea21d57c0a3b3b9e3c8c93e25ada48d38c03d7fd5446d
+oid sha256:00adfad39dc29a8ba99da9222898e93d32ae9aefabae1129b73b2933a1864c2c
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 76.0,
+  "epoch": 76.07692307692308,
   "eval_steps": 500,
-  "global_step": 9880,
+  "global_step": 9890,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17792,6 +17792,24 @@
       "mean_token_accuracy": 0.6536471992731094,
       "num_tokens": 36031980.0,
       "step": 9880
+    },
+    {
+      "epoch": 76.03846153846153,
+      "grad_norm": 0.0,
+      "learning_rate": 5.8e-07,
+      "loss": 1.7253,
+      "mean_token_accuracy": 0.6511723041534424,
+      "num_tokens": 36050841.0,
+      "step": 9885
+    },
+    {
+      "epoch": 76.07692307692308,
+      "grad_norm": 0.0,
+      "learning_rate": 5.550000000000001e-07,
+      "loss": 1.7605,
+      "mean_token_accuracy": 0.6479182183742523,
+      "num_tokens": 36069596.0,
+      "step": 9890
     }
   ],
   "logging_steps": 5,
@@ -17811,7 +17829,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8271429276203418e+18,
+  "total_flos": 1.829078127854715e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null