Training in progress, step 9880, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a538a8d6fc2cc1e275e8828477cee619ea4015ffeac86ef55493592148a531b
+oid sha256:fec2e4937aab544bc4a7a289c34393ecd56103032bc0d0d26b02e58276b1dbbc
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a848a36406091eeafbef24585a49febbf9ef5dcb023c4b65ecacd098364e717a
+oid sha256:6ec370349279813f830889071811ab5efe4b9e7cff1f539189d3d3eccba3be68
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c7138e99739429625382afd05fc4b7ce96e091fde4ec54f5985bc3ad47c26e8
+oid sha256:75fb6279d7a90f2eb40ea21d57c0a3b3b9e3c8c93e25ada48d38c03d7fd5446d
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 75.92307692307692,
+  "epoch": 76.0,
   "eval_steps": 500,
-  "global_step": 9870,
+  "global_step": 9880,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17774,6 +17774,24 @@
       "mean_token_accuracy": 0.6595763146877289,
       "num_tokens": 35996459.0,
       "step": 9870
+    },
+    {
+      "epoch": 75.96153846153847,
+      "grad_norm": 0.0,
+      "learning_rate": 6.3e-07,
+      "loss": 1.7751,
+      "mean_token_accuracy": 0.6440996766090393,
+      "num_tokens": 36013795.0,
+      "step": 9875
+    },
+    {
+      "epoch": 76.0,
+      "grad_norm": 0.0,
+      "learning_rate": 6.05e-07,
+      "loss": 1.719,
+      "mean_token_accuracy": 0.6536471992731094,
+      "num_tokens": 36031980.0,
+      "step": 9880
     }
   ],
   "logging_steps": 5,
@@ -17793,7 +17811,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.825323159825285e+18,
+  "total_flos": 1.8271429276203418e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null