Training in progress, step 650, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a031186fad857ed27442646fa945802d103b5070b29970e2c85effc80838b56b
+oid sha256:a3d058ad83df1248104aebddc68809ad8181f5a738d3f262c01b230445d8e1fc
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f638fc438ba9953bf254ad3a6b2aac7576a6b22d5b3d7bbc1db0fa94d0592a82
+oid sha256:00648f9b7943d3ae0509fa93d55d7679eb9850a9e388c336882761ef94c40c27
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37faec2b709803256f69cb521c8aa3bed0c30eeec15307675432682753e8b6da
+oid sha256:e6d02bdaf0794c337f68e13f716ae0e84cd20f99027150136cae575e5693e46e
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.923076923076923,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 640,
+  "global_step": 650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1160,6 +1160,24 @@
       "mean_token_accuracy": 0.6711235165596008,
       "num_tokens": 2333816.0,
       "step": 640
+    },
+    {
+      "epoch": 4.961538461538462,
+      "grad_norm": 0.0,
+      "learning_rate": 4.678e-05,
+      "loss": 1.7512,
+      "mean_token_accuracy": 0.647821244597435,
+      "num_tokens": 2352150.0,
+      "step": 645
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.0,
+      "learning_rate": 4.6755e-05,
+      "loss": 1.7376,
+      "mean_token_accuracy": 0.6522481203079223,
+      "num_tokens": 2370525.0,
+      "step": 650
     }
   ],
   "logging_steps": 5,
@@ -1179,7 +1197,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1829379831087104e+17,
+  "total_flos": 1.2021026260598784e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null