Training in progress, step 2990, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6089f6b2d3b6a280d26789a304fcfde27ddb5ff002ba8855aca22705c536d37e
+oid sha256:65e787b18a45e3fe53d0164a6ba171dce969357f4b20b9cc87a290d0316f7477
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f95de6db78f2a80c80212513cb636935b979f404f078755f93942cd2460052d
+oid sha256:9c0ddeaf0737cef5ec7cd8e12e7460b57df54b3816e592dc6aab5af01bd0c4ef
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a76a2933dc00ec7ae197b81fca3da9c2907aadc732447bddad1c46392450afa
+oid sha256:b02ec551fa98d7fbe4e782eccd6f5d9966ff01816171d9296bba211a882ffc45
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 22.923076923076923,
+  "epoch": 23.0,
   "eval_steps": 500,
-  "global_step": 2980,
+  "global_step": 2990,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5372,6 +5372,24 @@
       "mean_token_accuracy": 0.6427533149719238,
       "num_tokens": 10867773.0,
       "step": 2980
+    },
+    {
+      "epoch": 22.96153846153846,
+      "grad_norm": 0.0,
+      "learning_rate": 3.508e-05,
+      "loss": 1.7629,
+      "mean_token_accuracy": 0.6471167922019958,
+      "num_tokens": 10885829.0,
+      "step": 2985
+    },
+    {
+      "epoch": 23.0,
+      "grad_norm": 0.0,
+      "learning_rate": 3.5055e-05,
+      "loss": 1.7349,
+      "mean_token_accuracy": 0.65148167014122,
+      "num_tokens": 10904415.0,
+      "step": 2990
     }
   ],
   "logging_steps": 5,
@@ -5391,7 +5409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.507445222309888e+17,
+  "total_flos": 5.525887420145664e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null