Training in progress, step 5, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b5a9ec3c2be1afae9dfda259a41d2343035540b0a6174aaccfab770162f6c2
+oid sha256:6cb78f9fcda0bad66432568a46fe975baed42a91e7c5b4706e81b57071094f90
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb209c74960b4eb84bfeca9e8871a02542ac75a9d38ddc85f5346e7ec7d43a1f
+oid sha256:f52e5a5ff0f4f04d732963bff5758feafdba7016a3b92e01fe0a47369b5dd76c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8421052631578947,
+  "epoch": 1.1578947368421053,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 23.013,
       "eval_steps_per_second": 11.507,
       "step": 4
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 734826558652416.0,
+  "total_flos": 918533198315520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null