Training in progress, step 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:659e856d9b772af99c334f70f16eba254170872658d1be152763ea3540da1089
+oid sha256:56b5a9ec3c2be1afae9dfda259a41d2343035540b0a6174aaccfab770162f6c2
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2547eaf80d7f8345c62387653af67ac7fae5a8d41aac312dfcd2a10bad5a9ed
+oid sha256:fb209c74960b4eb84bfeca9e8871a02542ac75a9d38ddc85f5346e7ec7d43a1f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.42105263157894735,
+  "epoch": 0.8421052631578947,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 22.863,
       "eval_steps_per_second": 11.432,
       "step": 2
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": NaN,
+      "eval_runtime": 0.0869,
+      "eval_samples_per_second": 23.013,
+      "eval_steps_per_second": 11.507,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 367413279326208.0,
+  "total_flos": 734826558652416.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null