Training in progress, step 5, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c67a6d5516396247f78e672019632cb827d8fb2b5c48dafb5278175502cf0edc
+oid sha256:042b44eb4bee35c45b02f787272c35ea6d322a62393d784f46c3757206da48a5
 size 20814996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c367f329ae6cb5bb8e3e64fd29746c6490651d10a102be67dd7605dc7a667ed5
+oid sha256:7f470c33e40ad98eb31adc1fe70f97c2d5c3b1c77358bd2ee5f96dc68b3111f0
 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": 0.002735276519360629,
+  "epoch": 0.0034190956492007865,
   "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": 6.924,
       "eval_steps_per_second": 6.924,
       "step": 4
+    },
+    {
+      "epoch": 0.0034190956492007865,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.2667,
+      "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": 416733726769152.0,
+  "total_flos": 538704573628416.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null