Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9422c181e80beaba0508e43a70fb2f21e087ccc636502200eb59d351b326eb15
+oid sha256:a8ac9d41287de7debc68651490676aa50ef230d744b065699d21d04375d83588
 size 64683604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c8f3d1a3b6d477a03acbf7dd0224c1db8e20da3ef49010019bfb5ec701f8f08
+oid sha256:8e0eff79d7a3948a47f32181b5c0728a4794b8272f85479fa4de86279c0c155d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0029194712513178167,
+  "epoch": 0.0032438569459086854,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 13.062,
       "eval_steps_per_second": 6.531,
       "step": 9
+    },
+    {
+      "epoch": 0.0032438569459086854,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4703216486842368.0,
+  "total_flos": 5225796096491520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null