Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eea4fa638baaf8d472a3a354c065c1e117bae3812cab21611a3e83f5012d229
+oid sha256:b412f3b1951d17ac8ae88b5821599182640f8e978fea0494972d8483947de2b1
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d87e31e70bd00544a171f1f4d95a75e20cac3097ae8bfe86653f57d1d07c450
+oid sha256:063ecfe21618d93d19ac529d766a324de1d1f90f9a41b5178e190a18a48dc155
 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": 0.0032059845044082286,
+  "epoch": 0.0035622050048980318,
   "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": 30.454,
       "eval_steps_per_second": 15.227,
       "step": 9
+    },
+    {
+      "epoch": 0.0035622050048980318,
+      "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": 1252301482229760.0,
+  "total_flos": 1391446091366400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null