Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20928efcf87ab7d7b9058cf889e6ca1b0ce7b102a83aeaf47520859779dbf1c4
+oid sha256:21a2ece37157777820cfd4d060a315983d61aaa0b57d23eeb160e5a00e75b45d
 size 608186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc2c3b808c54d800eddfa46c12bf36473a4c57a2cd05db6d1bd04d9c5ac9e110
+oid sha256:3900e38eb419a51c0652153851cbcdcbb9100ce2e80069c9b4925da2fe412d8f
 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": 0.008735743751516622,
+  "epoch": 0.009706381946129581,
   "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": 263.785,
       "eval_steps_per_second": 131.892,
       "step": 9
+    },
+    {
+      "epoch": 0.009706381946129581,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 3.773,
+      "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": 19079055802368.0,
+  "total_flos": 21228808568832.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null