Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a84a251ecd9c8fb67c63a59a8d224783f20b00322aa91714b6858fd0de1eb9d
+oid sha256:454ad61037be02fcb7a5d1ab5349a36d52e9f394a317bfd6f5ab7fb7116dceaa
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1626124117ea029ca8b31e67d127dc2073ba58eb663ae67db6b7bb3d9f6c920
+oid sha256:9019561187ba150b241479355e0354731cc71a9bc0e70a7286b23eb4f8b454a7
 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": 0.0032588032950122206,
+  "epoch": 0.003620892550013578,
   "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": 29.402,
       "eval_steps_per_second": 14.714,
       "step": 9
+    },
+    {
+      "epoch": 0.003620892550013578,
+      "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": 291868432662528.0,
+  "total_flos": 324298258513920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null