Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7febd8d9b91dc5f1dc64605fa5ad8eb089c35f12c361b8e118636ea56684c1b0
+oid sha256:fbd656709380cdc03d912e26ab16da42ec85b4b286702ea59cd89647f0aa85f1
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f962f3aeee84895d12d77fcc89b352232c7e33129610fc6571d50b4a4c4806
+oid sha256:ba2c71fa1735005a0fac0d669cc222fad36906855093f4399a0c8d6b1dae0f56
 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": 0.025423728813559324,
+  "epoch": 0.02824858757062147,
   "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": 5.523,
       "eval_steps_per_second": 2.762,
       "step": 9
+    },
+    {
+      "epoch": 0.02824858757062147,
+      "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": 5711923563724800.0,
+  "total_flos": 6346581737472000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null