Training in progress, step 600, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792ea85767dea8354213c046ddfc283c058438c9bd42b956b56d21b999bed010
+oid sha256:b11b4fbe976846a9b3278e44f225a63a67e85d625a57e67c37fa9ae5e307aace
 size 1598819130

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5148b50590ba2eccaa9614d01e91c63955c36980943998f454561d580e8f60ba
+oid sha256:6f48b81368166faa6e913dbe50b345c1ff918742c19e7d11caea2dc2d9e56500
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006114338122898196,
+  "epoch": 0.009171507184347295,
   "eval_steps": 1000,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -22,6 +22,13 @@
       "learning_rate": 4.99999995525116e-05,
       "loss": 0.0,
       "step": 400
+    },
+    {
+      "epoch": 0.009171507184347295,
+      "grad_norm": NaN,
+      "learning_rate": 4.999999898290334e-05,
+      "loss": 0.0,
+      "step": 600
     }
   ],
   "logging_steps": 200,
@@ -41,7 +48,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 121767624073170.0,
+  "total_flos": 179452957671360.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null