Training in progress, step 16800, checkpoint

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c882567b4587e54e73e64f89aebf7700832afcf149737b89c4ab63b4ad03f67
-size 14567
+oid sha256:3dcfcd7c355804cf8b13e6226a71391df1b5d90db51709d836250af5fd03a627
+size 14503

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.8704487722269265,
+  "epoch": 4.063868392403532,
   "eval_steps": 800,
-  "global_step": 16000,
+  "global_step": 16800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -327,6 +327,22 @@
       "eval_steps_per_second": 5.398,
       "eval_wer": 1.0,
       "step": 16000
+    },
+    {
+      "epoch": 4.063868392403532,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002604114621601763,
+      "loss": 0.0,
+      "step": 16800
+    },
+    {
+      "epoch": 4.063868392403532,
+      "eval_loss": NaN,
+      "eval_runtime": 527.7152,
+      "eval_samples_per_second": 44.232,
+      "eval_steps_per_second": 5.529,
+      "eval_wer": 1.0,
+      "step": 16800
     }
   ],
   "logging_steps": 800,
@@ -346,7 +362,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.614468588324194e+19,
+  "total_flos": 3.7959210547118785e+19,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null