Training in progress, step 23200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a16074066d83775c4a17f83bfe52f28073ece39419bc4a2c1994d1e78611cd1
+oid sha256:dac70d72a24d512f2a2e3fd0fd8d84d60223ad0915eefbb8c48a7e7e248a43b4
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffdaa7ea99a7342739b3bc43c0b8e16b6c966f5fe52975037fac0a052ca78060
+oid sha256:ab92c42c4ede1e1137df03fec181089be3f6f03b2729177d83381089627860da
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63df3feb106877a0c8b87b26e82b03b96040a2cc3e6b78b40ee9491bfeb2aba
+oid sha256:c7bac1e51b05f474b9d8beeed9745a3a290e9b2cd9d66757dfc6c886dc8eceaa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:639e352d17a1224a5c4830a5109fe70a62931a8070aa98536eb532b2f173108d
+oid sha256:2fd1c2311b060c16b15ce3ffca2f7e3c98ace7f2078bf59f7d72ea9c5e7e6481
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.468113975576662,
+  "epoch": 15.739484396200814,
   "eval_steps": 400,
-  "global_step": 22800,
+  "global_step": 23200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -919,6 +919,22 @@
       "eval_steps_per_second": 0.84,
       "eval_wer": 0.05345863503312279,
       "step": 22800
+    },
+    {
+      "epoch": 15.74,
+      "grad_norm": 0.9596304297447205,
+      "learning_rate": 0.00014423604757548032,
+      "loss": 0.0664,
+      "step": 23200
+    },
+    {
+      "epoch": 15.74,
+      "eval_loss": 0.03153248876333237,
+      "eval_runtime": 209.4047,
+      "eval_samples_per_second": 6.681,
+      "eval_steps_per_second": 0.836,
+      "eval_wer": 0.05515328916961947,
+      "step": 23200
     }
   ],
   "logging_steps": 400,
@@ -926,7 +942,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 6.954458728485663e+19,
+  "total_flos": 7.07572671118286e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null