Training in progress, step 23600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac70d72a24d512f2a2e3fd0fd8d84d60223ad0915eefbb8c48a7e7e248a43b4
+oid sha256:f27f5b61c1f90948dd0010ae8fe09b2ee05d65814c1485c88a416751b2977ce6
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab92c42c4ede1e1137df03fec181089be3f6f03b2729177d83381089627860da
+oid sha256:c8c7327b4481ffedc3f87866a5c81e8bef2081ee0e7564ef993f87477b497ca6
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7bac1e51b05f474b9d8beeed9745a3a290e9b2cd9d66757dfc6c886dc8eceaa
+oid sha256:fa7e40ee09d6a17e6a9f525685c6dd28582a8bf9dd51f9ac2e205828da6e88ad
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fd1c2311b060c16b15ce3ffca2f7e3c98ace7f2078bf59f7d72ea9c5e7e6481
+oid sha256:f92ad734640125620ead43ba6f565701d742f7f96a1acb5b572295c79e960c56
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.739484396200814,
+  "epoch": 16.010854816824967,
   "eval_steps": 400,
-  "global_step": 23200,
+  "global_step": 23600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -935,6 +935,22 @@
       "eval_steps_per_second": 0.836,
       "eval_wer": 0.05515328916961947,
       "step": 23200
+    },
+    {
+      "epoch": 16.01,
+      "grad_norm": 0.5310277938842773,
+      "learning_rate": 0.00014149130832570906,
+      "loss": 0.0678,
+      "step": 23600
+    },
+    {
+      "epoch": 16.01,
+      "eval_loss": 0.031200062483549118,
+      "eval_runtime": 212.7627,
+      "eval_samples_per_second": 6.575,
+      "eval_steps_per_second": 0.823,
+      "eval_wer": 0.054845170235710984,
+      "step": 23600
     }
   ],
   "logging_steps": 400,
@@ -942,7 +958,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 7.07572671118286e+19,
+  "total_flos": 7.198809146011316e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null