Training in progress, step 24800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f2397e6114960d2082bdf5be464d269b233b0aacd6184267a435fc8a6ecd222
+oid sha256:851a28b7e940e785424cc03c7151652441e2d0b4cb4048bf57b713c9fda62c9e
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3061d8247c75832593a3c5d379d8136a34802911a21c1a7e98ce18e9370afc80
+oid sha256:2d9843a0073d8f07d9aa97c137539c89b0381be390ec771c3c7b58bba473b0be
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:081b36c60682558da2008c23faaa9a9c965a8e6a3032698eae1b9a1cec945b2f
+oid sha256:97189dcbb87b9c52a1a9c6d79d6e1a7a44305ec3b8e7f4166780be43ed2490a1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7385ea8fcbfe828da13abda991b7c863c98739c7403d7f8feb3c6c861ca53671
+oid sha256:26ee95546328bc80917916b550a51773a942413144a5bcc1489955d54811ff34
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.55359565807327,
+  "epoch": 16.824966078697422,
   "eval_steps": 400,
-  "global_step": 24400,
+  "global_step": 24800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -983,6 +983,22 @@
       "eval_steps_per_second": 0.837,
       "eval_wer": 0.048066553689724234,
       "step": 24400
+    },
+    {
+      "epoch": 16.82,
+      "grad_norm": 0.44349026679992676,
+      "learning_rate": 0.00013325709057639522,
+      "loss": 0.062,
+      "step": 24800
+    },
+    {
+      "epoch": 16.82,
+      "eval_loss": 0.030771076679229736,
+      "eval_runtime": 210.1625,
+      "eval_samples_per_second": 6.657,
+      "eval_steps_per_second": 0.833,
+      "eval_wer": 0.05130180249576336,
+      "step": 24800
     }
   ],
   "logging_steps": 400,
@@ -990,7 +1006,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 7.443488870240685e+19,
+  "total_flos": 7.5649661613062e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null