Training in progress, step 25200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:851a28b7e940e785424cc03c7151652441e2d0b4cb4048bf57b713c9fda62c9e
+oid sha256:27a674e742240b524ce188020b73573835ac8f296394b668356fd66c8c9fa6cc
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d9843a0073d8f07d9aa97c137539c89b0381be390ec771c3c7b58bba473b0be
+oid sha256:d5902abc14c171acdf4ca2d3efcda72f7dc2114aeab53f6586255e47bfdef582
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97189dcbb87b9c52a1a9c6d79d6e1a7a44305ec3b8e7f4166780be43ed2490a1
+oid sha256:99448603cfe163aa10314006ec7b49515a18b30afe746ed134b517ff6bcd739c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26ee95546328bc80917916b550a51773a942413144a5bcc1489955d54811ff34
+oid sha256:f0f76e0d13363c153062d0b122aaf8bb4e63d66e1d28037f97d4991b72d5302e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.824966078697422,
+  "epoch": 17.096336499321573,
   "eval_steps": 400,
-  "global_step": 24800,
+  "global_step": 25200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -999,6 +999,22 @@
       "eval_steps_per_second": 0.833,
       "eval_wer": 0.05130180249576336,
       "step": 24800
+    },
+    {
+      "epoch": 17.1,
+      "grad_norm": 0.5564978718757629,
+      "learning_rate": 0.00013051235132662396,
+      "loss": 0.0584,
+      "step": 25200
+    },
+    {
+      "epoch": 17.1,
+      "eval_loss": 0.02937587909400463,
+      "eval_runtime": 209.0218,
+      "eval_samples_per_second": 6.693,
+      "eval_steps_per_second": 0.837,
+      "eval_wer": 0.05022338622708365,
+      "step": 25200
     }
   ],
   "logging_steps": 400,
@@ -1006,7 +1022,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 7.5649661613062e+19,
+  "total_flos": 7.685295324911179e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null