Training in progress, step 25600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27a674e742240b524ce188020b73573835ac8f296394b668356fd66c8c9fa6cc
+oid sha256:1309fe10b172bb260fb88a1ef512f0133cab403545e2e410e012ee77c1b61079
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5902abc14c171acdf4ca2d3efcda72f7dc2114aeab53f6586255e47bfdef582
+oid sha256:e0a3553dc821d23806cfaa4fae7f776de5dc8546d1865096234c8afdc141d396
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99448603cfe163aa10314006ec7b49515a18b30afe746ed134b517ff6bcd739c
+oid sha256:5262439c917fd4e99ff014fbcd1abfcb88c18e776e072e32cebb9351832a6a75
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0f76e0d13363c153062d0b122aaf8bb4e63d66e1d28037f97d4991b72d5302e
+oid sha256:59e4db644290cc0b4cb99efa12e07fb0da05480d4cd19963f6986ed6d2705369
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.096336499321573,
+  "epoch": 17.367706919945725,
   "eval_steps": 400,
-  "global_step": 25200,
+  "global_step": 25600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1015,6 +1015,22 @@
       "eval_steps_per_second": 0.837,
       "eval_wer": 0.05022338622708365,
       "step": 25200
+    },
+    {
+      "epoch": 17.37,
+      "grad_norm": 0.3329567015171051,
+      "learning_rate": 0.0001277676120768527,
+      "loss": 0.0563,
+      "step": 25600
+    },
+    {
+      "epoch": 17.37,
+      "eval_loss": 0.02935618720948696,
+      "eval_runtime": 208.6661,
+      "eval_samples_per_second": 6.704,
+      "eval_steps_per_second": 0.839,
+      "eval_wer": 0.04922199969188107,
+      "step": 25600
     }
   ],
   "logging_steps": 400,
@@ -1022,7 +1038,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 7.685295324911179e+19,
+  "total_flos": 7.807330775664206e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null