Training in progress, step 26800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21142536b7429d36ebfde44d13c2b325374448c902fcc9e839cba576d4af0a5d
+oid sha256:454556d34765dde3ef0274c5c6b8eb640baa6e6df29bfda1cfc6dee223b8e007
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6ffa4a4ac815d752cb56575bdd6ff326deddd4f4faf61327414b0ac96d10f5
+oid sha256:0ddd8ed542961bb752300cafd51f0407b631cdc7c5454a6c0ade8d6fe545927a
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:236d55043b3599d5a469ae056de5086947317f985ab12d123e125917adb2b500
-size 14308
+oid sha256:fd885655941c277ae79cac4e6aa317e40edeeb51d003a9c14bd5afa883c299e2
+size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:928c9f403c58021dae7447c256dc2a1215c54e4c2d233c0751f8c3952708770e
+oid sha256:a79b8f6ac5adc78ea938a1602b91550b06839c8391ae94f652aa3c8e2540ea8c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.91044776119403,
+  "epoch": 18.181818181818183,
   "eval_steps": 400,
-  "global_step": 26400,
+  "global_step": 26800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1063,6 +1063,22 @@
       "eval_steps_per_second": 0.838,
       "eval_wer": 0.04513942381759359,
       "step": 26400
+    },
+    {
+      "epoch": 18.18,
+      "grad_norm": 0.172608882188797,
+      "learning_rate": 0.00011953339432753888,
+      "loss": 0.0572,
+      "step": 26800
+    },
+    {
+      "epoch": 18.18,
+      "eval_loss": 0.029318030923604965,
+      "eval_runtime": 208.963,
+      "eval_samples_per_second": 6.695,
+      "eval_steps_per_second": 0.837,
+      "eval_wer": 0.045986750885841934,
+      "step": 26800
     }
   ],
   "logging_steps": 400,
@@ -1070,7 +1086,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 8.050306741013055e+19,
+  "total_flos": 8.175079702729595e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null