Training in progress, step 22400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a394aeeea4a2de10f768b61832c5745c1c11d2e1d8a9cc5baec1c529bf6fdc87
+oid sha256:650fbf8d3ad6a937ad00b726e0e059fa5b0d4095b358ccb8b83b99d705d67f3a
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84a2d925065461d86e9e9afc058809c9dd1ad9bcb825ca34061365af47a11542
+oid sha256:b39a22fbed5001e0bf23ebb6e438a705bc06cdb375ddfc0ba39c29784850d050
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f692015617e705ff861686b4082c2da1240af93c73d6ae630cfff58a945aab7
+oid sha256:09310d30ce2f1f65bdee86a47be5289ce008cf20400e5805ad00f3f50b144fbe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e33c5010c37401e20c1de34fe9285c339740cd9c43f7069d973e83e97e3419e1
+oid sha256:f68ad3f7fcdd16a1878b08fa3b7e4a910f778b64d8df6baad5daa110cbd65670
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.925373134328359,
+  "epoch": 15.19674355495251,
   "eval_steps": 400,
-  "global_step": 22000,
+  "global_step": 22400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -887,6 +887,22 @@
       "eval_steps_per_second": 0.836,
       "eval_wer": 0.05754121090741026,
       "step": 22000
+    },
+    {
+      "epoch": 15.2,
+      "grad_norm": 0.333710640668869,
+      "learning_rate": 0.00014972552607502287,
+      "loss": 0.0666,
+      "step": 22400
+    },
+    {
+      "epoch": 15.2,
+      "eval_loss": 0.031425874680280685,
+      "eval_runtime": 210.734,
+      "eval_samples_per_second": 6.639,
+      "eval_steps_per_second": 0.83,
+      "eval_wer": 0.05592358650439069,
+      "step": 22400
     }
   ],
   "logging_steps": 400,
@@ -894,7 +910,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 6.710427073339886e+19,
+  "total_flos": 6.831976523110607e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null