Training in progress, step 22800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:650fbf8d3ad6a937ad00b726e0e059fa5b0d4095b358ccb8b83b99d705d67f3a
+oid sha256:2a16074066d83775c4a17f83bfe52f28073ece39419bc4a2c1994d1e78611cd1
 size 1262135480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b39a22fbed5001e0bf23ebb6e438a705bc06cdb375ddfc0ba39c29784850d050
+oid sha256:ffdaa7ea99a7342739b3bc43c0b8e16b6c966f5fe52975037fac0a052ca78060
 size 2490815798

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09310d30ce2f1f65bdee86a47be5289ce008cf20400e5805ad00f3f50b144fbe
+oid sha256:c63df3feb106877a0c8b87b26e82b03b96040a2cc3e6b78b40ee9491bfeb2aba
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f68ad3f7fcdd16a1878b08fa3b7e4a910f778b64d8df6baad5daa110cbd65670
+oid sha256:639e352d17a1224a5c4830a5109fe70a62931a8070aa98536eb532b2f173108d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.19674355495251,
+  "epoch": 15.468113975576662,
   "eval_steps": 400,
-  "global_step": 22400,
+  "global_step": 22800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -903,6 +903,22 @@
       "eval_steps_per_second": 0.83,
       "eval_wer": 0.05592358650439069,
       "step": 22400
+    },
+    {
+      "epoch": 15.47,
+      "grad_norm": 0.4220418632030487,
+      "learning_rate": 0.00014698078682525158,
+      "loss": 0.0672,
+      "step": 22800
+    },
+    {
+      "epoch": 15.47,
+      "eval_loss": 0.030694805085659027,
+      "eval_runtime": 208.4031,
+      "eval_samples_per_second": 6.713,
+      "eval_steps_per_second": 0.84,
+      "eval_wer": 0.05345863503312279,
+      "step": 22800
     }
   ],
   "logging_steps": 400,
@@ -910,7 +926,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 400,
-  "total_flos": 6.831976523110607e+19,
+  "total_flos": 6.954458728485663e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null