Training in progress, step 33600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26cd6571ff6013ee4040c7e9bab5317447cfb4cc34e7b1da8ba6fb8c2ffae362
+oid sha256:3f22325aa1f5ed494b0d5c0d16a8a913f20d38ec71bd0dd5e939c08738dde49d
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9c377312e70d82cb6f732e1d40d46c81b7b9474fba935ebf032c3f1f2757d90
+oid sha256:e8e0d19a7a0c0b61e3d26116ae68f7eaa58e61ff51d6f44d3d0bf74bdf2300ee
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7233ed33137c98d9b12160c311872e55d6db55aa61e9d7f77192b7e6a13fa95
+oid sha256:071d1078d3ac4159702884d4d75a81a594e66bcc8d271e9eff2fa9013e87bfc4
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b25248087d69965ddef920c8054bb52ba085ee231272e0795b2da361d2f441be
+oid sha256:7716c9ce498bee52d2573a1cacdfdb44092db12b548eaa85005da9fb2a335024
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db00d50dd421d79ba139d2536bd27ca7a13377d9e22c077973ca6936cb06d8eb
+oid sha256:cfbb59a646988d0220b43b90f89f163169bfcd3208a594ad2cc8a4e9b2b6b2ea
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 32400,
   "best_metric": 0.19510757441791923,
   "best_model_checkpoint": "./distil-whisper/checkpoint-32400",
-  "epoch": 23.659184037056832,
+  "epoch": 23.944236593621948,
   "eval_steps": 400,
-  "global_step": 33200,
+  "global_step": 33600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3079,6 +3079,43 @@
       "eval_steps_per_second": 0.397,
       "eval_wer": 0.19952844090775126,
       "step": 33200
+    },
+    {
+      "epoch": 23.730447176198112,
+      "grad_norm": 18.851301193237305,
+      "learning_rate": 5.188720173535792e-06,
+      "loss": 1.0099,
+      "step": 33300
+    },
+    {
+      "epoch": 23.801710315339392,
+      "grad_norm": 12.088775634765625,
+      "learning_rate": 4.899493853940709e-06,
+      "loss": 0.9931,
+      "step": 33400
+    },
+    {
+      "epoch": 23.872973454480668,
+      "grad_norm": 12.231010437011719,
+      "learning_rate": 4.610267534345626e-06,
+      "loss": 1.0545,
+      "step": 33500
+    },
+    {
+      "epoch": 23.944236593621948,
+      "grad_norm": 12.138983726501465,
+      "learning_rate": 4.323933477946494e-06,
+      "loss": 1.0527,
+      "step": 33600
+    },
+    {
+      "epoch": 23.944236593621948,
+      "eval_loss": 0.09295401722192764,
+      "eval_runtime": 158.8474,
+      "eval_samples_per_second": 3.148,
+      "eval_steps_per_second": 0.397,
+      "eval_wer": 0.19643383436486886,
+      "step": 33600
     }
   ],
   "logging_steps": 100,
@@ -3098,7 +3135,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.316381645635584e+19,
+  "total_flos": 4.368414503337984e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null