Training in progress, step 34400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20bdfe64bb7787dbde06ed0249c104c2a75f74f77a4da7b6d17b0be3c907bffe
+oid sha256:7c7bac0ecd11e105ba77bc6b9c1e49b56f9b9523b4862c6989ad212585b9e24c
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55dd9570954d73b04e0eb476a55f9ed87ca0571abe03bdd05b897829def60e9b
+oid sha256:19981691c62f8f347e95b064d87dda28cd05190b739901bc88cf7a374983b649
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19d659484e215c1796fcedcf712444963aec532ba7ef9b9f53c66f0a4322a2d0
+oid sha256:ce15f59f8cb64bc668dfb4e258be90d962b7c8172b3c45431bfac7361d50154f
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e82de6898de222ba34f053188f784b1daff292a8caca719707d751a738a4d585
+oid sha256:c9dbb3e5d0fc7426e887c7892235a6eb2991774261a344c85f92b5b41d28ebaf
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8627c62832e908e5ee44d6dc9ec10410d33b0d8b29cb328e2941165b3e5c98eb
+oid sha256:ee882eac40b50fbdc8d881b62f827901f35cd88d24357d996c81a66bb3343b11
 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": 24.228754676643508,
+  "epoch": 24.513807233208624,
   "eval_steps": 400,
-  "global_step": 34000,
+  "global_step": 34400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3153,6 +3153,43 @@
       "eval_steps_per_second": 0.393,
       "eval_wer": 0.19790745652814618,
       "step": 34000
+    },
+    {
+      "epoch": 24.300017815784784,
+      "grad_norm": 11.129683494567871,
+      "learning_rate": 2.8778018799710775e-06,
+      "loss": 0.9646,
+      "step": 34100
+    },
+    {
+      "epoch": 24.371280954926064,
+      "grad_norm": 11.022905349731445,
+      "learning_rate": 2.588575560375994e-06,
+      "loss": 0.9873,
+      "step": 34200
+    },
+    {
+      "epoch": 24.442544094067344,
+      "grad_norm": 9.839102745056152,
+      "learning_rate": 2.299349240780911e-06,
+      "loss": 0.9995,
+      "step": 34300
+    },
+    {
+      "epoch": 24.513807233208624,
+      "grad_norm": 10.704620361328125,
+      "learning_rate": 2.010122921185828e-06,
+      "loss": 0.9504,
+      "step": 34400
+    },
+    {
+      "epoch": 24.513807233208624,
+      "eval_loss": 0.09273621439933777,
+      "eval_runtime": 158.2643,
+      "eval_samples_per_second": 3.159,
+      "eval_steps_per_second": 0.398,
+      "eval_wer": 0.19599174771588565,
+      "step": 34400
     }
   ],
   "logging_steps": 100,
@@ -3172,7 +3209,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.420329474097152e+19,
+  "total_flos": 4.472362331799552e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null