Training in progress, step 34000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f22325aa1f5ed494b0d5c0d16a8a913f20d38ec71bd0dd5e939c08738dde49d
+oid sha256:20bdfe64bb7787dbde06ed0249c104c2a75f74f77a4da7b6d17b0be3c907bffe
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e0d19a7a0c0b61e3d26116ae68f7eaa58e61ff51d6f44d3d0bf74bdf2300ee
+oid sha256:55dd9570954d73b04e0eb476a55f9ed87ca0571abe03bdd05b897829def60e9b
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:071d1078d3ac4159702884d4d75a81a594e66bcc8d271e9eff2fa9013e87bfc4
+oid sha256:19d659484e215c1796fcedcf712444963aec532ba7ef9b9f53c66f0a4322a2d0
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7716c9ce498bee52d2573a1cacdfdb44092db12b548eaa85005da9fb2a335024
+oid sha256:e82de6898de222ba34f053188f784b1daff292a8caca719707d751a738a4d585
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfbb59a646988d0220b43b90f89f163169bfcd3208a594ad2cc8a4e9b2b6b2ea
+oid sha256:8627c62832e908e5ee44d6dc9ec10410d33b0d8b29cb328e2941165b3e5c98eb
 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": 23.944236593621948,
+  "epoch": 24.228754676643508,
   "eval_steps": 400,
-  "global_step": 33600,
+  "global_step": 34000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3116,6 +3116,43 @@
       "eval_steps_per_second": 0.397,
       "eval_wer": 0.19643383436486886,
       "step": 33600
+    },
+    {
+      "epoch": 24.014965259219668,
+      "grad_norm": 12.55706787109375,
+      "learning_rate": 4.03470715835141e-06,
+      "loss": 0.9904,
+      "step": 33700
+    },
+    {
+      "epoch": 24.086228398360948,
+      "grad_norm": 15.65674114227295,
+      "learning_rate": 3.745480838756327e-06,
+      "loss": 1.0292,
+      "step": 33800
+    },
+    {
+      "epoch": 24.157491537502228,
+      "grad_norm": 12.829319953918457,
+      "learning_rate": 3.4562545191612434e-06,
+      "loss": 0.9981,
+      "step": 33900
+    },
+    {
+      "epoch": 24.228754676643508,
+      "grad_norm": 10.557638168334961,
+      "learning_rate": 3.1670281995661605e-06,
+      "loss": 0.9927,
+      "step": 34000
+    },
+    {
+      "epoch": 24.228754676643508,
+      "eval_loss": 0.09272577613592148,
+      "eval_runtime": 160.295,
+      "eval_samples_per_second": 3.119,
+      "eval_steps_per_second": 0.393,
+      "eval_wer": 0.19790745652814618,
+      "step": 34000
     }
   ],
   "logging_steps": 100,
@@ -3135,7 +3172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.368414503337984e+19,
+  "total_flos": 4.420329474097152e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null