Training in progress, step 16800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca8011124d0f221faa4eb3b1f5807e6470d1dd9bfb0156373450459019d21744
+oid sha256:8daf519e56262574da44c0ef1b99ce20dfa6917108a4ca7ed2f9d533fdc8c1ba
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a826227c1be35c245376ed0eb5a33e0f9a8a71889f3dff49fdb26a9119149fae
+oid sha256:ce9deb2c7c7a8e25f17f3d650ec4d54d8887269d9c51b346d47fc9ace2e49db7
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:555d0067d9f1c1fc2b1b7c71d71398365c1d5558a1d42d553c44ffc8c014c517
+oid sha256:ee6dca5678b882df81a5d39896646c925c7d4cb2a4c9671ace85732fa736c4f5
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:536e3fa5d2a8f82eeda248728189fbebc2416ac265143729cf0f10ae696351bc
+oid sha256:fc569727a87d5c1414231bcc21e5c78774f97c9039044a671a07f1c0b2ba722b
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a464e4f2a2d94276e87a75af475e934d6a2163995fdae5bebdd11aacc1a5e5
+oid sha256:f0ec29cf1aa64cbf5f3ca0e7be0776f13fe78466f1761905213206b4277e5b76
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 4000,
   "best_metric": 0.18950781019746538,
   "best_model_checkpoint": "./distil-whisper/checkpoint-4000",
-  "epoch": 9.72139893301719,
+  "epoch": 9.95850622406639,
   "eval_steps": 400,
-  "global_step": 16400,
+  "global_step": 16800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1525,6 +1525,43 @@
       "eval_steps_per_second": 0.433,
       "eval_wer": 0.19805481874447392,
       "step": 16400
+    },
+    {
+      "epoch": 9.780675755779491,
+      "grad_norm": 9.186098098754883,
+      "learning_rate": 2.333536957849725e-06,
+      "loss": 1.0397,
+      "step": 16500
+    },
+    {
+      "epoch": 9.83995257854179,
+      "grad_norm": 8.19621753692627,
+      "learning_rate": 1.7226634086744045e-06,
+      "loss": 1.0364,
+      "step": 16600
+    },
+    {
+      "epoch": 9.89922940130409,
+      "grad_norm": 13.115442276000977,
+      "learning_rate": 1.1117898594990837e-06,
+      "loss": 1.07,
+      "step": 16700
+    },
+    {
+      "epoch": 9.95850622406639,
+      "grad_norm": 15.874578475952148,
+      "learning_rate": 5.00916310323763e-07,
+      "loss": 1.0786,
+      "step": 16800
+    },
+    {
+      "epoch": 9.95850622406639,
+      "eval_loss": 0.08894996345043182,
+      "eval_runtime": 145.9726,
+      "eval_samples_per_second": 3.425,
+      "eval_steps_per_second": 0.432,
+      "eval_wer": 0.1971706454465075,
+      "step": 16800
     }
   ],
   "logging_steps": 100,
@@ -1544,7 +1581,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.133091066576896e+19,
+  "total_flos": 2.185123924279296e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null