Training in progress, step 16400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e529aa534b455b4eff4932a6e3b836c9e65f7be46fc1874d9f859a9e75815f77
+oid sha256:ca8011124d0f221faa4eb3b1f5807e6470d1dd9bfb0156373450459019d21744
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4959f70554ccda9a7d4fbb1dc56b148ec2883ebe1035fafd4983cc7a61850fce
+oid sha256:a826227c1be35c245376ed0eb5a33e0f9a8a71889f3dff49fdb26a9119149fae
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efeb2b09a3ebe9d77764455f499442d89b09ad90eaa316aee6f01fc29e187ef4
+oid sha256:555d0067d9f1c1fc2b1b7c71d71398365c1d5558a1d42d553c44ffc8c014c517
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef37a95aea029b5f384590bb36f0bdc9eb449e36987d8a918a741a10bb0e8c7c
+oid sha256:536e3fa5d2a8f82eeda248728189fbebc2416ac265143729cf0f10ae696351bc
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff16977829e78bf0fb958643a72071d6b1b23f707f478c1387dc1a19869d365b
+oid sha256:c2a464e4f2a2d94276e87a75af475e934d6a2163995fdae5bebdd11aacc1a5e5
 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": 9.48429164196799,
+  "epoch": 9.72139893301719,
   "eval_steps": 400,
-  "global_step": 16000,
+  "global_step": 16400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1488,6 +1488,43 @@
       "eval_steps_per_second": 0.426,
       "eval_wer": 0.197465369879163,
       "step": 16000
+    },
+    {
+      "epoch": 9.54356846473029,
+      "grad_norm": 10.986649513244629,
+      "learning_rate": 4.777031154551008e-06,
+      "loss": 1.1039,
+      "step": 16100
+    },
+    {
+      "epoch": 9.60284528749259,
+      "grad_norm": 9.453868865966797,
+      "learning_rate": 4.166157605375687e-06,
+      "loss": 1.0473,
+      "step": 16200
+    },
+    {
+      "epoch": 9.66212211025489,
+      "grad_norm": 11.858141899108887,
+      "learning_rate": 3.555284056200367e-06,
+      "loss": 1.0339,
+      "step": 16300
+    },
+    {
+      "epoch": 9.72139893301719,
+      "grad_norm": 6.421123504638672,
+      "learning_rate": 2.9444105070250457e-06,
+      "loss": 1.0436,
+      "step": 16400
+    },
+    {
+      "epoch": 9.72139893301719,
+      "eval_loss": 0.08884581178426743,
+      "eval_runtime": 145.5928,
+      "eval_samples_per_second": 3.434,
+      "eval_steps_per_second": 0.433,
+      "eval_wer": 0.19805481874447392,
+      "step": 16400
     }
   ],
   "logging_steps": 100,
@@ -1507,7 +1544,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.081058208874496e+19,
+  "total_flos": 2.133091066576896e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null