Training in progress, step 41600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6e2823f88f5f24074d58b21cfe18f66f131ac34667095575c4c40e4eae863e3
+oid sha256:f8f4de11682a0c8e88d71359dafa5b34053b806b63c76bc17b578626c59d10d7
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:337d3b57220580ed03ee608a9a877cb6776a0f7fb530d8a389436c6d77d26aed
+oid sha256:60be441bde6c082a27eac961cb3a0e53373da53b188daae45ac42c8b9f832bbd
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37da37f32b9da157d0f354c842374bbe28e2210ef8b4e1a2f62909ef09fdefb
+oid sha256:8fd9a99c413ca4719ee97edd196fbd497aaa8fa62bf6aa7ecef1095789a7c684
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bbf1059b349dfce5e1aca93ba02e0a5c14f3145f54aaedb0a25d075e6e0aaa9
+oid sha256:8e0c332553653cd9d4981e38bf20cbc0d49f17070be19495c137d21df729fecf
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e2692c415195d4cb598a1230fff1568c572f90b174e77b60f1d07171445123
+oid sha256:e2e5b2934f5267113b7be9d670e6b6f99e8588ce7390623947ef0eb6778afb9f
 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": 29.362729378229112,
+  "epoch": 29.647781934794228,
   "eval_steps": 400,
-  "global_step": 41200,
+  "global_step": 41600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3819,6 +3819,43 @@
       "eval_steps_per_second": 0.433,
       "eval_wer": 0.19687592101385204,
       "step": 41200
+    },
+    {
+      "epoch": 29.433992517370392,
+      "grad_norm": 9.201010704040527,
+      "learning_rate": 1.954796826160135e-06,
+      "loss": 0.9134,
+      "step": 41300
+    },
+    {
+      "epoch": 29.505255656511668,
+      "grad_norm": 12.38512134552002,
+      "learning_rate": 1.7143544121182977e-06,
+      "loss": 0.9591,
+      "step": 41400
+    },
+    {
+      "epoch": 29.576518795652948,
+      "grad_norm": 12.809625625610352,
+      "learning_rate": 1.4739119980764607e-06,
+      "loss": 0.8946,
+      "step": 41500
+    },
+    {
+      "epoch": 29.647781934794228,
+      "grad_norm": 11.387064933776855,
+      "learning_rate": 1.2334695840346237e-06,
+      "loss": 0.9297,
+      "step": 41600
+    },
+    {
+      "epoch": 29.647781934794228,
+      "eval_loss": 0.09202717989683151,
+      "eval_runtime": 145.5856,
+      "eval_samples_per_second": 3.434,
+      "eval_steps_per_second": 0.433,
+      "eval_wer": 0.19820218096080164,
+      "step": 41600
     }
   ],
   "logging_steps": 100,
@@ -3838,7 +3875,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.356449364967424e+19,
+  "total_flos": 5.408482222669824e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null