Training in progress, step 42000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8f4de11682a0c8e88d71359dafa5b34053b806b63c76bc17b578626c59d10d7
+oid sha256:bc425d05484c4b99e7a21e5e88f1efa1777409c46771fd4a3fa63fe044be2eb5
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60be441bde6c082a27eac961cb3a0e53373da53b188daae45ac42c8b9f832bbd
+oid sha256:ea0c99f2a920cd5b3db1fe7e99fae1fcad95da2e7a5b7dfac0d182daaf15dfbe
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fd9a99c413ca4719ee97edd196fbd497aaa8fa62bf6aa7ecef1095789a7c684
+oid sha256:82e429a69160a7e218f681be79bc0a1dd4abcd753291d3cd09970598fd33c375
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e0c332553653cd9d4981e38bf20cbc0d49f17070be19495c137d21df729fecf
+oid sha256:a4858df2f172563cac3713edd793643c1b95146d389b9ae8616518d8c80c3945
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2e5b2934f5267113b7be9d670e6b6f99e8588ce7390623947ef0eb6778afb9f
+oid sha256:0aa6b63fe8f302c8544aed592f7c3cd8ff925a68ee9acd3a9154b7f528575009
 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": 29.647781934794228,
+  "epoch": 29.932834491359344,
   "eval_steps": 400,
-  "global_step": 41600,
+  "global_step": 42000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3856,6 +3856,43 @@
       "eval_steps_per_second": 0.433,
       "eval_wer": 0.19820218096080164,
       "step": 41600
+    },
+    {
+      "epoch": 29.719045073935508,
+      "grad_norm": 11.282709121704102,
+      "learning_rate": 9.930271699927866e-07,
+      "loss": 0.9995,
+      "step": 41700
+    },
+    {
+      "epoch": 29.790308213076784,
+      "grad_norm": 10.81017780303955,
+      "learning_rate": 7.525847559509498e-07,
+      "loss": 0.9876,
+      "step": 41800
+    },
+    {
+      "epoch": 29.861571352218064,
+      "grad_norm": 11.903881072998047,
+      "learning_rate": 5.121423419091128e-07,
+      "loss": 0.9524,
+      "step": 41900
+    },
+    {
+      "epoch": 29.932834491359344,
+      "grad_norm": 11.278658866882324,
+      "learning_rate": 2.7410435200769414e-07,
+      "loss": 0.9491,
+      "step": 42000
+    },
+    {
+      "epoch": 29.932834491359344,
+      "eval_loss": 0.09202782809734344,
+      "eval_runtime": 145.311,
+      "eval_samples_per_second": 3.441,
+      "eval_steps_per_second": 0.434,
+      "eval_wer": 0.19908635425876806,
+      "step": 42000
     }
   ],
   "logging_steps": 100,
@@ -3875,7 +3912,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.408482222669824e+19,
+  "total_flos": 5.460515080372224e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null