Training in progress, step 10400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eebc1d9056f2e07f39b6f26b5b895ae666ebf27cb0c5e4d039d62197b8c21393
+oid sha256:32bad8e5e898f7bd64646ffe542574881c5c99a695226e0c589a32de1214c656
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b23867f188536ea66fd72fb25f8b38af033d89e784868a9198bd8636f41aafd6
+oid sha256:1d2bab3edf3c818468550fcecb255f70e0081386921b1170c9e5e841299d0328
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:532c517329b19c3c26a40128633dac433b21c2a9fdccf15f1ce841afac82a731
+oid sha256:590e90ecef4e4819dafc823f4ad9c998a5aacfd2b926cf2cb9f95f06ffc0cfcd
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30018a217305d9e46abd87e309f4ff8defdc4db75aeb3c0990ab48e9f73bc2fd
+oid sha256:2611e59e87ece153a468254db618de66b9b07c0052a3d86601e18b36e0cfec13
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8028b38e81306dbd3e5cdafcebbf51f8d644a14f781af304098d7365c655d64
+oid sha256:dfd4a34adcb8a04e1b5ebbc75f18fe7fef1dc2b70814196a7f2227732b449f96
 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": 5.927682276229994,
+  "epoch": 6.164789567279194,
   "eval_steps": 400,
-  "global_step": 10000,
+  "global_step": 10400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -933,6 +933,43 @@
       "eval_steps_per_second": 0.433,
       "eval_wer": 0.19201296787503683,
       "step": 10000
+    },
+    {
+      "epoch": 5.986959098992294,
+      "grad_norm": 13.559718132019043,
+      "learning_rate": 2.6200369344413665e-05,
+      "loss": 1.3007,
+      "step": 10100
+    },
+    {
+      "epoch": 6.046235921754594,
+      "grad_norm": 14.355300903320312,
+      "learning_rate": 2.543090181594337e-05,
+      "loss": 1.2402,
+      "step": 10200
+    },
+    {
+      "epoch": 6.1055127445168935,
+      "grad_norm": 12.74117660522461,
+      "learning_rate": 2.466143428747307e-05,
+      "loss": 1.1964,
+      "step": 10300
+    },
+    {
+      "epoch": 6.164789567279194,
+      "grad_norm": 8.264984130859375,
+      "learning_rate": 2.389196675900277e-05,
+      "loss": 1.2468,
+      "step": 10400
+    },
+    {
+      "epoch": 6.164789567279194,
+      "eval_loss": 0.09036662429571152,
+      "eval_runtime": 145.6353,
+      "eval_samples_per_second": 3.433,
+      "eval_steps_per_second": 0.433,
+      "eval_wer": 0.19820218096080164,
+      "step": 10400
     }
   ],
   "logging_steps": 100,
@@ -952,7 +989,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.30067916521472e+19,
+  "total_flos": 1.352683567448064e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null