Training in progress, step 24400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03838466207713eada91f2fe35ebdce379d78e8d934980b6a41a370b4b241fc4
+oid sha256:871e1a0f89abd57c35a7dbf130d5524fd292047262616b92ffd261d640fea12d
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39381cb8b076341e0af800d6001aac00e14f538bf29b54baa76c4fc71f6897cf
+oid sha256:9d4051e416251f823f3179b18d1769dda91712dedabff1b2dc39dc8e904b7e65
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a545a607a6cfc5a7cda494aeb18574f85c33430e90245257ba8c7ea46b1621b
+oid sha256:bdf8ed808c01d757c6e38911720948b5f9db18cf7ee348b7781f51b3aebdcb61
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40d683cb85559512f55ce631fbe47e10637f39943ba3b0a1a0e4edcbc56eadf7
+oid sha256:6467edd96925a2153b86ff151f4249484a23bca6d403095f0ddb5893900e1b8a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b664452bdc5abce0bae066b21b5f9a31052c253dc280d18e5bee7ce919977cb2
+oid sha256:8d6539ca7d27098218a78f61589dfb4cc73931bd4c3c71ec49d7760c7d425bf5
 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": 14.226437462951985,
+  "epoch": 14.463544754001186,
   "eval_steps": 400,
-  "global_step": 24000,
+  "global_step": 24400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2228,6 +2228,43 @@
       "eval_steps_per_second": 0.427,
       "eval_wer": 0.19923371647509577,
       "step": 24000
+    },
+    {
+      "epoch": 14.285714285714286,
+      "grad_norm": 10.366995811462402,
+      "learning_rate": 4.914331787945979e-06,
+      "loss": 0.9278,
+      "step": 24100
+    },
+    {
+      "epoch": 14.344991108476586,
+      "grad_norm": 8.624448776245117,
+      "learning_rate": 4.511187260632937e-06,
+      "loss": 0.8601,
+      "step": 24200
+    },
+    {
+      "epoch": 14.404267931238886,
+      "grad_norm": 7.910577774047852,
+      "learning_rate": 4.108042733319895e-06,
+      "loss": 0.9198,
+      "step": 24300
+    },
+    {
+      "epoch": 14.463544754001186,
+      "grad_norm": 7.259771823883057,
+      "learning_rate": 3.7048982060068537e-06,
+      "loss": 0.9282,
+      "step": 24400
+    },
+    {
+      "epoch": 14.463544754001186,
+      "eval_loss": 0.08803451806306839,
+      "eval_runtime": 147.5242,
+      "eval_samples_per_second": 3.389,
+      "eval_steps_per_second": 0.427,
+      "eval_wer": 0.20247568523430592,
+      "step": 24400
     }
   ],
   "logging_steps": 100,
@@ -2247,7 +2284,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.121573085577216e+19,
+  "total_flos": 3.173605943279616e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null