Training in progress, step 9600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2634ee5c91e47c9d9438951c5a31b6505f921ccdc3c0a21f3663947156853947
+oid sha256:6ca4effc12eba3aac6be54b6ebefbe335a68a355bfa1a4dd5f6a757e3d20e67a
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75bb3146d72d9dd817a812afea831681c0b29bc8550b271772873f4b41dbd457
+oid sha256:7fa103db88bb063249cf00198f06c391c0cbe109211197c08de8bcb1f223a081
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e464bae5ad4106f5a3627e7d672fcdac62ea5f98f2885a50ca5598f6f6382a9
+oid sha256:3fe4aa3c6d64b2359fdca2b677edc0f16c40c47a59d8fb0f684e2e556f14ffab
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a55405e1660e5257b9afd90e5fb43c8cb59734b3562afe4dea9642684f8e6541
+oid sha256:2679b4f3b91289b00dcc38839d58e85292314e6e8c351585202758bc552e8648
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba8b9029ae05745a1673f92384ec22df6e7e540c2703e5221e20ea21bb31a083
+oid sha256:ab9e93c2a1c338d0c2d563b755e9dc5f46b92db971a762ae1d3d9695b77e067d
 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": 5.453467694131595,
+  "epoch": 5.6905749851807945,
   "eval_steps": 400,
-  "global_step": 9200,
+  "global_step": 9600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -859,6 +859,43 @@
       "eval_steps_per_second": 0.432,
       "eval_wer": 0.1943707633362806,
       "step": 9200
+    },
+    {
+      "epoch": 5.512744516893894,
+      "grad_norm": 15.388890266418457,
+      "learning_rate": 3.235610957217606e-05,
+      "loss": 1.3068,
+      "step": 9300
+    },
+    {
+      "epoch": 5.572021339656194,
+      "grad_norm": 12.056999206542969,
+      "learning_rate": 3.1586642043705757e-05,
+      "loss": 1.3009,
+      "step": 9400
+    },
+    {
+      "epoch": 5.631298162418494,
+      "grad_norm": 15.635717391967773,
+      "learning_rate": 3.081717451523546e-05,
+      "loss": 1.2486,
+      "step": 9500
+    },
+    {
+      "epoch": 5.6905749851807945,
+      "grad_norm": 15.254015922546387,
+      "learning_rate": 3.004770698676516e-05,
+      "loss": 1.3753,
+      "step": 9600
+    },
+    {
+      "epoch": 5.6905749851807945,
+      "eval_loss": 0.09110399335622787,
+      "eval_runtime": 146.1078,
+      "eval_samples_per_second": 3.422,
+      "eval_steps_per_second": 0.431,
+      "eval_wer": 0.1940760389036251,
+      "step": 9600
     }
   ],
   "logging_steps": 100,
@@ -878,7 +915,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.19661344980992e+19,
+  "total_flos": 1.24864630751232e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null