Training in progress, step 9600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f05a8f3b9545038c737479857e625563b49c5a9e1663b3ff65119eb61b1737
+oid sha256:a0d201c6fdc10947fdcbc30b3469c6b9077d585e2c5868215ae5e42116dc6474
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:587a6bbb80e5a198c0a3b4934e1064f39989cd5a1b237ef58c702e3bc1b6cf00
+oid sha256:130507098d59862ec259645703f3fad405852b629bfaeee0268dc464f0e4f082
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eec015e59980280e108855a6063133888c6e33ebbb2e7fd32e9c10b8162f527
+oid sha256:21322c6272f8d27c689906f590406c6587ddf5b7d44e771d42434753eeebb5d2
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9039f88fb701fdd21221702031af1370bad3952c767b68b088c840170bbc071
+oid sha256:e042f5ae15da2bc4849c16e6e602f27acac8d49038db98bbaa073c1c2141c422
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd348dedbf54f3007c947c40ad8c0727a9e5c37852843e39f15578f9796a9f2d
+oid sha256:3d16e4263aed7ed8110daa9e5727beb6b5d763ac1620f2de37fbf4b96ef6a0aa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 8000,
-  "best_metric": 0.20645446507515472,
-  "best_model_checkpoint": "./distil-whisper/checkpoint-8000",
-  "epoch": 6.553001959736326,
+  "best_global_step": 9600,
+  "best_metric": 0.2045387562628942,
+  "best_model_checkpoint": "./distil-whisper/checkpoint-9600",
+  "epoch": 6.838054516301443,
   "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": 0.405,
       "eval_wer": 0.20733863837312114,
       "step": 9200
+    },
+    {
+      "epoch": 6.624265098877606,
+      "grad_norm": 40.971221923828125,
+      "learning_rate": 3.507021433850702e-05,
+      "loss": 1.9757,
+      "step": 9300
+    },
+    {
+      "epoch": 6.695528238018885,
+      "grad_norm": 39.76367950439453,
+      "learning_rate": 3.4331116038433115e-05,
+      "loss": 1.9012,
+      "step": 9400
+    },
+    {
+      "epoch": 6.766791377160164,
+      "grad_norm": 39.237640380859375,
+      "learning_rate": 3.35920177383592e-05,
+      "loss": 1.9141,
+      "step": 9500
+    },
+    {
+      "epoch": 6.838054516301443,
+      "grad_norm": 31.298519134521484,
+      "learning_rate": 3.2852919438285297e-05,
+      "loss": 2.0199,
+      "step": 9600
+    },
+    {
+      "epoch": 6.838054516301443,
+      "eval_loss": 0.09809073060750961,
+      "eval_runtime": 156.8243,
+      "eval_samples_per_second": 3.188,
+      "eval_steps_per_second": 0.402,
+      "eval_wer": 0.2045387562628942,
+      "step": 9600
     }
   ],
   "logging_steps": 100,
@@ -878,7 +915,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.196048405495808e+19,
+  "total_flos": 1.248081263198208e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null