Training in progress, step 9200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86da88a8a0a69d7c1d5f87229394421e4969bf1707a31e76adfff4a7b8cc2037
+oid sha256:f4f05a8f3b9545038c737479857e625563b49c5a9e1663b3ff65119eb61b1737
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4290a9e3ee5aaaf7f950c873e7a267820f9f5f5daf577e9e6c6061285ccf9aec
+oid sha256:587a6bbb80e5a198c0a3b4934e1064f39989cd5a1b237ef58c702e3bc1b6cf00
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8693e088215ad55319b63926487fa8590d0dd7d8f7aa399ff15befdd16bc6ca
+oid sha256:5eec015e59980280e108855a6063133888c6e33ebbb2e7fd32e9c10b8162f527
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ea494ae325733d7a0d93622123a613ff037b948409043828db2a80190e10c8
+oid sha256:c9039f88fb701fdd21221702031af1370bad3952c767b68b088c840170bbc071
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a55c0148d18ab07544f623edb58aa78ea7cbea28a0106207b7e6a3749f37716
+oid sha256:cd348dedbf54f3007c947c40ad8c0727a9e5c37852843e39f15578f9796a9f2d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 8000,
   "best_metric": 0.20645446507515472,
   "best_model_checkpoint": "./distil-whisper/checkpoint-8000",
-  "epoch": 6.26794940317121,
+  "epoch": 6.553001959736326,
   "eval_steps": 400,
-  "global_step": 8800,
+  "global_step": 9200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -822,6 +822,43 @@
       "eval_steps_per_second": 0.401,
       "eval_wer": 0.2116121426466254,
       "step": 8800
+    },
+    {
+      "epoch": 6.339212542312489,
+      "grad_norm": 30.01650047302246,
+      "learning_rate": 3.8026607538802664e-05,
+      "loss": 1.9085,
+      "step": 8900
+    },
+    {
+      "epoch": 6.410475681453768,
+      "grad_norm": 45.52370071411133,
+      "learning_rate": 3.728750923872875e-05,
+      "loss": 1.9014,
+      "step": 9000
+    },
+    {
+      "epoch": 6.481738820595047,
+      "grad_norm": 26.402570724487305,
+      "learning_rate": 3.6548410938654846e-05,
+      "loss": 1.824,
+      "step": 9100
+    },
+    {
+      "epoch": 6.553001959736326,
+      "grad_norm": 43.61695861816406,
+      "learning_rate": 3.580931263858093e-05,
+      "loss": 1.8778,
+      "step": 9200
+    },
+    {
+      "epoch": 6.553001959736326,
+      "eval_loss": 0.09877074509859085,
+      "eval_runtime": 155.4125,
+      "eval_samples_per_second": 3.217,
+      "eval_steps_per_second": 0.405,
+      "eval_wer": 0.20733863837312114,
+      "step": 9200
     }
   ],
   "logging_steps": 100,
@@ -841,7 +878,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.144015547793408e+19,
+  "total_flos": 1.196048405495808e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null