Training in progress, step 9200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb5d7da1b209571a42761f2acda70045e87f2f5393538333c69aa6be5730a682
+oid sha256:2634ee5c91e47c9d9438951c5a31b6505f921ccdc3c0a21f3663947156853947
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4045b8c929a0fb9e7576abf8eb3f4b952fdd4666d17e7350e182722fbc30d896
+oid sha256:75bb3146d72d9dd817a812afea831681c0b29bc8550b271772873f4b41dbd457
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:573b8846751747c8c9f821d740773f26bdc18311fd829c492aee93a262a7fd26
+oid sha256:9e464bae5ad4106f5a3627e7d672fcdac62ea5f98f2885a50ca5598f6f6382a9
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:688eaddc6ab64410ae7ae3de0b5c007c2fdc95cc8779ec9261dd523d672f7de3
+oid sha256:a55405e1660e5257b9afd90e5fb43c8cb59734b3562afe4dea9642684f8e6541
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07c6d599d4044e43352a07d178cf8318fcc3fe97bb451adab81781c82561eae9
+oid sha256:ba8b9029ae05745a1673f92384ec22df6e7e540c2703e5221e20ea21bb31a083
 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": 5.216360403082395,
+  "epoch": 5.453467694131595,
   "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": 0.425,
       "eval_wer": 0.19422340111995284,
       "step": 8800
+    },
+    {
+      "epoch": 5.275637225844695,
+      "grad_norm": 21.900598526000977,
+      "learning_rate": 3.543397968605725e-05,
+      "loss": 1.3348,
+      "step": 8900
+    },
+    {
+      "epoch": 5.334914048606994,
+      "grad_norm": 11.572765350341797,
+      "learning_rate": 3.4664512157586956e-05,
+      "loss": 1.3409,
+      "step": 9000
+    },
+    {
+      "epoch": 5.394190871369295,
+      "grad_norm": 9.629471778869629,
+      "learning_rate": 3.389504462911665e-05,
+      "loss": 1.3919,
+      "step": 9100
+    },
+    {
+      "epoch": 5.453467694131595,
+      "grad_norm": 12.661375045776367,
+      "learning_rate": 3.3125577100646356e-05,
+      "loss": 1.3186,
+      "step": 9200
+    },
+    {
+      "epoch": 5.453467694131595,
+      "eval_loss": 0.09043103456497192,
+      "eval_runtime": 145.9203,
+      "eval_samples_per_second": 3.427,
+      "eval_steps_per_second": 0.432,
+      "eval_wer": 0.1943707633362806,
+      "step": 9200
     }
   ],
   "logging_steps": 100,
@@ -841,7 +878,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.14458059210752e+19,
+  "total_flos": 1.19661344980992e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null