Training in progress, step 37554, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82e580b76e08cdfb8448ca6d1803c64c049f1cef861419e8036adf1677312206
+oid sha256:e8b9281a6b09625fe8ef329d325b3617b261175ce263da64422ce3eb4bf32fc7
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51fc0f82c59c2b71d10f095d4baf2da47474fd2fe1bbcbc826cc6c39a81ee2ec
+oid sha256:8ddbf47924ce0b202878aefa08df60d1dfdac5bc57f06d3e7653e962c8348d4b
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f328fe058de8a228ddebf585a5f24f49207d162996c245c7975352b2646f7ee
+oid sha256:9b1ee0a7cbe660ccdfb692cb8233c5f11e5835a36f7d6d7c2ae404eb3aaeb573
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c8852b8972fe5d4076d17cae40f3bcca1d0af379559b08bc3be9a35e8e8830
+oid sha256:615a2a304c106eccc92843b64971e0c98b40f210bc51b0ae9becd0dae6a72ab5
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5779eae6320dd873f29bcf99b0bddfe558494d35dfd606a3b158d47caa27415
+oid sha256:e229fb3370f6503adbe15ce94a76f296a892df2f922fc7e71b59c654950e7987
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 28000,
   "best_metric": 0.18110816386678455,
   "best_model_checkpoint": "./distil-whisper/checkpoint-28000",
-  "epoch": 21.675454012888107,
+  "epoch": 22.0,
   "eval_steps": 1000,
-  "global_step": 37000,
+  "global_step": 37554,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2931,6 +2931,41 @@
       "eval_steps_per_second": 0.427,
       "eval_wer": 0.1861184792219275,
       "step": 37000
+    },
+    {
+      "epoch": 21.73403632103105,
+      "grad_norm": 6.6599273681640625,
+      "learning_rate": 1.2738165920008636e-06,
+      "loss": 0.6701,
+      "step": 37100
+    },
+    {
+      "epoch": 21.79261862917399,
+      "grad_norm": 4.662840366363525,
+      "learning_rate": 1.0039401953905112e-06,
+      "loss": 0.7006,
+      "step": 37200
+    },
+    {
+      "epoch": 21.851200937316932,
+      "grad_norm": 6.501893043518066,
+      "learning_rate": 7.340637987801587e-07,
+      "loss": 0.66,
+      "step": 37300
+    },
+    {
+      "epoch": 21.90978324545987,
+      "grad_norm": 5.708708763122559,
+      "learning_rate": 4.6418740216980626e-07,
+      "loss": 0.6819,
+      "step": 37400
+    },
+    {
+      "epoch": 21.968365553602812,
+      "grad_norm": 4.885653018951416,
+      "learning_rate": 1.943110055594538e-07,
+      "loss": 0.7,
+      "step": 37500
     }
   ],
   "logging_steps": 100,
@@ -2945,12 +2980,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.812697871843328e+19,
+  "total_flos": 4.88474711949312e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null