Training in progress, epoch 49, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f365b1320449815ffe0c16e52e26940676932948040e0b1163ae8ae80adb3f
+oid sha256:46f26b7c7b98aea584520e7cb43e0c742a2fab82d01bbc510e14658ecd7060c0
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2928b4c21ccb3daa4250e10e9a90837a277360cdb2e57d69cd6b99fc42071346
+oid sha256:a9a9b2d74d1927f905921e170cea4cd074caeff6c9fa3e6c6457198a1efed480
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a609e80108e1f20e139f34415efcc0eb15e758c086a88fcb14861619965f6cd4
+oid sha256:cb264940fbf03f94d8e47f1772b5a686e13ccf938b92dfbcbf596e8b0d470855
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b56613432949077a9a1bb74b405267dca8de0fcdf4d4e0c13eb2317ba12b4f0
+oid sha256:130318fbfb45bf27f44198c9d3acab280dc9bda99dd669b2a413ca9672551f5e
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ad8d61e710272e3c5e9fa76888f18c92bc475e8c3e8156da39262eababf15c1
+oid sha256:7aba72fb2d8e27204901b5d6a919d20063e1ff32ba82923c6be3270dacccacab
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 17738,
   "best_metric": 0.2120542292956086,
   "best_model_checkpoint": "./distil-whisper/checkpoint-17738",
-  "epoch": 49.0,
+  "epoch": 49.972101673899566,
   "eval_steps": 500,
-  "global_step": 19758,
+  "global_step": 20150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1882,6 +1882,43 @@
       "eval_steps_per_second": 0.421,
       "eval_wer": 0.2163277335691129,
       "step": 19758
+    },
+    {
+      "epoch": 49.104153750774955,
+      "grad_norm": 19.84515380859375,
+      "learning_rate": 1.8575063613231552e-06,
+      "loss": 1.4737,
+      "step": 19800
+    },
+    {
+      "epoch": 49.3521388716677,
+      "grad_norm": 14.313343048095703,
+      "learning_rate": 1.3486005089058526e-06,
+      "loss": 1.5536,
+      "step": 19900
+    },
+    {
+      "epoch": 49.60012399256045,
+      "grad_norm": 13.140170097351074,
+      "learning_rate": 8.396946564885497e-07,
+      "loss": 1.4557,
+      "step": 20000
+    },
+    {
+      "epoch": 49.84810911345319,
+      "grad_norm": 17.50598907470703,
+      "learning_rate": 3.3078880407124687e-07,
+      "loss": 1.5171,
+      "step": 20100
+    },
+    {
+      "epoch": 49.972101673899566,
+      "eval_loss": 0.10252001881599426,
+      "eval_runtime": 149.0596,
+      "eval_samples_per_second": 3.354,
+      "eval_steps_per_second": 0.423,
+      "eval_wer": 0.2120542292956086,
+      "step": 20150
     }
   ],
   "logging_steps": 100,
@@ -1896,12 +1933,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.567967870025728e+19,
+  "total_flos": 2.61896007057408e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null