Training in progress, step 33740, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35630aaf8d25704318c506c5652dcc7989eb3675f345f27f818f2ea9f5a27b3e
+oid sha256:892f5770babae72f86fbe7676dc8bcf97db73722f0f63eb0b42e15455a57d7d2
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d2919ac48beca92f152cebfc8ede282362c2a9fbcf84e083ca71a4741ea04a4
+oid sha256:12d045ce4d30a954f6ce12c0249fd382623d3fffc707129bca5a2387cf707b5a
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:576380a256a4340c462ffc82306c52abbab7f38e65a7b12e9ab2634163e0fae7
+oid sha256:a999e0010ea13513073a8d97dfabf347a8d02268da2cd188d9e2ffb955a37853
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:466cefc251c3bff2bf1a7b8f775c63823fd9874f5797306ccc17b28b5d55b904
+oid sha256:fb779461c157e920976902f7e10da553ef08690b8cb1e678f1ad0ceb27b3b0a1
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bade4422d18437c221217e78bc3118e350dee6be4d722036a744d311fb763b10
+oid sha256:ce728e16d5ac03050b00527a8e1a90dc74db0b69a4e3e2d0415dc2af3e021509
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 12000,
   "best_metric": 0.1958443854995579,
   "best_model_checkpoint": "./distil-whisper/checkpoint-12000",
-  "epoch": 19.561351511558982,
+  "epoch": 20.0,
   "eval_steps": 1000,
-  "global_step": 33000,
+  "global_step": 33740,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2615,6 +2615,55 @@
       "eval_steps_per_second": 0.426,
       "eval_wer": 0.2076333628057766,
       "step": 33000
+    },
+    {
+      "epoch": 19.62062833432128,
+      "grad_norm": 6.8571367263793945,
+      "learning_rate": 1.976534296028881e-06,
+      "loss": 0.8777,
+      "step": 33100
+    },
+    {
+      "epoch": 19.67990515708358,
+      "grad_norm": 8.974102020263672,
+      "learning_rate": 1.6756919374247895e-06,
+      "loss": 0.8382,
+      "step": 33200
+    },
+    {
+      "epoch": 19.73918197984588,
+      "grad_norm": 8.73436450958252,
+      "learning_rate": 1.377858002406739e-06,
+      "loss": 0.854,
+      "step": 33300
+    },
+    {
+      "epoch": 19.79845880260818,
+      "grad_norm": 11.128707885742188,
+      "learning_rate": 1.0770156438026475e-06,
+      "loss": 0.8173,
+      "step": 33400
+    },
+    {
+      "epoch": 19.85773562537048,
+      "grad_norm": 6.551008701324463,
+      "learning_rate": 7.76173285198556e-07,
+      "loss": 0.8194,
+      "step": 33500
+    },
+    {
+      "epoch": 19.91701244813278,
+      "grad_norm": 7.966579914093018,
+      "learning_rate": 4.753309265944645e-07,
+      "loss": 0.8342,
+      "step": 33600
+    },
+    {
+      "epoch": 19.97628927089508,
+      "grad_norm": 7.3733978271484375,
+      "learning_rate": 1.7448856799037304e-07,
+      "loss": 0.8733,
+      "step": 33700
     }
   ],
   "logging_steps": 100,
@@ -2629,12 +2678,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.292170106535936e+19,
+  "total_flos": 4.38840243781632e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null