Training in progress, step 30000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3327b0b8af85925610a41cee7c7ae4963a7b7dde6cc08465efc2826ef5c0af2
+oid sha256:2105cf7a5c87ba982f87194bf389b220d816f9425c25ae107f042200ab4b16f2
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93bad43f4b8af45a608a4b225343bd214941a8efeb3c4c469a14c0c86c0ab957
+oid sha256:051e18e97a9194053216c43776da56ec3eda3abdc1ab8afb6b1b39ca733cdb32
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b9421ad0d5b73228617c1cf302e1d33ef76aeb1e4831b98c6e9c5c8cf44bf4
+oid sha256:4b5cc2e059bf5994720338ae5c6e6dec69e298afa0568c75f8adaffc4768726d
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c416cfd8c4766d6cc7a298c9543da4fe2068ac18114961cd2b770fab5f0668d7
+oid sha256:7ba137982c64fa8b963ffa3da35dfd85bc4ae996706d0bfce9f15caad6a862fa
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68304b2d0c95d2b28b071e7dc26d0215ae7596f8485d75f9bb15fd5d82eef471
+oid sha256:4690afe34793ca3a29158fb149768d32cc1f45ba8e1ff250dc324b500662d817
 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": 17.190278601066982,
+  "epoch": 17.783046828689983,
   "eval_steps": 1000,
-  "global_step": 29000,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2299,6 +2299,85 @@
       "eval_steps_per_second": 0.426,
       "eval_wer": 0.1989389920424403,
       "step": 29000
+    },
+    {
+      "epoch": 17.249555423829282,
+      "grad_norm": 6.731088638305664,
+      "learning_rate": 4.292506529163597e-06,
+      "loss": 0.9345,
+      "step": 29100
+    },
+    {
+      "epoch": 17.30883224659158,
+      "grad_norm": 12.75145435333252,
+      "learning_rate": 3.95767762673274e-06,
+      "loss": 0.8958,
+      "step": 29200
+    },
+    {
+      "epoch": 17.36810906935388,
+      "grad_norm": 6.983468055725098,
+      "learning_rate": 3.6228487243018817e-06,
+      "loss": 0.8837,
+      "step": 29300
+    },
+    {
+      "epoch": 17.42738589211618,
+      "grad_norm": 6.845942974090576,
+      "learning_rate": 3.288019821871024e-06,
+      "loss": 0.8323,
+      "step": 29400
+    },
+    {
+      "epoch": 17.48666271487848,
+      "grad_norm": 7.515448570251465,
+      "learning_rate": 2.9531909194401663e-06,
+      "loss": 0.8625,
+      "step": 29500
+    },
+    {
+      "epoch": 17.545939537640784,
+      "grad_norm": 6.841838836669922,
+      "learning_rate": 2.6183620170093084e-06,
+      "loss": 0.8454,
+      "step": 29600
+    },
+    {
+      "epoch": 17.605216360403084,
+      "grad_norm": 16.295787811279297,
+      "learning_rate": 2.2835331145784505e-06,
+      "loss": 0.8664,
+      "step": 29700
+    },
+    {
+      "epoch": 17.664493183165384,
+      "grad_norm": 7.235702991485596,
+      "learning_rate": 1.9487042121475926e-06,
+      "loss": 0.8713,
+      "step": 29800
+    },
+    {
+      "epoch": 17.723770005927683,
+      "grad_norm": 7.121592998504639,
+      "learning_rate": 1.6138753097167347e-06,
+      "loss": 0.8724,
+      "step": 29900
+    },
+    {
+      "epoch": 17.783046828689983,
+      "grad_norm": 7.38678503036499,
+      "learning_rate": 1.279046407285877e-06,
+      "loss": 0.8303,
+      "step": 30000
+    },
+    {
+      "epoch": 17.783046828689983,
+      "eval_loss": 0.08706488460302353,
+      "eval_runtime": 146.9212,
+      "eval_samples_per_second": 3.403,
+      "eval_steps_per_second": 0.429,
+      "eval_wer": 0.20218096080165046,
+      "step": 30000
     }
   ],
   "logging_steps": 100,
@@ -2318,7 +2397,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.771898440450048e+19,
+  "total_flos": 3.901980584706048e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null