Training in progress, step 33600, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a33e2a9a0affd051aac1c7665e18997e84b227fc64a2d65fa9609bf1aee62a7f
+oid sha256:23ef42a9fc9233dcc343084f9ce7d93482fb05b80136c44f06eb62dce740e1e1
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2308dca1affc41f4139adeab34b202780dbaffa38d33da74d10bffbdc9f992
+oid sha256:32c869cc0994601b8230c0fb7be3b823eef4092219ab8cbfc386196f812e2946
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a32623e1d63738a1bdeec437a263adbe9abe4c93b22549ff8aec372a656d11a0
+oid sha256:d3c799733816fb8c27de7a857b6166730dd1c37c89ae2ebf9b77cbef47bdf09b
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff937df5339a9bf718c213945c933aaacb1c82d2eaba042eefa6236253ea20ed
+oid sha256:f0ca45c6ca9d8e60f0da01fa0c96188461c4c1df90a4d99312ba8b2c40b8e0f3
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa5c3c0fcb7217371c4e23f5780d2467b353babca52533f15bb43ba98008fae8
+oid sha256:3625cf5c5369228475174d4f84a602898f6a11c9e59317a786848cd0367b3ce2
 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": 19.67990515708358,
+  "epoch": 19.91701244813278,
   "eval_steps": 400,
-  "global_step": 33200,
+  "global_step": 33600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3079,6 +3079,43 @@
       "eval_steps_per_second": 0.427,
       "eval_wer": 0.19790745652814618,
       "step": 33200
+    },
+    {
+      "epoch": 19.73918197984588,
+      "grad_norm": 8.436558723449707,
+      "learning_rate": 1.377858002406739e-06,
+      "loss": 0.857,
+      "step": 33300
+    },
+    {
+      "epoch": 19.79845880260818,
+      "grad_norm": 10.084759712219238,
+      "learning_rate": 1.0770156438026475e-06,
+      "loss": 0.8229,
+      "step": 33400
+    },
+    {
+      "epoch": 19.85773562537048,
+      "grad_norm": 6.3987836837768555,
+      "learning_rate": 7.76173285198556e-07,
+      "loss": 0.8247,
+      "step": 33500
+    },
+    {
+      "epoch": 19.91701244813278,
+      "grad_norm": 7.521144866943359,
+      "learning_rate": 4.753309265944645e-07,
+      "loss": 0.8416,
+      "step": 33600
+    },
+    {
+      "epoch": 19.91701244813278,
+      "eval_loss": 0.08716024458408356,
+      "eval_runtime": 149.0302,
+      "eval_samples_per_second": 3.355,
+      "eval_steps_per_second": 0.423,
+      "eval_wer": 0.2002652519893899,
+      "step": 33600
     }
   ],
   "logging_steps": 100,
@@ -3098,7 +3135,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.318186535387136e+19,
+  "total_flos": 4.370219393089536e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null