Training in progress, step 32800, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720ec26f34508162cd3ed48aa354f1a55bde3c940e3b941db4493d80be90061c
+oid sha256:f5c9a0489a2cf843b764d138398df3a7a6a5d1d0e8773f219c72b4c09ccfae61
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:288024677ae015fd9f07724ebcc4a5c2dde656deb4c2988d4acbc6416d681ba4
+oid sha256:db6620df8d73410ffb0bf9409a6ade7370440551ac5d5b4428a111e658eecd44
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:732b979418123e1232daa0215db26fcf01224d94c16971ed415238028e85e575
+oid sha256:28cbe766e4153cd167aa13892e6d8f2b2fb01f0cf38c806d1ede3210aea189b8
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:676a0c92f411f549dea3afe0b01db3d2c7fd7a67a5bdccc0755488565188383a
+oid sha256:9ef2649ceb258c6256acc0ae4c4605bb5b2c0540ea4c5d0deec7e198b382fb7a
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50ca82bbea02fc725f68bafbc19bec35c56c4c96823814172201a68e0f179761
+oid sha256:51726f789396c230f9beb438f4af63a6120e53498ea8e472d26397da95a5f066
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 32400,
   "best_metric": 0.19510757441791923,
   "best_model_checkpoint": "./distil-whisper/checkpoint-32400",
-  "epoch": 23.0890789239266,
+  "epoch": 23.374131480491716,
   "eval_steps": 400,
-  "global_step": 32400,
+  "global_step": 32800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3005,6 +3005,43 @@
       "eval_steps_per_second": 0.396,
       "eval_wer": 0.19510757441791923,
       "step": 32400
+    },
+    {
+      "epoch": 23.16034206306788,
+      "grad_norm": 15.528765678405762,
+      "learning_rate": 7.502530730296457e-06,
+      "loss": 0.9855,
+      "step": 32500
+    },
+    {
+      "epoch": 23.231605202209156,
+      "grad_norm": 11.74361801147461,
+      "learning_rate": 7.213304410701374e-06,
+      "loss": 1.0193,
+      "step": 32600
+    },
+    {
+      "epoch": 23.302868341350436,
+      "grad_norm": 11.150557518005371,
+      "learning_rate": 6.924078091106291e-06,
+      "loss": 0.9878,
+      "step": 32700
+    },
+    {
+      "epoch": 23.374131480491716,
+      "grad_norm": 11.871788024902344,
+      "learning_rate": 6.634851771511208e-06,
+      "loss": 1.0443,
+      "step": 32800
+    },
+    {
+      "epoch": 23.374131480491716,
+      "eval_loss": 0.09271341562271118,
+      "eval_runtime": 157.7057,
+      "eval_samples_per_second": 3.17,
+      "eval_steps_per_second": 0.399,
+      "eval_wer": 0.19952844090775126,
+      "step": 32800
     }
   ],
   "logging_steps": 100,
@@ -3024,7 +3061,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.212315930230784e+19,
+  "total_flos": 4.264348787933184e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null