Training in progress, step 33200, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5c9a0489a2cf843b764d138398df3a7a6a5d1d0e8773f219c72b4c09ccfae61
+oid sha256:26cd6571ff6013ee4040c7e9bab5317447cfb4cc34e7b1da8ba6fb8c2ffae362
 size 223144592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6620df8d73410ffb0bf9409a6ade7370440551ac5d5b4428a111e658eecd44
+oid sha256:e9c377312e70d82cb6f732e1d40d46c81b7b9474fba935ebf032c3f1f2757d90
 size 281574266

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28cbe766e4153cd167aa13892e6d8f2b2fb01f0cf38c806d1ede3210aea189b8
+oid sha256:c7233ed33137c98d9b12160c311872e55d6db55aa61e9d7f77192b7e6a13fa95
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ef2649ceb258c6256acc0ae4c4605bb5b2c0540ea4c5d0deec7e198b382fb7a
+oid sha256:b25248087d69965ddef920c8054bb52ba085ee231272e0795b2da361d2f441be
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51726f789396c230f9beb438f4af63a6120e53498ea8e472d26397da95a5f066
+oid sha256:db00d50dd421d79ba139d2536bd27ca7a13377d9e22c077973ca6936cb06d8eb
 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": 23.374131480491716,
+  "epoch": 23.659184037056832,
   "eval_steps": 400,
-  "global_step": 32800,
+  "global_step": 33200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3042,6 +3042,43 @@
       "eval_steps_per_second": 0.399,
       "eval_wer": 0.19952844090775126,
       "step": 32800
+    },
+    {
+      "epoch": 23.445394619632996,
+      "grad_norm": 17.588510513305664,
+      "learning_rate": 6.3456254519161245e-06,
+      "loss": 1.019,
+      "step": 32900
+    },
+    {
+      "epoch": 23.516657758774272,
+      "grad_norm": 13.247255325317383,
+      "learning_rate": 6.0563991323210416e-06,
+      "loss": 1.0711,
+      "step": 33000
+    },
+    {
+      "epoch": 23.587920897915552,
+      "grad_norm": 10.2926025390625,
+      "learning_rate": 5.7671728127259586e-06,
+      "loss": 1.0257,
+      "step": 33100
+    },
+    {
+      "epoch": 23.659184037056832,
+      "grad_norm": 13.390459060668945,
+      "learning_rate": 5.4779464931308756e-06,
+      "loss": 0.9972,
+      "step": 33200
+    },
+    {
+      "epoch": 23.659184037056832,
+      "eval_loss": 0.09225763380527496,
+      "eval_runtime": 158.7123,
+      "eval_samples_per_second": 3.15,
+      "eval_steps_per_second": 0.397,
+      "eval_wer": 0.19952844090775126,
+      "step": 33200
     }
   ],
   "logging_steps": 100,
@@ -3061,7 +3098,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.264348787933184e+19,
+  "total_flos": 4.316381645635584e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null