Saving train state of step 1000

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "./distil-large-v3-init",
+  "_name_or_path": "openai/whisper-large-v3",
   "activation_dropout": 0.0,
   "activation_function": "gelu",
   "apply_spec_augment": false,

distil-whisper/events.out.tfevents.1727223225.22c57e4734ce.13411.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c1f39e61f34ffd721eb64bd3d5d7799afae89413b54fe5532242beb335477c
+size 88

distil-whisper/events.out.tfevents.1727223588.22c57e4734ce.14278.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6109060c54ad1230fdc32ded249fd5a11ad84ffb2c740c561c25738017fc5347
+size 12458

run_distillation.sh

@@ -22,8 +22,8 @@ python run_distillation.py \
   --save_total_limit 1 \
   --max_steps 10000 \
   --wer_threshold 20 \
-  --per_device_train_batch_size 40 \
-  --per_device_eval_batch_size 40 \
+  --per_device_train_batch_size 30 \
+  --per_device_eval_batch_size 30 \
   --dataloader_num_workers 8 \
   --preprocessing_num_workers 8 \
   --ddp_timeout 7200 \