Saving train state of step 5000

checkpoint-5000-epoch-0/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c8afe47501f6ac5b2f112cbfc5b57bce18e4930d09140d818a8e1397b02110
+size 3025686376

checkpoint-5000-epoch-0/model_1.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b395c8a7e2bda655c415580106288d0387c227efd641bf4e11c1cd735fdb37a
+size 4361070048

checkpoint-5000-epoch-0/optimizer.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa1457704c96775105d1787f67bb4a4cb2c899b948d39aae7605519a119a841d
+size 955539578

checkpoint-5000-epoch-0/random_states_0.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:182d0310c20462ddb30b52d3b75bc973bf951ee7a1044515e35ba0fa6bf75189
+size 14344

checkpoint-5000-epoch-0/scheduler.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e59aef00050f673889222b3d653de69a99bb1a8c64cad08748089305697e88a
+size 1064

distil-whisper/events.out.tfevents.1715198685.server02.2050598.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c49381c60ae8ceff82f71af02dbf8e86599e6acefc6e343d54f3164ff96cfb4c
-size 1036
+oid sha256:acd480b8f76bebae6dd2b6412b25e2b1b996840cd1b32bf89eb83fd3199a3008
+size 1680

distil-whisper/events.out.tfevents.1715202403.server02.2067342.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:155cd2eec4daa073571f0a64cf8d9e267994346662108932f0971dba6abde89d
+size 88

distil-whisper/events.out.tfevents.1715222264.server02.2131186.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32a06e3a1863146ccc1d6e9d2f7348ca1e03111936f4b49886b06d25442480bd
+size 62058

run_distillation.py

@@ -1756,5 +1756,5 @@ def main():
 if __name__ == "__main__":
     main()
     '''
-    accelerate launch --mixed_precision=bf16 run_distillation.py   --model_name_or_path "./distil-large-v3-init"   --teacher_model_name_or_path "openai/whisper-large-v3"   --train_dataset_name "mozilla-foundation/common_voice_15_0"   --train_dataset_config_name "de"   --train_split_name "train"   --text_column_name "sentence"   --eval_dataset_name "mozilla-foundation/common_voice_15_0"   --eval_dataset_config_name "de"   --eval_split_name "validation"   --eval_text_column_name "sentence"   --eval_steps 5 --save_steps 5   --warmup_steps 500   --learning_rate 1e-4   --lr_scheduler_type "linear"   --logging_steps 5   --save_total_limit 1   --max_steps 15   --per_device_train_batch_size 4   --per_device_eval_batch_size 2   --dataloader_num_workers 2   --preprocessing_num_workers 2   --ddp_timeout 7200   --dtype "bfloat16"   --output_dir "./"   --use_pseudo_labels "false"   --condition_on_prev_probability "0.0"   --do_train   --do_eval   --gradient_checkpointing   --overwrite_output_dir   --predict_with_generate   --freeze_encoder   --streaming   --push_to_hub --language de --max_eval_samples 50
+    accelerate launch --mixed_precision=bf16 run_distillation.py   --model_name_or_path "./distil-large-v3-init"   --teacher_model_name_or_path "openai/whisper-large-v3"   --train_dataset_name "mozilla-foundation/common_voice_15_0"   --train_dataset_config_name "de"   --train_split_name "train"   --text_column_name "sentence"   --eval_dataset_name "mozilla-foundation/common_voice_15_0"   --eval_dataset_config_name "de"   --eval_split_name "validation"   --eval_text_column_name "sentence"   --eval_steps 5000 --save_steps 5000   --warmup_steps 500   --learning_rate 1e-4   --lr_scheduler_type "linear"   --logging_steps 25   --save_total_limit 1   --max_steps 50000   --per_device_train_batch_size 4   --per_device_eval_batch_size 4   --dataloader_num_workers 2   --preprocessing_num_workers 2   --ddp_timeout 7200   --dtype "bfloat16"   --output_dir "./"   --use_pseudo_labels "false"   --condition_on_prev_probability "0.0"   --do_train   --do_eval   --gradient_checkpointing   --overwrite_output_dir   --predict_with_generate   --freeze_encoder   --streaming   --push_to_hub --language de --max_eval_samples 50
     '''