| CUDA_VISIBLE_DEVICES=0 python run_audio_classification.py \ | |
| --model_name_or_path facebook/wav2vec2-base \ | |
| --dataset_name superb \ | |
| --dataset_config_name ks \ | |
| --trust_remote_code \ | |
| --output_dir wav2vec2-base-ft-keyword-spotting \ | |
| --overwrite_output_dir \ | |
| --remove_unused_columns False \ | |
| --do_train \ | |
| --do_eval \ | |
| --fp16 \ | |
| --learning_rate 3e-5 \ | |
| --max_length_seconds 1 \ | |
| --attention_mask False \ | |
| --warmup_ratio 0.1 \ | |
| --num_train_epochs 8 \ | |
| --per_device_train_batch_size 64 \ | |
| --gradient_accumulation_steps 4 \ | |
| --per_device_eval_batch_size 32 \ | |
| --dataloader_num_workers 4 \ | |
| --logging_strategy steps \ | |
| --logging_steps 10 \ | |
| --eval_strategy epoch \ | |
| --save_strategy epoch \ | |
| --load_best_model_at_end True \ | |
| --metric_for_best_model accuracy \ | |
| --save_total_limit 3 \ | |
| --seed 0 \ | |
| --push_to_hub \ | |
| --apply-trp --trp-depths 1 --trp-p 0.1 --trp-lambdas 0.4 0.2 0.1 |