Error when run bash run_scripts/s1.sh #6
Description
Hi @Hertin @BradyFU, Thanks for opening source the training code of LUCY. when running the training scripts in README, an error occurs:
$ bash run_scripts/s1.sh
...
usage: train.py [-h] [--model_type MODEL_TYPE] [--model_name_or_path MODEL_NAME_OR_PATH] [--tokenizer_name_or_path TOKENIZER_NAME_OR_PATH] [--audio_encoder AUDIO_ENCODER] [--model_hidden_size MODEL_HIDDEN_SIZE] [--freeze_backbone [FREEZE_BACKBONE]] [--no_freeze_backbone] [--freeze_audio_encoder [FREEZE_AUDIO_ENCODER]] [--no_freeze_audio_encoder]
[--freeze_tts_adapter [FREEZE_TTS_ADAPTER]] [--no_freeze_tts_adapter] [--freeze_audio_encoder_adapter [FREEZE_AUDIO_ENCODER_ADAPTER]] [--no_freeze_audio_encoder_adapter] [--freeze_lm_head [FREEZE_LM_HEAD]] [--freeze_embed_tokens [FREEZE_EMBED_TOKENS]] [--no_freeze_embed_tokens] [--audio_encoder_hidden_size AUDIO_ENCODER_HIDDEN_SIZE]
[--audio_projector_type AUDIO_PROJECTOR_TYPE] [--text_vocab_size TEXT_VOCAB_SIZE] [--text_special_tokens TEXT_SPECIAL_TOKENS] [--audio_vocab_size AUDIO_VOCAB_SIZE] [--audio_special_tokens AUDIO_SPECIAL_TOKENS] [--audio_projector_hidden_size AUDIO_PROJECTOR_HIDDEN_SIZE] [--audio_num_codebook AUDIO_NUM_CODEBOOK]
[--text_additional TEXT_ADDITIONAL [TEXT_ADDITIONAL ...]] [--audio_additional AUDIO_ADDITIONAL [AUDIO_ADDITIONAL ...]] [--emotion_token_as_text [EMOTION_TOKEN_AS_TEXT]] [--cache_dir CACHE_DIR] [--model_max_length MODEL_MAX_LENGTH] [--tune_text_embed [TUNE_TEXT_EMBED]] [--tie_word_embeddings [TIE_WORD_EMBEDDINGS]]
[--loss_reduction LOSS_REDUCTION] [--post_tts_adapter [POST_TTS_ADAPTER]] [--initialize_additional_modules [INITIALIZE_ADDITIONAL_MODULES]] [--post_tts_adapter_num_layers POST_TTS_ADAPTER_NUM_LAYERS] [--loss_weights LOSS_WEIGHTS [LOSS_WEIGHTS ...]] [--audio_in AUDIO_IN [AUDIO_IN ...]] [--text_in TEXT_IN [TEXT_IN ...]]
[--codec_out CODEC_OUT [CODEC_OUT ...]] [--text_out TEXT_OUT [TEXT_OUT ...]] [--data_jsons DATA_JSONS [DATA_JSONS ...]] [--data_codecs DATA_CODECS [DATA_CODECS ...]] [--eval_audio_in EVAL_AUDIO_IN [EVAL_AUDIO_IN ...]] [--eval_text_in EVAL_TEXT_IN [EVAL_TEXT_IN ...]] [--eval_codec_out EVAL_CODEC_OUT [EVAL_CODEC_OUT ...]]
[--eval_text_out EVAL_TEXT_OUT [EVAL_TEXT_OUT ...]] [--eval_data_jsons EVAL_DATA_JSONS [EVAL_DATA_JSONS ...]] [--eval_data_codecs EVAL_DATA_CODECS [EVAL_DATA_CODECS ...]] [--asr_template ASR_TEMPLATE] [--audio_encoder_type AUDIO_ENCODER_TYPE] [--use_last_turn_if_codec [USE_LAST_TURN_IF_CODEC]] [--negative_tsvs NEGATIVE_TSVS [NEGATIVE_TSVS ...]]
[--negative_ratio NEGATIVE_RATIO] [--data_ratio DATA_RATIO [DATA_RATIO ...]] [--max_convs MAX_CONVS] [--max_input_length MAX_INPUT_LENGTH] [--sample_rate SAMPLE_RATE] [--audio_feature_rate AUDIO_FEATURE_RATE] [--max_keep_sample_size MAX_KEEP_SAMPLE_SIZE] [--min_keep_sample_size MIN_KEEP_SAMPLE_SIZE] [--num_codebook NUM_CODEBOOK]
[--text_additional_tokens TEXT_ADDITIONAL_TOKENS] [--audio_additional_tokens AUDIO_ADDITIONAL_TOKENS] [--padded_vocab_size PADDED_VOCAB_SIZE] [--padded_audio_vocab_size PADDED_AUDIO_VOCAB_SIZE] [--tasks TASKS [TASKS ...]] [--add_codec_target [ADD_CODEC_TARGET]] [--no_add_codec_target] [--emotion_tk_as_text [EMOTION_TK_AS_TEXT]] --output_dir
OUTPUT_DIR [--overwrite_output_dir [OVERWRITE_OUTPUT_DIR]] [--do_train [DO_TRAIN]] [--do_eval [DO_EVAL]] [--do_predict [DO_PREDICT]] [--eval_strategy {no,steps,epoch}] [--prediction_loss_only [PREDICTION_LOSS_ONLY]] [--per_device_train_batch_size PER_DEVICE_TRAIN_BATCH_SIZE] [--per_device_eval_batch_size PER_DEVICE_EVAL_BATCH_SIZE]
[--per_gpu_train_batch_size PER_GPU_TRAIN_BATCH_SIZE] [--per_gpu_eval_batch_size PER_GPU_EVAL_BATCH_SIZE] [--gradient_accumulation_steps GRADIENT_ACCUMULATION_STEPS] [--eval_accumulation_steps EVAL_ACCUMULATION_STEPS] [--eval_delay EVAL_DELAY] [--learning_rate LEARNING_RATE] [--weight_decay WEIGHT_DECAY] [--adam_beta1 ADAM_BETA1]
[--adam_beta2 ADAM_BETA2] [--adam_epsilon ADAM_EPSILON] [--max_grad_norm MAX_GRAD_NORM] [--num_train_epochs NUM_TRAIN_EPOCHS] [--max_steps MAX_STEPS] [--lr_scheduler_type {linear,cosine,cosine_with_restarts,polynomial,constant,constant_with_warmup,inverse_sqrt,reduce_lr_on_plateau,cosine_with_min_lr,warmup_stable_decay}]
[--lr_scheduler_kwargs LR_SCHEDULER_KWARGS] [--warmup_ratio WARMUP_RATIO] [--warmup_steps WARMUP_STEPS] [--log_level {detail,debug,info,warning,error,critical,passive}] [--log_level_replica {detail,debug,info,warning,error,critical,passive}] [--log_on_each_node [LOG_ON_EACH_NODE]] [--no_log_on_each_node] [--logging_dir LOGGING_DIR]
[--logging_strategy {no,steps,epoch}] [--logging_first_step [LOGGING_FIRST_STEP]] [--logging_steps LOGGING_STEPS] [--logging_nan_inf_filter [LOGGING_NAN_INF_FILTER]] [--no_logging_nan_inf_filter] [--save_strategy {no,steps,epoch}] [--save_steps SAVE_STEPS] [--save_total_limit SAVE_TOTAL_LIMIT] [--save_safetensors [SAVE_SAFETENSORS]]
[--no_save_safetensors] [--save_on_each_node [SAVE_ON_EACH_NODE]] [--save_only_model [SAVE_ONLY_MODEL]] [--restore_callback_states_from_checkpoint [RESTORE_CALLBACK_STATES_FROM_CHECKPOINT]] [--no_cuda [NO_CUDA]] [--use_cpu [USE_CPU]] [--use_mps_device [USE_MPS_DEVICE]] [--seed SEED] [--data_seed DATA_SEED] [--jit_mode_eval [JIT_MODE_EVAL]]
[--use_ipex [USE_IPEX]] [--bf16 [BF16]] [--fp16 [FP16]] [--fp16_opt_level FP16_OPT_LEVEL] [--half_precision_backend {auto,apex,cpu_amp}] [--bf16_full_eval [BF16_FULL_EVAL]] [--fp16_full_eval [FP16_FULL_EVAL]] [--tf32 TF32] [--local_rank LOCAL_RANK] [--ddp_backend {nccl,gloo,mpi,ccl,hccl,cncl}] [--tpu_num_cores TPU_NUM_CORES]
[--tpu_metrics_debug [TPU_METRICS_DEBUG]] [--debug DEBUG [DEBUG ...]] [--dataloader_drop_last [DATALOADER_DROP_LAST]] [--eval_steps EVAL_STEPS] [--dataloader_num_workers DATALOADER_NUM_WORKERS] [--dataloader_prefetch_factor DATALOADER_PREFETCH_FACTOR] [--past_index PAST_INDEX] [--run_name RUN_NAME] [--disable_tqdm DISABLE_TQDM]
[--remove_unused_columns [REMOVE_UNUSED_COLUMNS]] [--no_remove_unused_columns] [--label_names LABEL_NAMES [LABEL_NAMES ...]] [--load_best_model_at_end [LOAD_BEST_MODEL_AT_END]] [--metric_for_best_model METRIC_FOR_BEST_MODEL] [--greater_is_better GREATER_IS_BETTER] [--ignore_data_skip [IGNORE_DATA_SKIP]] [--fsdp FSDP]
[--fsdp_min_num_params FSDP_MIN_NUM_PARAMS] [--fsdp_config FSDP_CONFIG] [--fsdp_transformer_layer_cls_to_wrap FSDP_TRANSFORMER_LAYER_CLS_TO_WRAP] [--accelerator_config ACCELERATOR_CONFIG] [--deepspeed DEEPSPEED] [--label_smoothing_factor LABEL_SMOOTHING_FACTOR] [--optim OPTIM] [--optim_args OPTIM_ARGS] [--adafactor [ADAFACTOR]]
[--group_by_length [GROUP_BY_LENGTH]] [--length_column_name LENGTH_COLUMN_NAME] [--report_to REPORT_TO] [--ddp_find_unused_parameters DDP_FIND_UNUSED_PARAMETERS] [--ddp_bucket_cap_mb DDP_BUCKET_CAP_MB] [--ddp_broadcast_buffers DDP_BROADCAST_BUFFERS] [--dataloader_pin_memory [DATALOADER_PIN_MEMORY]] [--no_dataloader_pin_memory]
[--dataloader_persistent_workers [DATALOADER_PERSISTENT_WORKERS]] [--skip_memory_metrics [SKIP_MEMORY_METRICS]] [--no_skip_memory_metrics] [--use_legacy_prediction_loop [USE_LEGACY_PREDICTION_LOOP]] [--push_to_hub [PUSH_TO_HUB]] [--resume_from_checkpoint RESUME_FROM_CHECKPOINT] [--hub_model_id HUB_MODEL_ID]
[--hub_strategy {end,every_save,checkpoint,all_checkpoints}] [--hub_token HUB_TOKEN] [--hub_private_repo [HUB_PRIVATE_REPO]] [--hub_always_push [HUB_ALWAYS_PUSH]] [--gradient_checkpointing [GRADIENT_CHECKPOINTING]] [--gradient_checkpointing_kwargs GRADIENT_CHECKPOINTING_KWARGS] [--include_inputs_for_metrics [INCLUDE_INPUTS_FOR_METRICS]]
[--eval_do_concat_batches [EVAL_DO_CONCAT_BATCHES]] [--no_eval_do_concat_batches] [--fp16_backend {auto,apex,cpu_amp}] [--evaluation_strategy {no,steps,epoch}] [--push_to_hub_model_id PUSH_TO_HUB_MODEL_ID] [--push_to_hub_organization PUSH_TO_HUB_ORGANIZATION] [--push_to_hub_token PUSH_TO_HUB_TOKEN] [--mp_parameters MP_PARAMETERS]
[--auto_find_batch_size [AUTO_FIND_BATCH_SIZE]] [--full_determinism [FULL_DETERMINISM]] [--torchdynamo TORCHDYNAMO] [--ray_scope RAY_SCOPE] [--ddp_timeout DDP_TIMEOUT] [--torch_compile [TORCH_COMPILE]] [--torch_compile_backend TORCH_COMPILE_BACKEND] [--torch_compile_mode TORCH_COMPILE_MODE] [--dispatch_batches DISPATCH_BATCHES]
[--split_batches SPLIT_BATCHES] [--include_tokens_per_second [INCLUDE_TOKENS_PER_SECOND]] [--include_num_input_tokens_seen [INCLUDE_NUM_INPUT_TOKENS_SEEN]] [--neftune_noise_alpha NEFTUNE_NOISE_ALPHA] [--optim_target_modules OPTIM_TARGET_MODULES] [--batch_eval_metrics [BATCH_EVAL_METRICS]] [--bits BITS] [--double_quant [DOUBLE_QUANT]]
[--no_double_quant] [--quant_type QUANT_TYPE] [--mm_projector_lr MM_PROJECTOR_LR]
train.py: error: argument --audio_in: expected at least one argument
seems like some arguments is not set. Any fix?