C:\Users\workstation.conda\envs\qwen-vl\python.exe C:\Users\workstation\Desktop\Qwen-VL-master\finetune.py C:\Users\workstation\Desktop\Qwen-VL-master\output_dir
C:\Users\workstation.conda\envs\qwen-vl\lib\site-packages\deepspeed\runtime\zero\linear.py:44: FutureWarning: torch.cuda.amp.custom_fwd(args...) is deprecated. Please use torch.amp.custom_fwd(args..., device_type='cuda') instead.
def forward(ctx, input, weight, bias=None):
C:\Users\workstation.conda\envs\qwen-vl\lib\site-packages\deepspeed\runtime\zero\linear.py:70: FutureWarning: torch.cuda.amp.custom_bwd(args...) is deprecated. Please use torch.amp.custom_bwd(args..., device_type='cuda') instead.
def backward(ctx, grad_output):
C:\Users\workstation.conda\envs\qwen-vl\lib\site-packages\transformers\utils\generic.py:482: FutureWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch_pytree.register_pytree_node(
C:\Users\workstation.conda\envs\qwen-vl\lib\site-packages\transformers\utils\generic.py:339: FutureWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.
torch_pytree.register_pytree_node(
C:\Users\workstation.conda\envs\qwen-vl\lib\site-packages\transformers\deepspeed.py:24: FutureWarning: transformers.deepspeed module is deprecated and will be removed in a future version. Please import deepspeed modules directly from transformers.integrations
warnings.warn(
usage: finetune.py [-h] [--model_name_or_path MODEL_NAME_OR_PATH]
[--data_path DATA_PATH] [--eval_data_path EVAL_DATA_PATH]
[--lazy_preprocess [LAZY_PREPROCESS]] --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]
[--torch_empty_cache_steps TORCH_EMPTY_CACHE_STEPS]
[--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]]
[--eval_on_start [EVAL_ON_START]]
[--eval_use_gather_object [EVAL_USE_GATHER_OBJECT]]
[--cache_dir CACHE_DIR]
[--model_max_length MODEL_MAX_LENGTH]
[--use_lora [USE_LORA]] [--no_use_lora]
[--fix_vit [FIX_VIT]] [--no_fix_vit] [--lora_r LORA_R]
[--lora_alpha LORA_ALPHA] [--lora_dropout LORA_DROPOUT]
[--lora_target_modules LORA_TARGET_MODULES [LORA_TARGET_MODULES ...]]
[--lora_weight_path LORA_WEIGHT_PATH]
[--lora_bias LORA_BIAS] [--q_lora [Q_LORA]]
finetune.py: error: the following arguments are required: --output_dir
进程已结束，退出代码为 2