I uploaded my private github repo as data set to private hugging face dataset. Below is the error I receive when I try to train using PEFT method
2024-05-05 18:43:36.206142: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:9261] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered
2024-05-05 18:43:36.206194: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:607] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered
2024-05-05 18:43:36.207621: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1515] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered
2024-05-05 18:43:36.214881: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2024-05-05 18:43:37.321192: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
usage: train.py [-h] --model_name_or_path MODEL_NAME_OR_PATH [--lora_alpha LORA_ALPHA]
[--lora_dropout LORA_DROPOUT] [--lora_r LORA_R]
[--lora_target_modules LORA_TARGET_MODULES]
[--use_nested_quant [USE_NESTED_QUANT]]
[--bnb_4bit_compute_dtype BNB_4BIT_COMPUTE_DTYPE]
[--bnb_4bit_quant_type BNB_4BIT_QUANT_TYPE] [--use_flash_attn [USE_FLASH_ATTN]]
[--use_peft_lora [USE_PEFT_LORA]]
[--use_8bit_qunatization [USE_8BIT_QUNATIZATION]]
[--use_4bit_quantization [USE_4BIT_QUANTIZATION]]
[--use_reentrant [USE_REENTRANT]] [--use_unsloth [USE_UNSLOTH]]
[--use_loftq [USE_LOFTQ]] [--use_loftq_callback [USE_LOFTQ_CALLBACK]]
[--dataset_name DATASET_NAME] [--dataset_text_field DATASET_TEXT_FIELD]
[--max_seq_length MAX_SEQ_LENGTH] [--test_size TEST_SIZE] [--fim_rate FIM_RATE]
[--fim_spm_rate FIM_SPM_RATE] [--splits SPLITS] --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 {adamw_hf,adamw_torch,adamw_torch_fused,adamw_torch_xla,adamw_torch_npu_fused,adamw_apex_fused,adafactor,adamw_anyprecision,sgd,adagrad,adamw_bnb_8bit,adamw_8bit,lion_8bit,lion_32bit,paged_adamw_32bit,paged_adamw_8bit,paged_lion_32bit,paged_lion_8bit,rmsprop,rmsprop_bnb,rmsprop_bnb_8bit,rmsprop_bnb_32bit,galore_adamw,galore_adamw_8bit,galore_adafactor,galore_adamw_layerwise,galore_adamw_8bit_layerwise,galore_adafactor_layerwise}]
[--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]
train.py: error: ambiguous option: --split could match --splits, --split_batches