finance_qwen_VL_7B / args.json
guneetsk99's picture
Upload 16 files
6e3e050 verified
{
"model": "Qwen/Qwen2-VL-7B-Instruct",
"model_type": "qwen2_vl",
"model_revision": null,
"torch_dtype": "bfloat16",
"attn_impl": null,
"rope_scaling": null,
"device_map": null,
"local_repo_path": null,
"template": "qwen2_vl",
"system": null,
"max_length": 32768,
"truncation_strategy": "delete",
"max_pixels": null,
"tools_prompt": "react_en",
"loss_scale": "default",
"sequence_parallel_size": 1,
"use_chat_template": true,
"template_backend": "swift",
"dataset": [
"structured_dataset.jsonl"
],
"val_dataset": [],
"split_dataset_ratio": 0.01,
"data_seed": 42,
"dataset_num_proc": 1,
"streaming": false,
"load_from_cache_file": false,
"download_mode": "reuse_dataset_if_exists",
"strict": false,
"model_name": [
null,
null
],
"model_author": [
null,
null
],
"custom_dataset_info": [],
"quant_method": null,
"quant_bits": null,
"hqq_axis": null,
"bnb_4bit_compute_dtype": "bfloat16",
"bnb_4bit_quant_type": "nf4",
"bnb_4bit_use_double_quant": true,
"bnb_4bit_quant_storage": null,
"max_new_tokens": null,
"temperature": 0.0,
"top_k": null,
"top_p": null,
"repetition_penalty": null,
"num_beams": 1,
"stream": false,
"stop_words": [],
"tuner_backend": "peft",
"train_type": "lora",
"seed": 42,
"model_kwargs": {},
"load_dataset_config": false,
"use_hf": false,
"hub_token": null,
"custom_register_path": [],
"ignore_args_error": false,
"use_swift_lora": false,
"output_dir": "/root/multimodal/output/Qwen2-VL-7B-Instruct/v4-20241217-191810",
"overwrite_output_dir": false,
"do_train": false,
"do_eval": false,
"do_predict": false,
"eval_strategy": "steps",
"prediction_loss_only": false,
"per_device_train_batch_size": 2,
"per_device_eval_batch_size": 1,
"per_gpu_train_batch_size": null,
"per_gpu_eval_batch_size": null,
"gradient_accumulation_steps": 16,
"eval_accumulation_steps": null,
"eval_delay": 0,
"torch_empty_cache_steps": null,
"learning_rate": 0.0001,
"weight_decay": 0.1,
"adam_beta1": 0.9,
"adam_beta2": 0.999,
"adam_epsilon": 1e-08,
"max_grad_norm": 1.0,
"num_train_epochs": 5.0,
"max_steps": -1,
"lr_scheduler_type": "cosine",
"lr_scheduler_kwargs": null,
"warmup_ratio": 0.0,
"warmup_steps": 0,
"log_level": "passive",
"log_level_replica": "warning",
"log_on_each_node": true,
"logging_dir": "/root/multimodal/output/Qwen2-VL-7B-Instruct/v4-20241217-191810/runs",
"logging_strategy": "steps",
"logging_first_step": true,
"logging_steps": 5,
"logging_nan_inf_filter": true,
"save_strategy": "steps",
"save_steps": 100.0,
"save_total_limit": 2,
"save_safetensors": true,
"save_on_each_node": false,
"save_only_model": false,
"restore_callback_states_from_checkpoint": false,
"no_cuda": false,
"use_cpu": false,
"use_mps_device": false,
"jit_mode_eval": false,
"use_ipex": false,
"bf16": true,
"fp16": false,
"fp16_opt_level": "O1",
"half_precision_backend": "auto",
"bf16_full_eval": false,
"fp16_full_eval": false,
"tf32": null,
"local_rank": -1,
"ddp_backend": null,
"tpu_num_cores": null,
"tpu_metrics_debug": false,
"debug": null,
"dataloader_drop_last": false,
"eval_steps": 100.0,
"dataloader_num_workers": 0,
"dataloader_prefetch_factor": null,
"past_index": -1,
"run_name": null,
"disable_tqdm": null,
"remove_unused_columns": false,
"label_names": null,
"load_best_model_at_end": false,
"metric_for_best_model": "loss",
"greater_is_better": false,
"ignore_data_skip": false,
"fsdp": "",
"fsdp_min_num_params": 0,
"fsdp_config": null,
"fsdp_transformer_layer_cls_to_wrap": null,
"accelerator_config": {
"dispatch_batches": false
},
"deepspeed": null,
"label_smoothing_factor": 0.0,
"optim": "adamw_torch",
"optim_args": null,
"adafactor": false,
"group_by_length": false,
"length_column_name": "length",
"report_to": [
"tensorboard"
],
"ddp_find_unused_parameters": null,
"ddp_bucket_cap_mb": null,
"ddp_broadcast_buffers": null,
"dataloader_pin_memory": true,
"dataloader_persistent_workers": false,
"skip_memory_metrics": true,
"use_legacy_prediction_loop": false,
"push_to_hub": false,
"resume_from_checkpoint": null,
"hub_model_id": null,
"hub_strategy": "every_save",
"hub_private_repo": false,
"hub_always_push": false,
"gradient_checkpointing": true,
"gradient_checkpointing_kwargs": null,
"include_inputs_for_metrics": false,
"include_for_metrics": [],
"eval_do_concat_batches": true,
"fp16_backend": "auto",
"evaluation_strategy": "steps",
"push_to_hub_model_id": null,
"push_to_hub_organization": null,
"push_to_hub_token": null,
"mp_parameters": "",
"auto_find_batch_size": false,
"full_determinism": false,
"torchdynamo": null,
"ray_scope": "last",
"ddp_timeout": 1800,
"torch_compile": false,
"torch_compile_backend": null,
"torch_compile_mode": null,
"dispatch_batches": null,
"split_batches": null,
"include_tokens_per_second": null,
"include_num_input_tokens_seen": null,
"neftune_noise_alpha": null,
"optim_target_modules": null,
"batch_eval_metrics": false,
"eval_on_start": false,
"use_liger_kernel": false,
"eval_use_gather_object": false,
"average_tokens_across_devices": null,
"sortish_sampler": false,
"predict_with_generate": false,
"generation_max_length": null,
"generation_num_beams": null,
"generation_config": null,
"freeze_parameters": [
"visual",
"visual.merger"
],
"freeze_parameters_ratio": 0.0,
"trainable_parameters": [],
"freeze_llm": false,
"freeze_vit": true,
"freeze_aligner": true,
"target_modules": [
"all-linear"
],
"target_regex": null,
"modules_to_save": [],
"lora_rank": 8,
"lora_alpha": 32,
"lora_dropout": 0.05,
"lora_bias": "none",
"lora_dtype": null,
"lorap_lr_ratio": null,
"use_rslora": false,
"use_dora": false,
"lora_ga_batch_size": 2,
"lora_ga_iters": 2,
"lora_ga_max_length": 1024,
"lora_ga_direction": "ArB2r",
"lora_ga_scale": "stable",
"lora_ga_stable_gamma": 16,
"init_weights": true,
"fourier_n_frequency": 2000,
"fourier_scaling": 300.0,
"boft_block_size": 4,
"boft_block_num": 0,
"boft_n_butterfly_factor": 1,
"boft_dropout": 0.0,
"vera_rank": 256,
"vera_projection_prng_key": 0,
"vera_dropout": 0.0,
"vera_d_initial": 0.1,
"adapter_act": "gelu",
"adapter_length": 128,
"use_galore": false,
"galore_target_modules": null,
"galore_rank": 128,
"galore_update_proj_gap": 50,
"galore_scale": 1.0,
"galore_proj_type": "std",
"galore_optim_per_parameter": false,
"galore_with_embedding": false,
"galore_quantization": false,
"galore_proj_quant": false,
"galore_proj_bits": 4,
"galore_proj_group_size": 256,
"galore_cos_threshold": 0.4,
"galore_gamma_proj": 2,
"galore_queue_size": 5,
"adalora_target_r": 8,
"adalora_init_r": 12,
"adalora_tinit": 0,
"adalora_tfinal": 0,
"adalora_deltaT": 1,
"adalora_beta1": 0.85,
"adalora_beta2": 0.85,
"adalora_orth_reg_weight": 0.5,
"llamapro_num_new_blocks": 4,
"llamapro_num_groups": null,
"lisa_activated_layers": 0,
"lisa_step_interval": 20,
"reft_layer_key": null,
"reft_layers": null,
"reft_rank": 4,
"reft_intervention_type": "LoreftIntervention",
"reft_args": null,
"use_liger": false,
"model_layer_cls_name": null,
"metric_warmup_step": 0,
"fsdp_num": 1,
"acc_steps": 1,
"add_version": true,
"resume_only_model": false,
"check_model": true,
"loss_type": null,
"num_labels": null,
"packing": false,
"lazy_tokenize": null,
"acc_strategy": "token",
"optimizer": null,
"metric": null,
"rank": -1,
"local_world_size": 1,
"model_suffix": "Qwen2-VL-7B-Instruct",
"model_info": "ModelInfo(model_type='qwen2_vl', model_dir='/root/.cache/modelscope/hub/Qwen/Qwen2-VL-7B-Instruct', torch_dtype=torch.bfloat16, max_model_len=32768, quant_method=None, quant_bits=None, config={'type': 'mrope', 'mrope_section': [16, 24, 24]})",
"model_meta": "ModelMeta(model_type='qwen2_vl', model_groups=[ModelGroup(models=[Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct', hf_model_id='Qwen/Qwen2-VL-2B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct', hf_model_id='Qwen/Qwen2-VL-7B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct', hf_model_id='Qwen/Qwen2-VL-72B-Instruct', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B', hf_model_id='Qwen/Qwen2-VL-2B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B', hf_model_id='Qwen/Qwen2-VL-7B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B', hf_model_id='Qwen/Qwen2-VL-72B', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4', hf_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8', hf_model_id='Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-2B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-VL-2B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-7B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-VL-7B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='Qwen/Qwen2-VL-72B-Instruct-AWQ', hf_model_id='Qwen/Qwen2-VL-72B-Instruct-AWQ', model_path=None, ms_revision=None, hf_revision=None)], ignore_file_pattern=None, requires=None, tags=[])], template='qwen2_vl', get_function=<function get_model_tokenizer_qwen2_vl at 0x7f7edfdd2440>, model_arch='qwen2_vl', architectures=['Qwen2VLForConditionalGeneration'], is_multimodal=True, additional_saved_files=[], torch_dtype=None, ignore_file_pattern=['*.zip', '*.gguf', '*.pth', '*.pt', 'consolidated*', 'onnx', '*.safetensors.md', '*.msgpack', '*.onnx', '*.ot', '*.h5', '*.bin', '*.safetensors'], requires=['transformers>=4.45', 'qwen_vl_utils', 'pyav'], tags=[])",
"model_dir": "/root/.cache/modelscope/hub/Qwen/Qwen2-VL-7B-Instruct",
"hub": "<class 'swift.hub.hub.MSHub'>",
"training_args": "Seq2SeqTrainingArguments(output_dir='/root/multimodal/output/Qwen2-VL-7B-Instruct/v4-20241217-191810', overwrite_output_dir=False, do_train=False, do_eval=True, do_predict=False, eval_strategy=<IntervalStrategy.STEPS: 'steps'>, prediction_loss_only=False, per_device_train_batch_size=2, per_device_eval_batch_size=1, per_gpu_train_batch_size=None, per_gpu_eval_batch_size=None, gradient_accumulation_steps=16, eval_accumulation_steps=None, eval_delay=0, torch_empty_cache_steps=None, learning_rate=0.0001, weight_decay=0.1, adam_beta1=0.9, adam_beta2=0.999, adam_epsilon=1e-08, max_grad_norm=1.0, num_train_epochs=5.0, max_steps=-1, lr_scheduler_type=<SchedulerType.COSINE: 'cosine'>, lr_scheduler_kwargs=None, warmup_ratio=0.0, warmup_steps=0, log_level='passive', log_level_replica='warning', log_on_each_node=True, logging_dir='/root/multimodal/output/Qwen2-VL-7B-Instruct/v4-20241217-191810/runs', logging_strategy=<IntervalStrategy.STEPS: 'steps'>, logging_first_step=True, logging_steps=5, logging_nan_inf_filter=True, save_strategy=<IntervalStrategy.STEPS: 'steps'>, save_steps=100, save_total_limit=2, save_safetensors=True, save_on_each_node=False, save_only_model=False, restore_callback_states_from_checkpoint=False, no_cuda=False, use_cpu=False, use_mps_device=False, seed=42, data_seed=42, jit_mode_eval=False, use_ipex=False, bf16=True, fp16=False, fp16_opt_level='O1', half_precision_backend='auto', bf16_full_eval=False, fp16_full_eval=False, tf32=None, local_rank=0, ddp_backend=None, tpu_num_cores=None, tpu_metrics_debug=False, debug=[], dataloader_drop_last=False, eval_steps=100, dataloader_num_workers=0, dataloader_prefetch_factor=None, past_index=-1, run_name='/root/multimodal/output/Qwen2-VL-7B-Instruct/v4-20241217-191810', disable_tqdm=False, remove_unused_columns=False, label_names=None, load_best_model_at_end=False, metric_for_best_model='loss', greater_is_better=False, ignore_data_skip=False, fsdp=[], fsdp_min_num_params=0, fsdp_config={'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}, fsdp_transformer_layer_cls_to_wrap=None, accelerator_config=AcceleratorConfig(split_batches=False, dispatch_batches=False, even_batches=True, use_seedable_sampler=True, non_blocking=False, gradient_accumulation_kwargs=None, use_configured_state=False), deepspeed=None, label_smoothing_factor=0.0, optim=<OptimizerNames.ADAMW_TORCH: 'adamw_torch'>, optim_args=None, adafactor=False, group_by_length=False, length_column_name='length', report_to=['tensorboard'], ddp_find_unused_parameters=None, ddp_bucket_cap_mb=None, ddp_broadcast_buffers=None, dataloader_pin_memory=True, dataloader_persistent_workers=False, skip_memory_metrics=True, use_legacy_prediction_loop=False, push_to_hub=False, resume_from_checkpoint=None, hub_model_id=None, hub_strategy=<HubStrategy.EVERY_SAVE: 'every_save'>, hub_token=None, hub_private_repo=False, hub_always_push=False, gradient_checkpointing=True, gradient_checkpointing_kwargs=None, include_inputs_for_metrics=False, include_for_metrics=[], eval_do_concat_batches=True, fp16_backend='auto', evaluation_strategy='steps', push_to_hub_model_id=None, push_to_hub_organization=None, push_to_hub_token=None, mp_parameters='', auto_find_batch_size=False, full_determinism=False, torchdynamo=None, ray_scope='last', ddp_timeout=1800, torch_compile=False, torch_compile_backend=None, torch_compile_mode=None, dispatch_batches=None, split_batches=None, include_tokens_per_second=None, include_num_input_tokens_seen=None, neftune_noise_alpha=None, optim_target_modules=None, batch_eval_metrics=False, eval_on_start=False, use_liger_kernel=False, eval_use_gather_object=False, average_tokens_across_devices=None, sortish_sampler=False, predict_with_generate=False, generation_max_length=None, generation_num_beams=None, generation_config=None, acc_strategy='token', sequence_parallel_size=1, check_model=True, train_sampler_random=True, is_encoder_decoder=False, metric_warmup_step=0, train_dataset_sample=-1, fsdp_num=1, acc_steps=1, train_type='lora')"
}