| SYSTEM = '' | |
| accumulative_counts = 16 | |
| alpaca_en = dict( | |
| dataset=dict( | |
| data_files= | |
| '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/datasets--recogna-nlp--adalberto_dataset/snapshots/0b21870f7cec193508fd22d81be533ca240ee8b1/train.json', | |
| path='json', | |
| type='datasets.load_dataset'), | |
| dataset_map_fn='xtuner.dataset.map_fns.adalberto_map_fn', | |
| max_length=2048, | |
| pack_to_max_length=False, | |
| remove_unused_columns=True, | |
| shuffle_before_pack=True, | |
| template_map_fn=dict( | |
| template='xtuner.utils.PROMPT_TEMPLATE.internlm2_chat', | |
| type='xtuner.dataset.map_fns.template_map_fn_factory'), | |
| tokenizer=dict( | |
| padding_side='right', | |
| pretrained_model_name_or_path= | |
| '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--recogna-nlp--internlm-chatbode-7b/snapshots/b3acf1fa06aa64d49a6f725864316f35dcc885e2', | |
| trust_remote_code=True, | |
| type='transformers.AutoTokenizer.from_pretrained'), | |
| type='xtuner.dataset.process_hf_dataset', | |
| use_varlen_attn=False) | |
| alpaca_en_path = '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/datasets--recogna-nlp--adalberto_dataset/snapshots/0b21870f7cec193508fd22d81be533ca240ee8b1/train.json' | |
| batch_size = 3 | |
| betas = ( | |
| 0.9, | |
| 0.999, | |
| ) | |
| custom_hooks = [ | |
| dict( | |
| tokenizer=dict( | |
| padding_side='right', | |
| pretrained_model_name_or_path= | |
| '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--recogna-nlp--internlm-chatbode-7b/snapshots/b3acf1fa06aa64d49a6f725864316f35dcc885e2', | |
| trust_remote_code=True, | |
| type='transformers.AutoTokenizer.from_pretrained'), | |
| type='xtuner.engine.hooks.DatasetInfoHook'), | |
| dict( | |
| evaluation_inputs=[ | |
| 'O que é um bode?', | |
| 'Qual a capital da França?', | |
| 'Você pode me explicar o Teorema de Pitágoras com um exemplo, por favor?', | |
| 'Olá, tudo bem? Estou procurando livros de ficção científica para ler, você teria sugestões para mim?', | |
| 'Resolva a equação de segundo grau x² - x - 30 = 0', | |
| 'Escreva um código em python para calcular x^y usando divisão e conquista.', | |
| ], | |
| every_n_iters=500, | |
| prompt_template='xtuner.utils.PROMPT_TEMPLATE.internlm2_chat', | |
| system='', | |
| tokenizer=dict( | |
| padding_side='right', | |
| pretrained_model_name_or_path= | |
| '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--recogna-nlp--internlm-chatbode-7b/snapshots/b3acf1fa06aa64d49a6f725864316f35dcc885e2', | |
| trust_remote_code=True, | |
| type='transformers.AutoTokenizer.from_pretrained'), | |
| type='xtuner.engine.hooks.EvaluateChatHook'), | |
| ] | |
| dataloader_num_workers = 0 | |
| default_hooks = dict( | |
| checkpoint=dict( | |
| by_epoch=False, | |
| interval=500, | |
| max_keep_ckpts=2, | |
| type='mmengine.hooks.CheckpointHook'), | |
| logger=dict( | |
| interval=10, | |
| log_metric_by_epoch=False, | |
| type='mmengine.hooks.LoggerHook'), | |
| param_scheduler=dict(type='mmengine.hooks.ParamSchedulerHook'), | |
| sampler_seed=dict(type='mmengine.hooks.DistSamplerSeedHook'), | |
| timer=dict(type='mmengine.hooks.IterTimerHook')) | |
| env_cfg = dict( | |
| cudnn_benchmark=False, | |
| dist_cfg=dict(backend='nccl'), | |
| mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0)) | |
| evaluation_freq = 500 | |
| evaluation_inputs = [ | |
| 'O que é um bode?', | |
| 'Qual a capital da França?', | |
| 'Você pode me explicar o Teorema de Pitágoras com um exemplo, por favor?', | |
| 'Olá, tudo bem? Estou procurando livros de ficção científica para ler, você teria sugestões para mim?', | |
| 'Resolva a equação de segundo grau x² - x - 30 = 0', | |
| 'Escreva um código em python para calcular x^y usando divisão e conquista.', | |
| ] | |
| launcher = 'pytorch' | |
| load_from = 'work_dirs/internlm2_chat_7b_qlora_adalberto/iter_2500.pth' | |
| log_level = 'INFO' | |
| log_processor = dict(by_epoch=False) | |
| lr = 0.0002 | |
| max_epochs = 1 | |
| max_length = 2048 | |
| max_norm = 1 | |
| model = dict( | |
| llm=dict( | |
| attn_implementation='eager', | |
| pretrained_model_name_or_path= | |
| '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--recogna-nlp--internlm-chatbode-7b/snapshots/b3acf1fa06aa64d49a6f725864316f35dcc885e2', | |
| quantization_config=dict( | |
| bnb_4bit_compute_dtype='torch.float16', | |
| bnb_4bit_quant_type='nf4', | |
| bnb_4bit_use_double_quant=True, | |
| llm_int8_has_fp16_weight=False, | |
| llm_int8_threshold=6.0, | |
| load_in_4bit=True, | |
| load_in_8bit=False, | |
| type='transformers.BitsAndBytesConfig'), | |
| torch_dtype='torch.float16', | |
| trust_remote_code=True, | |
| type='transformers.AutoModelForCausalLM.from_pretrained'), | |
| lora=dict( | |
| bias='none', | |
| lora_alpha=128, | |
| lora_dropout=0.1, | |
| r=256, | |
| task_type='CAUSAL_LM', | |
| type='peft.LoraConfig'), | |
| type='xtuner.model.SupervisedFinetune', | |
| use_varlen_attn=False) | |
| optim_type = 'torch.optim.AdamW' | |
| optim_wrapper = dict( | |
| optimizer=dict( | |
| betas=( | |
| 0.9, | |
| 0.999, | |
| ), | |
| lr=0.0002, | |
| type='torch.optim.AdamW', | |
| weight_decay=0), | |
| type='DeepSpeedOptimWrapper') | |
| pack_to_max_length = False | |
| param_scheduler = [ | |
| dict( | |
| begin=0, | |
| by_epoch=True, | |
| convert_to_iter_based=True, | |
| end=0.03, | |
| start_factor=1e-05, | |
| type='mmengine.optim.LinearLR'), | |
| dict( | |
| begin=0.03, | |
| by_epoch=True, | |
| convert_to_iter_based=True, | |
| end=1, | |
| eta_min=0.0, | |
| type='mmengine.optim.CosineAnnealingLR'), | |
| ] | |
| pretrained_model_name_or_path = '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--recogna-nlp--internlm-chatbode-7b/snapshots/b3acf1fa06aa64d49a6f725864316f35dcc885e2' | |
| prompt_template = 'xtuner.utils.PROMPT_TEMPLATE.internlm2_chat' | |
| randomness = dict(deterministic=False, seed=922392227) | |
| resume = True | |
| runner_type = 'FlexibleRunner' | |
| save_steps = 500 | |
| save_total_limit = 2 | |
| strategy = dict( | |
| config=dict( | |
| bf16=dict(enabled=False), | |
| fp16=dict(enabled=True, initial_scale_power=16), | |
| gradient_accumulation_steps='auto', | |
| gradient_clipping='auto', | |
| train_micro_batch_size_per_gpu='auto', | |
| zero_allow_untested_optimizer=True, | |
| zero_force_ds_cpu_optimizer=False, | |
| zero_optimization=dict(overlap_comm=True, stage=2)), | |
| exclude_frozen_parameters=True, | |
| gradient_accumulation_steps=16, | |
| gradient_clipping=1, | |
| sequence_parallel_size=1, | |
| train_micro_batch_size_per_gpu=3, | |
| type='xtuner.engine.DeepSpeedStrategy') | |
| tokenizer = dict( | |
| padding_side='right', | |
| pretrained_model_name_or_path= | |
| '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--recogna-nlp--internlm-chatbode-7b/snapshots/b3acf1fa06aa64d49a6f725864316f35dcc885e2', | |
| trust_remote_code=True, | |
| type='transformers.AutoTokenizer.from_pretrained') | |
| train_cfg = dict(max_epochs=1, type='xtuner.engine.runner.TrainLoop') | |
| train_dataloader = dict( | |
| batch_size=3, | |
| collate_fn=dict( | |
| type='xtuner.dataset.collate_fns.default_collate_fn', | |
| use_varlen_attn=False), | |
| dataset=dict( | |
| dataset=dict( | |
| data_files= | |
| '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/datasets--recogna-nlp--adalberto_dataset/snapshots/0b21870f7cec193508fd22d81be533ca240ee8b1/train.json', | |
| path='json', | |
| type='datasets.load_dataset'), | |
| dataset_map_fn='xtuner.dataset.map_fns.adalberto_map_fn', | |
| max_length=2048, | |
| pack_to_max_length=False, | |
| remove_unused_columns=True, | |
| shuffle_before_pack=True, | |
| template_map_fn=dict( | |
| template='xtuner.utils.PROMPT_TEMPLATE.internlm2_chat', | |
| type='xtuner.dataset.map_fns.template_map_fn_factory'), | |
| tokenizer=dict( | |
| padding_side='right', | |
| pretrained_model_name_or_path= | |
| '/petrobr/parceirosbr/home/luis.afonso/.cache/huggingface/hub/models--recogna-nlp--internlm-chatbode-7b/snapshots/b3acf1fa06aa64d49a6f725864316f35dcc885e2', | |
| trust_remote_code=True, | |
| type='transformers.AutoTokenizer.from_pretrained'), | |
| type='xtuner.dataset.process_hf_dataset', | |
| use_varlen_attn=False), | |
| num_workers=0, | |
| sampler=dict(shuffle=True, type='mmengine.dataset.DefaultSampler')) | |
| use_varlen_attn = False | |
| visualizer = None | |
| warmup_ratio = 0.03 | |
| weight_decay = 0 | |
| work_dir = './work_dirs/internlm2_chat_7b_qlora_adalberto' | |