From 3366b8a8bf479b004cb0b56c5293ee249cb3757e Mon Sep 17 00:00:00 2001 From: ZhouXinAo <142309012+zxazys@users.noreply.github.com> Date: Fri, 12 Apr 2024 11:33:32 +0800 Subject: [PATCH] Create internlm2_20b_chat_lora_alpaca_e3.py MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 20b模型的配置文件 --- .../internlm2_20b_chat_lora_alpaca_e3.py | 230 ++++++++++++++++++ 1 file changed, 230 insertions(+) create mode 100644 xtuner_config/internlm2_20b_chat_lora_alpaca_e3.py diff --git a/xtuner_config/internlm2_20b_chat_lora_alpaca_e3.py b/xtuner_config/internlm2_20b_chat_lora_alpaca_e3.py new file mode 100644 index 0000000..40a05d9 --- /dev/null +++ b/xtuner_config/internlm2_20b_chat_lora_alpaca_e3.py @@ -0,0 +1,230 @@ +# Copyright (c) OpenMMLab. All rights reserved. +import torch +from datasets import load_dataset +from mmengine.dataset import DefaultSampler +from mmengine.hooks import (CheckpointHook, DistSamplerSeedHook, IterTimerHook, + LoggerHook, ParamSchedulerHook) +from mmengine.optim import AmpOptimWrapper, CosineAnnealingLR, LinearLR +from peft import LoraConfig +from torch.optim import AdamW +from transformers import (AutoModelForCausalLM, AutoTokenizer, + BitsAndBytesConfig) + +from xtuner.dataset import process_hf_dataset +from xtuner.dataset import ConcatDataset, process_hf_dataset +from xtuner.dataset.collate_fns import default_collate_fn +from xtuner.dataset.map_fns import alpaca_map_fn, template_map_fn_factory +from xtuner.engine.hooks import (DatasetInfoHook, EvaluateChatHook, + VarlenAttnArgsToMessageHubHook) +from xtuner.engine.runner import TrainLoop +from xtuner.model import SupervisedFinetune +from xtuner.utils import PROMPT_TEMPLATE, SYSTEM_TEMPLATE +from mmengine.visualization import Visualizer,WandbVisBackend, TensorboardVisBackend +####################################################################### +# PART 1 Settings # +####################################################################### +# Model +#存储模型的路径 +pretrained_model_name_or_path = '/root/share/model_repos/internlm2-chat-20b' +use_varlen_attn = False + +# Data +#alpaca_en_path = 'tatsu-lab/alpaca' +#两个数据集，存储数据集的路径 +data_path1 = '../datasets/data.json' +data_path2 = '../datasets/result.json' + +prompt_template = PROMPT_TEMPLATE.internlm2_chat +max_length = 3096 +pack_to_max_length = True + +# Scheduler & Optimizer +batch_size = 4 # per_device +accumulative_counts = 4 +dataloader_num_workers = 10 +max_epochs = 3 +optim_type = AdamW +lr = 3e-5 +betas = (0.9, 0.999) +weight_decay = 0.001 +max_norm = 1 # grad clip +warmup_ratio = 0.03 + +# Save +save_steps = 300 +save_total_limit = 2 # Maximum checkpoints to keep (-1 means unlimited) + +# Evaluate the generation performance during the training +evaluation_freq = 100 +SYSTEM = "你是心理健康助手EmoLLM，由EmoLLM团队打造。你旨在通过专业心理咨询，协助来访者完成心理诊断。请充分利用专业心理学知识与咨询技术，一步步帮助来访者解决心理问题。" +evaluation_inputs = [ + '我最近总是感到很焦虑，尤其是在学业上。我有个特别崇拜的同学，他好像在各方面都比我优秀，我总觉得自己怎么努力也追不上他，这让我压力特别大。', '我知道应该理性看待，但就是忍不住会去比较。我甚至晚上会因为这个睡不着觉，总想着怎样才能像他那样出色。' +] + +####################################################################### +# PART 2 Model & Tokenizer # +####################################################################### +tokenizer = dict( + type=AutoTokenizer.from_pretrained, + pretrained_model_name_or_path=pretrained_model_name_or_path, + trust_remote_code=True, + padding_side='right') + +model = dict( + type=SupervisedFinetune, + use_varlen_attn=use_varlen_attn, + llm=dict( + type=AutoModelForCausalLM.from_pretrained, + pretrained_model_name_or_path=pretrained_model_name_or_path, + trust_remote_code=True, + torch_dtype=torch.float16), + lora=dict( + type=LoraConfig, + r=64, + lora_alpha=128, + lora_dropout=0.1, + bias='none', + task_type='CAUSAL_LM')) + +####################################################################### +# PART 3 Dataset & Dataloader # +####################################################################### +data1 = dict( + type=process_hf_dataset, + dataset=dict(type=load_dataset, path='json', data_files=dict(train=data_path1)), + tokenizer=tokenizer, + max_length=max_length, + dataset_map_fn=None, + template_map_fn=dict( + type=template_map_fn_factory, template=prompt_template), + remove_unused_columns=True, + shuffle_before_pack=True, + pack_to_max_length=pack_to_max_length, + use_varlen_attn=use_varlen_attn) + +data2 = dict( + type=process_hf_dataset, + dataset=dict(type=load_dataset, path='json', data_files=dict(train=data_path2)), + tokenizer=tokenizer, + max_length=max_length, + dataset_map_fn=None, + template_map_fn=dict( + type=template_map_fn_factory, template=prompt_template), + remove_unused_columns=True, + shuffle_before_pack=True, + pack_to_max_length=pack_to_max_length, + use_varlen_attn=use_varlen_attn) + + +train_dataset = dict( + type=ConcatDataset, datasets=[data1, data2]) + +train_dataloader = dict( + batch_size=batch_size, + num_workers=dataloader_num_workers, + dataset=train_dataset, + sampler=dict(type=DefaultSampler, shuffle=True), + collate_fn=dict(type=default_collate_fn, use_varlen_attn=use_varlen_attn)) + +####################################################################### +# PART 4 Scheduler & Optimizer # +####################################################################### +# optimizer +optim_wrapper = dict( + type=AmpOptimWrapper, + optimizer=dict( + type=optim_type, lr=lr, betas=betas, weight_decay=weight_decay), + clip_grad=dict(max_norm=max_norm, error_if_nonfinite=False), + accumulative_counts=accumulative_counts, + loss_scale='dynamic', + dtype='float16') + +# learning policy +# More information: https://github.com/open-mmlab/mmengine/blob/main/docs/en/tutorials/param_scheduler.md # noqa: E501 +param_scheduler = [ + dict( + type=LinearLR, + start_factor=1e-5, + by_epoch=True, + begin=0, + end=warmup_ratio * max_epochs, + convert_to_iter_based=True), + dict( + type=CosineAnnealingLR, + eta_min=0.0, + by_epoch=True, + begin=warmup_ratio * max_epochs, + end=max_epochs, + convert_to_iter_based=True) +] + +# train, val, test setting +train_cfg = dict(type=TrainLoop, max_epochs=max_epochs) + +####################################################################### +# PART 5 Runtime # +####################################################################### +# Log the dialogue periodically during the training process, optional +custom_hooks = [ + dict(type=DatasetInfoHook, tokenizer=tokenizer), + dict( + type=EvaluateChatHook, + tokenizer=tokenizer, + every_n_iters=evaluation_freq, + evaluation_inputs=evaluation_inputs, + system=SYSTEM, + prompt_template=prompt_template) +] + +if use_varlen_attn: + custom_hooks += [dict(type=VarlenAttnArgsToMessageHubHook)] + +# configure default hooks +default_hooks = dict( + # record the time of every iteration. + timer=dict(type=IterTimerHook), + # print log every 10 iterations. + logger=dict(type=LoggerHook, log_metric_by_epoch=False, interval=10), + # enable the parameter scheduler. + param_scheduler=dict(type=ParamSchedulerHook), + # save checkpoint per `save_steps`. + checkpoint=dict( + type=CheckpointHook, + by_epoch=False, + interval=save_steps, + max_keep_ckpts=save_total_limit), + # set sampler seed in distributed evrionment. + sampler_seed=dict(type=DistSamplerSeedHook), +) + +# configure environment +env_cfg = dict( + # whether to enable cudnn benchmark + cudnn_benchmark=False, + # set multi process parameters + mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0), + # set distributed parameters + dist_cfg=dict(backend='nccl'), +) + +# set visualizer +visualizer = dict( + type=Visualizer, + vis_backends=[dict(type=WandbVisBackend)] +) + + +# set log level +log_level = 'INFO' + +# load from which checkpoint +load_from = None + +# whether to resume training from the loaded checkpoint +resume = False + +# Defaults to use random seed and disable `deterministic` +randomness = dict(seed=None, deterministic=False) + +# set log processor +log_processor = dict(by_epoch=False)