Create internlm2_5_chat_7b_qlora_oasst1_e3.py
This commit is contained in:
Kevin Rose
GitHub
parent
9faf452f39
commit
fc4210f11a
226
xtuner_config/internlm2_5_chat_7b_qlora_oasst1_e3.py
Normal file
226
xtuner_config/internlm2_5_chat_7b_qlora_oasst1_e3.py
Normal file
@ -0,0 +1,226 @@
|
||||
# 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.collate_fns import default_collate_fn
|
||||
from xtuner.dataset.map_fns import 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.parallel.sequence import SequenceParallelSampler
|
||||
from xtuner.utils import PROMPT_TEMPLATE
|
||||
|
||||
#######################################################################
|
||||
# PART 1 Settings #
|
||||
#######################################################################
|
||||
# Model
|
||||
pretrained_model_name_or_path = './internlm2_5-7b-chat'
|
||||
use_varlen_attn = False
|
||||
|
||||
# Data
|
||||
data_path = './data.jsonl'
|
||||
prompt_template = PROMPT_TEMPLATE.internlm2_chat
|
||||
max_length = 2048
|
||||
pack_to_max_length = True
|
||||
|
||||
# parallel
|
||||
sequence_parallel_size = 1
|
||||
|
||||
# Scheduler & Optimizer
|
||||
batch_size = 1 # per_device
|
||||
accumulative_counts = 16
|
||||
accumulative_counts *= sequence_parallel_size
|
||||
dataloader_num_workers = 0
|
||||
max_epochs = 4
|
||||
optim_type = AdamW
|
||||
lr = 2e-4
|
||||
betas = (0.9, 0.999)
|
||||
weight_decay = 0
|
||||
max_norm = 1 # grad clip
|
||||
warmup_ratio = 0.03
|
||||
|
||||
# Save
|
||||
save_steps = 500
|
||||
save_total_limit = 2 # Maximum checkpoints to keep (-1 means unlimited)
|
||||
|
||||
# Evaluate the generation performance during the training
|
||||
evaluation_freq = 500
|
||||
SYSTEM = f'''你是一个心理专家, 除了在心理方面拥有广博的知识储备和丰富的研究咨询经验, 还具有科学家的如下特质:
|
||||
1.客观理性：科学家会在处理感情问题时保持一定的客观和理性。例如，当他们遇到争执时，可能会试图从一个更客观的角度分析问题的根源，而不是让情绪主导。他们可能会提出具体的问题，试图理解双方的观点，并寻找基于逻辑和事实的解决方案。
|
||||
2.深入探讨：科学家在对话中会展现出对深层次理解的追求。在与别人讨论话题时，他们可能不满足于表面的聊天，而是倾向于深入探讨背后的原因和动机。例如，当谈论到个人的兴趣或职业选择时，他们可能会好奇地询问为什么她做出这样的选择，以及这背后的心理动力是什么。
|
||||
3.理性沟通：在遇到感情纠纷或误解时，科学家会倾向于通过理性的沟通来解决问题。他们可能会提倡开放和诚实的对话，鼓励双方表达自己的感受和观点，并尝试找到双方都能接受的解决方案。他们可能会避免使用指责的语言，而是努力理解对方的立场，并寻求共同的理解。
|
||||
4.好奇心：在日常生活中，科学家会表现出对朋友生活的好奇心。他们可能对她的工作、爱好、或是过去的经历感兴趣，并愿意花时间去了解和探索。这种好奇心不仅可以增加双方的交流和了解，也能使关系更加丰富多彩。
|
||||
5.在与他人交流时，科学家会注重清晰和精确的表达，有时会引用相关知识库和相关研究结果，有时会引用相关著作的内容来证明自己的观点。同时，他们也可能会倾听他人的观点，并以开放的心态接受不同的意见和反馈。
|
||||
|
||||
我现在有一些问题，请你解答：
|
||||
'''
|
||||
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,
|
||||
quantization_config=dict(
|
||||
type=BitsAndBytesConfig,
|
||||
load_in_4bit=True,
|
||||
load_in_8bit=False,
|
||||
llm_int8_threshold=6.0,
|
||||
llm_int8_has_fp16_weight=False,
|
||||
bnb_4bit_compute_dtype=torch.float16,
|
||||
bnb_4bit_use_double_quant=True,
|
||||
bnb_4bit_quant_type='nf4')),
|
||||
lora=dict(
|
||||
type=LoraConfig,
|
||||
r=64,
|
||||
lora_alpha=16,
|
||||
lora_dropout=0.1,
|
||||
bias='none',
|
||||
task_type='CAUSAL_LM'))
|
||||
|
||||
#######################################################################
|
||||
# PART 3 Dataset & Dataloader #
|
||||
#######################################################################
|
||||
train_dataset = dict(
|
||||
type=process_hf_dataset,
|
||||
dataset=dict(type=load_dataset, path='json', data_files=dict(train=data_path)),
|
||||
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)
|
||||
|
||||
sampler = SequenceParallelSampler \
|
||||
if sequence_parallel_size > 1 else DefaultSampler
|
||||
train_dataloader = dict(
|
||||
batch_size=batch_size,
|
||||
num_workers=dataloader_num_workers,
|
||||
dataset=train_dataset,
|
||||
sampler=dict(type=sampler, 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 = None
|
||||
|
||||
# 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)
|
||||
Loading…
Reference in New Issue
Block a user