自我认知数据集和处理代码
This commit is contained in:
HongCheng
parent
140217593c
commit
1d9ee54555
37
datasets/processed/process_self_cognition.py
Normal file
37
datasets/processed/process_self_cognition.py
Normal file
@ -0,0 +1,37 @@
|
||||
import json
|
||||
|
||||
# 打开JSON文件并读取其内容
|
||||
|
||||
# file_name = 'multi_turn_dataset_1.json'
|
||||
# file_name = 'multi_turn_dataset_2.json'
|
||||
# file_name = 'data_pro.json'
|
||||
file_name = 'self_cognition_EmoLLM.json'
|
||||
|
||||
with open(f'../datasets/{file_name}', 'rt', encoding='utf-8') as file:
|
||||
data = json.load(file)
|
||||
|
||||
n = 0
|
||||
datas = []
|
||||
for i in data:
|
||||
dict_ = dict()
|
||||
# dict_['conversation'] = i
|
||||
# print(dict_)
|
||||
try:
|
||||
dict_['conversation']= [i]
|
||||
dict_['conversation'][0]['input'] = i['instruction']
|
||||
dict_['conversation'][0]['output'] = i['output']
|
||||
dict_['conversation'][0]['system'] = "你是心理健康助手EmoLLM, 由EmoLLM团队打造, 是一个研究过无数具有心理健康问题的病人与心理健康医生对话的心理专家, 在心理方面拥有广博的知识储备和丰富的研究咨询经验。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。"
|
||||
# dict_['conversation']['system']
|
||||
|
||||
dict_['conversation'][0].pop('instruction')
|
||||
# dict_['conversation'] = [dict_['conversation']]
|
||||
datas.append(dict_)
|
||||
except:
|
||||
print(n,i) # 4 empty lines in data.json 425 483 742 1120
|
||||
n+=1
|
||||
|
||||
with open(f'./processed_{file_name}', 'wt', encoding='utf-8') as file:
|
||||
json.dump(datas, file, ensure_ascii=False, indent=4)
|
||||
|
||||
print(datas[0])
|
||||
print(datas[1])
|
||||
219
xtuner_config/llama3_8b_512_qlora_alpaca_e3.py
Normal file
219
xtuner_config/llama3_8b_512_qlora_alpaca_e3.py
Normal file
@ -0,0 +1,219 @@
|
||||
# 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 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.parallel.sequence import SequenceParallelSampler
|
||||
from xtuner.utils import PROMPT_TEMPLATE, SYSTEM_TEMPLATE
|
||||
|
||||
#######################################################################
|
||||
# PART 1 Settings #
|
||||
#######################################################################
|
||||
# Model
|
||||
pretrained_model_name_or_path = 'meta-llama/Meta-Llama-3-8B-Instruct'
|
||||
use_varlen_attn = False
|
||||
|
||||
# Data
|
||||
alpaca_en_path = 'tatsu-lab/alpaca'
|
||||
prompt_template = PROMPT_TEMPLATE.llama3_chat
|
||||
max_length = 512
|
||||
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 = 3
|
||||
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 = SYSTEM_TEMPLATE.alpaca
|
||||
evaluation_inputs = [
|
||||
'请给我介绍五个上海的景点', 'Please tell me five scenic spots in Shanghai'
|
||||
]
|
||||
|
||||
#######################################################################
|
||||
# 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=16,
|
||||
lora_alpha=16,
|
||||
lora_dropout=0.1,
|
||||
bias='none',
|
||||
task_type='CAUSAL_LM'))
|
||||
|
||||
#######################################################################
|
||||
# PART 3 Dataset & Dataloader #
|
||||
#######################################################################
|
||||
alpaca_en = dict(
|
||||
type=process_hf_dataset,
|
||||
dataset=dict(type=load_dataset, path=alpaca_en_path),
|
||||
tokenizer=tokenizer,
|
||||
max_length=max_length,
|
||||
dataset_map_fn=alpaca_map_fn,
|
||||
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=alpaca_en,
|
||||
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)
|
||||
219
xtuner_config/llama3_8b_8k_qlora_alpaca_e3.py
Normal file
219
xtuner_config/llama3_8b_8k_qlora_alpaca_e3.py
Normal file
@ -0,0 +1,219 @@
|
||||
# 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 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.parallel.sequence import SequenceParallelSampler
|
||||
from xtuner.utils import PROMPT_TEMPLATE, SYSTEM_TEMPLATE
|
||||
|
||||
#######################################################################
|
||||
# PART 1 Settings #
|
||||
#######################################################################
|
||||
# Model
|
||||
pretrained_model_name_or_path = 'meta-llama/Meta-Llama-3-8B-Instruct'
|
||||
use_varlen_attn = False
|
||||
|
||||
# Data
|
||||
alpaca_en_path = 'tatsu-lab/alpaca'
|
||||
prompt_template = PROMPT_TEMPLATE.llama3_chat
|
||||
max_length = 8192
|
||||
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 = 3
|
||||
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 = SYSTEM_TEMPLATE.alpaca
|
||||
evaluation_inputs = [
|
||||
'请给我介绍五个上海的景点', 'Please tell me five scenic spots in Shanghai'
|
||||
]
|
||||
|
||||
#######################################################################
|
||||
# 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=16,
|
||||
lora_alpha=16,
|
||||
lora_dropout=0.1,
|
||||
bias='none',
|
||||
task_type='CAUSAL_LM'))
|
||||
|
||||
#######################################################################
|
||||
# PART 3 Dataset & Dataloader #
|
||||
#######################################################################
|
||||
alpaca_en = dict(
|
||||
type=process_hf_dataset,
|
||||
dataset=dict(type=load_dataset, path=alpaca_en_path),
|
||||
tokenizer=tokenizer,
|
||||
max_length=max_length,
|
||||
dataset_map_fn=alpaca_map_fn,
|
||||
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=alpaca_en,
|
||||
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