add a script for data_generate and a modified configuration file in xtuner/self.md

xtuner/internlm_chat_7b_qlora_oasst1_e3_copy.py

@@ -0,0 +1,180 @@
+# Copyright (c) OpenMMLab. All rights reserved.
+import torch
+from bitsandbytes.optim import PagedAdamW32bit
+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
+from peft import LoraConfig
+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 oasst1_map_fn, template_map_fn_factory
+from xtuner.engine import DatasetInfoHook, EvaluateChatHook
+from xtuner.model import SupervisedFinetune
+from xtuner.utils import PROMPT_TEMPLATE
+
+#######################################################################
+#                          PART 1  Settings                           #
+#######################################################################
+# Model
+pretrained_model_name_or_path = '/root/personal_assistant/model/Shanghai_AI_Laboratory/internlm-chat-7b'
+
+# Data
+data_path = '/root/personal_assistant/data/personal_assistant.json'
+prompt_template = PROMPT_TEMPLATE.internlm_chat
+max_length = 512
+pack_to_max_length = True
+
+# Scheduler & Optimizer
+batch_size = 2  # per_device
+accumulative_counts = 16
+dataloader_num_workers = 0
+max_epochs = 3
+optim_type = PagedAdamW32bit
+lr = 2e-4
+betas = (0.9, 0.999)
+weight_decay = 0
+max_norm = 1  # grad clip
+
+# Evaluate the generation performance during the training
+evaluation_freq = 90
+SYSTEM = ''
+evaluation_inputs = [ '请介绍一下你自己', '请做一下自我介绍' ]
+
+#######################################################################
+#                      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,
+    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)
+
+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))
+
+#######################################################################
+#                    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=CosineAnnealingLR,
+    eta_min=0.0,
+    by_epoch=True,
+    T_max=max_epochs,
+    convert_to_iter_based=True)
+
+# train, val, test setting
+train_cfg = dict(by_epoch=True, max_epochs=max_epochs, val_interval=1)
+
+#######################################################################
+#                           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)
+]
+
+# configure default hooks
+default_hooks = dict(
+    # record the time of every iteration.
+    timer=dict(type=IterTimerHook),
+    # print log every 100 iterations.
+    logger=dict(type=LoggerHook, interval=10),
+    # enable the parameter scheduler.
+    param_scheduler=dict(type=ParamSchedulerHook),
+    # save checkpoint per epoch.
+    checkpoint=dict(type=CheckpointHook, interval=1),
+    # 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)

xtuner/self.md

@@ -54,7 +54,7 @@ pip install -e '.[all]'
 mkdir /root/personal_assistant/data && cd /root/personal_assistant/data
 ```
 
-在`data`目录下创建一个json文件`personal_assistant.json`作为本次微调所使用的数据集。json中内容可参考下方(复制粘贴n次做数据增广，数据量小无法有效微调，下面仅用于展示格式)
+在`data`目录下创建一个json文件`personal_assistant.json`作为本次微调所使用的数据集。json中内容可参考下方(复制粘贴n次做数据增广，数据量小无法有效微调，下面仅用于展示格式，下面也有生成脚本)
 
 其中`conversation`表示一次对话的内容，`input`为输入，即用户会问的问题，`output`为输出，即想要模型回答的答案。
 
@@ -79,6 +79,35 @@ mkdir /root/personal_assistant/data && cd /root/personal_assistant/data
 ]
 ```
 
+以下是一个python脚本，用于生成数据集。在`data`目录下新建一个generate_data.py文件，将以下代码复制进去，然后运行该脚本即可生成数据集。
+
+```python
+import json
+
+# 输入你的名字
+name = 'Shengshenlan'
+# 重复次数
+n = 10000
+
+data = [
+    {
+        "conversation": [
+            {
+                "input": "请做一下自我介绍",
+                "output": "我是{}的小助手，内在是上海AI实验室书生·浦语的7B大模型哦".format(name)
+            }
+        ]
+    }
+]
+
+for i in range(n):
+    data.append(data[0])
+
+with open('personal_assistant.json', 'w', encoding='utf-8') as f:
+    json.dump(data, f, ensure_ascii=False, indent=4)
+
+```
+
 ### 2.3配置准备
 
 下载模型`InternLM-chat-7B`
@@ -112,6 +141,7 @@ xtuner copy-cfg internlm_chat_7b_qlora_oasst1_e3 .
 ```
 
 修改拷贝后的文件internlm_chat_7b_qlora_oasst1_e3_copy.py，修改下述位置：
+(这是一份修改好的文件[internlm_chat_7b_qlora_oasst1_e3_copy.py](./internlm_chat_7b_qlora_oasst1_e3_copy.py))
 ![xtuner_config_1.png](imgs%2Fxtuner_config_1.png)
 >红框为配置文件中PART 1需要修改的内容