环境

微调框架：LLaMA-Efficient-Tuning 训练机器：4*RTX3090TI (24G显存) python环境：python3.8, 安装requirements.txt依赖包

一、Lora微调

1、准备数据集

2、训练及测试

1）创建模型输出目录

mkdir -p models/baichuan2_13b_chat/train_models/baichuan2_13b_chat_multi_gpus_03_epoch100/train_model

2）创建deepspeed配置文件目录

mkdir -p models/baichuan2_13b_chat/deepspeed_config

3）创建deepspeed配置文件

vi models/baichuan2_13b_chat/deepspeed_config/ds_config_baichuan2_13b_chat_multi_gpus_03_epoch100.json

{

"bf16": {

"enabled": true

},

"fp16": {

"enabled": "auto",

"loss_scale": 0,

"loss_scale_window": 1000,

"initial_scale_power": 16,

"hysteresis": 2,

"min_loss_scale": 1

},

"optimizer": {

"type": "AdamW",

"params": {

"lr": "auto",

"betas": "auto",

"eps": "auto",

"weight_decay": "auto"

}

},

"scheduler": {

"type": "WarmupDecayLR",

"params": {

"last_batch_iteration": -1,

"total_num_steps": "auto",

"warmup_min_lr": "auto",

"warmup_max_lr": "auto",

"warmup_num_steps": "auto"

}

},

"zero_optimization": {

"stage": 3,

"offload_optimizer": {

"device": "cpu",

"pin_memory": true

},

"offload_param": {

"device": "cpu",

"pin_memory": true

},

"overlap_comm": true,

"contiguous_gradients": true,

"sub_group_size": 1e9,

"reduce_bucket_size": "auto",

"stage3_prefetch_bucket_size": "auto",

"stage3_param_persistence_threshold": "auto",

"stage3_max_live_parameters": 2e9,

"stage3_max_reuse_distance": 2e9,

"stage3_gather_16bit_weights_on_model_save": true

},

"gradient_accumulation_steps": "auto",

"gradient_clipping": "auto",

"steps_per_print": 2000,

"train_batch_size": "auto",

"train_micro_batch_size_per_gpu": "auto",

"wall_clock_breakdown": false

}

4）训练模型

deepspeed --num_nodes 1 --num_gpus 4 --master_port=9901 src/train_bash.py \

--stage sft \

--model_name_or_path baichuan-inc/Baichuan2-13B-Chat \

--do_train \

--dataset example1 \

--template baichuan2 \

--finetuning_type lora \

--lora_rank 16 \

--lora_target W_pack,o_proj,gate_proj,down_proj,up_proj \

--output_dir models/baichuan2_13b_chat/train_models/baichuan2_13b_chat_multi_gpus_03_epoch100/train_model \

--overwrite_cache \

--per_device_train_batch_size 4 \

--gradient_accumulation_steps 4 \

--preprocessing_num_workers 4 \

--lr_scheduler_type cosine \

--logging_steps 10 \

--save_steps 100 \

--learning_rate 5e-3 \

--max_grad_norm 0.5 \

--num_train_epochs 300.0 \

--evaluation_strategy steps \

--plot_loss \

--bf16 \

--deepspeed models/baichuan2_13b_chat/deepspeed_config/ds_config_baichuan2_13b_chat_multi_gpus_03_epoch100.json

[INFO|trainer.py:1686] 2023-09-19 04:07:47,607 >> ***** Running training *****

[INFO|trainer.py:1687] 2023-09-19 04:07:47,607 >> Num examples = 94

[INFO|trainer.py:1688] 2023-09-19 04:07:47,608 >> Num Epochs = 300

[INFO|trainer.py:1689] 2023-09-19 04:07:47,608 >> Instantaneous batch size per device = 4

[INFO|trainer.py:1692] 2023-09-19 04:07:47,608 >> Total train batch size (w. parallel, distributed & accumulation) = 64

[INFO|trainer.py:1693] 2023-09-19 04:07:47,608 >> Gradient Accumulation steps = 4

[INFO|trainer.py:1694] 2023-09-19 04:07:47,608 >> Total optimization steps = 300

[INFO|trainer.py:1695] 2023-09-19 04:07:47,612 >> Number of trainable parameters = 55,787,520

{'loss': 7.7023, 'learning_rate': 0.00488255033557047, 'epoch': 6.67}

{'loss': 7.0675, 'learning_rate': 0.004714765100671141, 'epoch': 13.33}

8%|█████████▊ | 25/300 [17:10<3:07:01, 40.81s/it]

测试模型

python src/cli_demo.py \

--model_name_or_path baichuan-inc/Baichuan2-13B-Chat \

--template baichuan2 \

--finetuning_type lora \

--checkpoint_dir models/baichuan2_13b_chat/train_models/baichuan2_13b_chat_multi_gpus_03_epoch100/train_model

3、注意事项：

1）我用的是3090TI显卡，使用fp16精度时，训练结果始终没有效果，而且训练到后面有（loss为0）的问题。这个不清楚时什么原因。所以需要采用bf16，deepspeed配置文件中要将bf16配置为true。训练时添加参数–bf16 。 所以如果显卡不是 3090TI ，可以尝试用 --fp16。

Refer:

使用baichuan2-13B进行微调时出现loss全为0的情况Deepspeed zero3对Baichuan系的13b-chat进行微调，微调效果失效（Baichuan-13b-chat和Baichuan2-13b-chat都尝试过）

2）deepspeed中 stage 需要选择 3 。尝试过 2 ，内存会溢出。 3) 报错：AttributeError: 'Parameter' object has no attribute 'ds_status' ; 解决办法：关闭验证集，比如 --val_size 0.01, --load_best_model_at_end

Refer:

Baichuan2-13B-Base微调eval报错

此次训练，loss还没降下去，测试效果不太理想。但是知识库微调成功，只是表达凌乱。所以建议如果知识库不大的话，尽量用单卡训练，效果更好。

好文链接

评论可见，请评论后查看内容，谢谢！！！
 您阅读本篇文章共花了：