Comments (3)
(yk_py39) amd00@MZ32-00:~/llm_dev/Efficient-Tuning-LLMs$ git diff
diff --git a/data/dataset_info.yaml b/data/dataset_info.yaml
index 47dc433..b5ff767 100644
--- a/data/dataset_info.yaml
+++ b/data/dataset_info.yaml
@@ -1,7 +1,7 @@
The dataset_info.yaml file contains the information of the datasets used in the experiments.
alpaca:
hf_hub_url: tatsu-lab/alpaca
- local_path: tatsu-lab/alpaca/alpaca.json
- local_path:
dataset_format: alpaca
multi_turn: False
(yk_py39) amd00@MZ32-00:~/llm_dev/Efficient-Tuning-LLMs$
yk_py39) amd00@MZ32-00:/llm_dev/Efficient-Tuning-LLMs$/llm_dev/Efficient-Tuning-LLMs$ python train_qlora.py --model_name_or_path /home/amd00/hf_model/llama-7b --output_dir ./out-llama-7b --dataset_name alpaca --num_train_epochs 4 --per_device_train_batch_size 4 --per_device_eval_batch_size 4 --gradient_accumulation_steps 8 --evaluation_strategy steps --eval_steps 50 --save_strategy steps --save_total_limit 5 --save_steps 100 --logging_strategy steps --logging_steps 1 --learning_rate 0.0002 --warmup_ratio 0.03 --weight_decay 0.0 --lr_scheduler_type constant --adam_beta2 0.999 --max_grad_norm 0.3 --max_new_tokens 32 --lora_r 64 --lora_alpha 16 --lora_dropout 0.1 --double_quant --quant_type nf4 --fp16 --bits 4 --gradient_checkpointing --trust_remote_code --do_train --do_eval --sample_generate --data_seed 42 --seed 0
(yk_py39) amd00@MZ32-00:
[2023-08-03 18:09:46,641] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect)
Traceback (most recent call last):
File "/home/amd00/llm_dev/Efficient-Tuning-LLMs/train_qlora.py", line 102, in
main()
File "/home/amd00/llm_dev/Efficient-Tuning-LLMs/train_qlora.py", line 31, in main
data_args.init_for_training()
File "/home/amd00/llm_dev/Efficient-Tuning-LLMs/chatllms/configs/data_args.py", line 114, in init_for_training
raise Warning(
Warning: You have set local_path for alpaca but it does not exist! Will load the data from tatsu-lab/alpaca
(yk_py39) amd00@MZ32-00:~/llm_dev/Efficient-Tuning-LLMs$
from llamatuner.
Warning: You have set local_path for alpaca but it does not exist!
from llamatuner.
please visit README.md to see how to use the dataset
from llamatuner.
Related Issues (20)
- 中文文档里没写对baichuan-13B的支持,但英文写了 HOT 1
- 微调训练失败 HOT 4
- 多卡似乎不能将每张卡跑满,请问如何才能让每张卡的计算负载跑满呢 HOT 13
- 单机多卡并行训练报错 HOT 3
- Baichuan7B使用lora微调后测试时总会再次输出query HOT 1
- 下载了百川7b模型后,直接在gradio_webserver.py里推理,生成内容乱码问题 HOT 3
- llama2-13B和llama2-70b微调所需要的显卡配置 HOT 1
- 如何使用自己的数据集 HOT 1
- zero3保存的模型无法加载 HOT 2
- About llama-2-70B fine-tuning HOT 2
- [问题]有关训练可视化 HOT 2
- 总是这个错误怎么解决 HOT 1
- llama-2-13b的模型用单卡跑lora就会报错 HOT 1
- QLORA微调alpaca_data.json报错 'padding_value' (position 3) must be float, not NoneType HOT 2
- 微调后的Llama-2-7b,在模型加载时出错 HOT 1
- 批量推理时结果异常
- 该项目与qlora的差别
- 不同样式的样本对应什么样的情形,如何根据自己的需求选择样本的样式
- 参数设置
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from llamatuner.