ValueError: Undefined dataset tatsu-lab/alpaca
Closed this issue · 3 comments
(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 tatsu-lab/alpaca
(yk_py39) amd00@MZ32-00:
[2023-08-03 17:54:26,303] [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 95, in init_for_training
raise ValueError('Undefined dataset {} in {}'.format(
ValueError: Undefined dataset tatsu-lab/alpaca in /home/amd00/llm_dev/Efficient-Tuning-LLMs/chatllms/configs/../../data/dataset_info.yaml
(yk_py39) amd00@MZ32-00:~/llm_dev/Efficient-Tuning-LLMs$
(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$
Warning: You have set local_path for alpaca but it does not exist!