LMFlow

LMFlow copied to clipboard

demo of DPO with QLoRA (w Llama3 70B Instruct)

1

anchen1011

Full parameter fine-tuning bugs

3

I got this bug. ` bash run.sh [2024-06-20 23:47:57,121] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-06-20 23:48:00,497] [WARNING] [runner.py:196:fetch_hostfile] Unable to find hostfile, will proceed with training with...

tankeui

[BUG] The text cannot be generated successfully during the Raft step

1

**Describe the bug** When I use the fine-tuned LLAMA3 model to run the `examples/raft_align.py` script, I encountered the following error: ``` Traceback (most recent call last): File "/home/work/user-job-dir/app/liubiao/llm/LMflow/examples/raft_align.py", line 220,...

biaoliu-kiritsugu

multi-gpu full para train error

2

[2024-06-12 19:36:07,800] [INFO] [real_accelerator.py:191:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-06-12 19:36:09,648] [WARNING] [runner.py:202:fetch_hostfile] Unable to find hostfile, will proceed with training with local resources only. [2024-06-12 19:36:09,648] [INFO] [runner.py:568:main]...

tankeui

Discussion about LISA

2

In the article, only the comparison of the average weight paradigm of each layer during lora fine-tuning is given. 1. But what if their weights are different before fine-tuning? 2....

caoshuai03

[BUG]when map the dataset, i set the num_proc = 2 or 4, it will make mistakes.

8

Running tokenizer on dataset (num_proc=2): 0%| | 0/666 [00:00

nicosouth

Full parameter fine-tuning cannot be trained

1

(lmflow_train) root@duxact:/data/projects/lmflow/LMFlow# ./scripts/run_finetune.sh \ --model_name_or_path /data/guihunmodel8.8B \ --dataset_path /data/projects/lmflow/case_report_data \ --output_model_path /data/projects/lmflow/guihun_fintune_model [2024-05-22 15:23:02,959] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect) [2024-05-22 15:23:05,346] [WARNING] [runner.py:196:fetch_hostfile] Unable to find hostfile,...

orderer0001

Training was successful on a single card 4090GPU, but an error was reported on a 3*4090GPU. why

1

(lmflow_train) root@duxact:/data/projects/lmflow/LMFlow# ./scripts/run_finetune_with_lisa.sh \ --model_name_or_path /data/guihunmodel8.8B \ --dataset_path /data/projects/lmflow/case_report_data \ --output_model_path /data/projects/lmflow/guihun_fintune_model \ --lisa_activated_layers 1 \ --lisa_interval_steps 20 [2024-05-22 14:32:20,602] [INFO] [real_accelerator.py:133:get_accelerator] Setting ds_accelerator to cuda (auto detect) /root/anaconda3/envs/lmflow_train/lib/python3.9/site-packages/transformers/deepspeed.py:23: FutureWarning:...

orderer0001

Weird Loss Curve

1

I trained the llama3 on my own conversation dataset with the command : ./scripts/run_finetune.sh \ --model_name_or_path meta-llama/Meta-Llama-3-8B \ --dataset_path data/alpaca_selected/train \ --conversation_template llama3 \ --output_model_path output_models/finetuned_llama3_8b_selected The initial learning rate...

Zihang-Xu-2002

Hello, let me one question. If using LMFlow for supervised fune-tuning, how do I implement penalizing the distance between starting and current weights? This was shown to be effective in...

sedol1339