MonteXiaofeng's picture
Update README.md
307c902 verified
|
raw
history blame
998 Bytes
metadata
license: apache-2.0
language:
  - en
  - zh
base_model:
  - meta-llama/Meta-Llama-3.1-8B-Instruct
datasets:
  - BAAI/IndustryInstruction_Finance-Economics
  - BAAI/IndustryInstruction

This model is finetuned on the model llama3.1-8b-instruct using the dataset BAAI/IndustryInstruction_Finance-Economics dataset, the dataset details can jump to the repo: BAAI/IndustryInstruction

training params

learning_rate=1e-5
lr_scheduler_type=cosine
max_length=2048
warmup_ratio=0.05
batch_size=64
epoch=10

select best ckpt by the evaluation loss

evaluation

The following is an evaluation on the FinerBen dataset metrci. Since there are too many samples in the dataset, I randomly selected 500 samples from each dataset for evaluation.

image/png