Hugging Face's logo

CMLM
/
ZhongJing-2-1_8b

PEFT
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Community
ZhongJing-2-1_8b / README.md
CMLL's picture
CMLL
Upload 13 files
9918ad6 verified
preview code
|
raw
history blame
1.3 kB
metadata
license: other
library_name: peft
tags:
  - llama-factory
  - lora
  - generated_from_trainer
base_model: Qwen/Qwen1.5-1.8B-Chat
model-index:
  - name: train_2024
    results: []

train_2024

This model is a fine-tuned version of /root/.cache/modelscope/hub/qwen/Qwen1___5-1___8B-Chat/ on the self_cognition and the FX datasets.

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 2e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 3.0
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • PEFT 0.8.2
  • Transformers 4.37.2
  • Pytorch 2.2.0+cu121
  • Datasets 2.17.0
  • Tokenizers 0.15.2