Hugging Face's logo

yyx123
/
Yi-6B-ruozhiba

PEFT
Safetensors
llama
alignment-handbook
Generated from Trainer
trl
sft
4-bit precision
bitsandbytes
Model card Files Community
Yi-6B-ruozhiba / README.md
yyx123's picture
yyx123
End of training
d64924e verified
preview code
|
raw
history blame
1.6 kB
metadata
license: other
library_name: peft
tags:
  - alignment-handbook
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - ruozhiba
base_model: 01-ai/Yi-6B
model-index:
  - name: Yi-6B-ruozhiba
    results: []

Yi-6B-ruozhiba

This model is a fine-tuned version of 01-ai/Yi-6B on the ruozhiba dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9288

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: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss
2.2958 1.0 55 1.9636
1.8837 2.0 110 1.9193
1.7174 3.0 165 1.9123
1.6515 4.0 220 1.9246
1.6337 5.0 275 1.9288

Framework versions

  • PEFT 0.7.1
  • Transformers 4.36.2
  • Pytorch 2.2.2+cu118
  • Datasets 2.14.6
  • Tokenizers 0.15.2