---
license: other
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: 01-ai/Yi-6B
model-index:
- name: Yi-6B-ruozhiba
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# Yi-6B-ruozhiba

This model is a fine-tuned version of [01-ai/Yi-6B](https://huggingface.co/01-ai/Yi-6B) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 4.1664

## 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: 20

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 2.333         | 1.0   | 55   | 2.0215          |
| 1.8575        | 2.0   | 110  | 1.8371          |
| 1.6435        | 3.0   | 165  | 1.8182          |
| 1.4138        | 4.0   | 220  | 1.9196          |
| 1.0749        | 5.0   | 275  | 2.2265          |
| 0.6715        | 6.0   | 330  | 2.5187          |
| 0.4252        | 7.0   | 385  | 2.8304          |
| 0.2572        | 8.0   | 440  | 3.1702          |
| 0.1543        | 9.0   | 495  | 3.3739          |
| 0.1095        | 10.0  | 550  | 3.4964          |
| 0.0875        | 11.0  | 605  | 3.6468          |
| 0.0692        | 12.0  | 660  | 3.8002          |
| 0.0573        | 13.0  | 715  | 3.9182          |
| 0.0527        | 14.0  | 770  | 4.0117          |
| 0.0494        | 15.0  | 825  | 4.0920          |
| 0.0459        | 16.0  | 880  | 4.1272          |
| 0.0456        | 17.0  | 935  | 4.1514          |
| 0.0435        | 18.0  | 990  | 4.1618          |
| 0.0446        | 19.0  | 1045 | 4.1660          |
| 0.0428        | 20.0  | 1100 | 4.1664          |


### Framework versions

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