|
--- |
|
license: other |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: 01-ai/Yi-6B-Chat |
|
model-index: |
|
- name: Mental-Yi-6B |
|
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. --> |
|
|
|
# Mental-Yi-6B |
|
|
|
This model is a fine-tuned version of [01-ai/Yi-6B-Chat](https://huggingface.co/01-ai/Yi-6B-Chat) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.1702 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.3241 | 1.0 | 1000 | 2.1771 | |
|
| 2.1687 | 1.99 | 2000 | 2.1709 | |
|
| 2.1664 | 2.99 | 3000 | 2.1702 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.8.2 |
|
- Transformers 4.38.1 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.1 |
