|
--- |
|
license: mit |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: TheBloke/zephyr-7B-beta-GPTQ |
|
model-index: |
|
- name: zephyr_10k |
|
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. --> |
|
|
|
# zephyr_10k |
|
|
|
This model is a fine-tuned version of [TheBloke/zephyr-7B-beta-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-beta-GPTQ) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1827 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- 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: 1 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.4074 | 0.16 | 100 | 1.1947 | |
|
| 0.7674 | 0.32 | 200 | 0.4081 | |
|
| 0.3036 | 0.48 | 300 | 0.2392 | |
|
| 0.2253 | 0.64 | 400 | 0.1989 | |
|
| 0.2016 | 0.8 | 500 | 0.1855 | |
|
| 0.1963 | 0.96 | 600 | 0.1827 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.0.0 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
