|
--- |
|
license: mit |
|
base_model: HuggingFaceH4/zephyr-7b-beta |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
model-index: |
|
- name: results |
|
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. --> |
|
|
|
# results |
|
|
|
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.5273 |
|
|
|
## 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: 0.00025 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- lr_scheduler_warmup_ratio: 0.03 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.1126 | 0.38 | 50 | 0.9045 | |
|
| 0.781 | 0.76 | 100 | 0.7953 | |
|
| 0.6092 | 1.14 | 150 | 0.6737 | |
|
| 0.5484 | 1.52 | 200 | 0.6842 | |
|
| 0.5078 | 1.89 | 250 | 0.5686 | |
|
| 0.3905 | 2.27 | 300 | 0.6194 | |
|
| 0.4328 | 2.65 | 350 | 0.5543 | |
|
| 0.3872 | 3.03 | 400 | 0.5406 | |
|
| 0.3147 | 3.41 | 450 | 0.5504 | |
|
| 0.3327 | 3.79 | 500 | 0.5473 | |
|
| 0.2734 | 4.17 | 550 | 0.5514 | |
|
| 0.2972 | 4.55 | 600 | 0.5327 | |
|
| 0.2974 | 4.92 | 650 | 0.5273 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
|
|
