|
--- |
|
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: 1.0751 |
|
|
|
## 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: 2.5e-05 |
|
- 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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.2434 | 0.72 | 100 | 1.2548 | |
|
| 0.772 | 1.45 | 200 | 0.8910 | |
|
| 0.5866 | 2.17 | 300 | 0.8081 | |
|
| 0.5755 | 2.9 | 400 | 0.7824 | |
|
| 0.3935 | 3.62 | 500 | 0.8343 | |
|
| 0.2616 | 4.35 | 600 | 0.8752 | |
|
| 0.244 | 5.07 | 700 | 0.8777 | |
|
| 0.2414 | 5.8 | 800 | 0.9291 | |
|
| 0.19 | 6.52 | 900 | 1.0490 | |
|
| 0.1828 | 7.25 | 1000 | 1.0226 | |
|
| 0.1939 | 7.97 | 1100 | 1.0120 | |
|
| 0.1647 | 8.7 | 1200 | 1.0177 | |
|
| 0.1544 | 9.42 | 1300 | 1.0751 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
