|
|
--- |
|
|
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: 0.6570 |
|
|
|
|
|
## 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: 8 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:-----:|:----:|:---------------:| |
|
|
| 1.0381 | 0.17 | 50 | 1.1373 | |
|
|
| 0.7645 | 0.35 | 100 | 1.0030 | |
|
|
| 0.7008 | 0.52 | 150 | 0.8769 | |
|
|
| 0.6463 | 0.69 | 200 | 0.8396 | |
|
|
| 0.6139 | 0.87 | 250 | 0.7906 | |
|
|
| 0.6415 | 1.04 | 300 | 0.7021 | |
|
|
| 0.5952 | 1.22 | 350 | 0.6840 | |
|
|
| 0.5802 | 1.39 | 400 | 0.7160 | |
|
|
| 0.6116 | 1.56 | 450 | 0.6585 | |
|
|
| 0.5921 | 1.74 | 500 | 0.6428 | |
|
|
| 0.5532 | 1.91 | 550 | 0.6181 | |
|
|
| 0.4655 | 2.08 | 600 | 0.6465 | |
|
|
| 0.4249 | 2.26 | 650 | 0.6487 | |
|
|
| 0.4441 | 2.43 | 700 | 0.6431 | |
|
|
| 0.4652 | 2.6 | 750 | 0.6256 | |
|
|
| 0.4325 | 2.78 | 800 | 0.6412 | |
|
|
| 0.4728 | 2.95 | 850 | 0.6173 | |
|
|
| 0.3161 | 3.12 | 900 | 0.6945 | |
|
|
| 0.3375 | 3.3 | 950 | 0.6501 | |
|
|
| 0.3509 | 3.47 | 1000 | 0.6561 | |
|
|
| 0.3519 | 3.65 | 1050 | 0.6765 | |
|
|
| 0.3379 | 3.82 | 1100 | 0.6570 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.35.2 |
|
|
- Pytorch 2.1.0+cu121 |
|
|
- Datasets 2.16.1 |
|
|
- Tokenizers 0.15.0 |
|
|
|
