|
--- |
|
license: mit |
|
base_model: HuggingFaceH4/zephyr-7b-beta |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: sft-zephyr-7b-beta-v1 |
|
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. --> |
|
|
|
# sft-zephyr-7b-beta-v1 |
|
|
|
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: 0.4927 |
|
|
|
## 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: 3e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.05 |
|
- training_steps: 1000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.0538 | 0.19 | 50 | 1.1364 | |
|
| 0.7744 | 0.37 | 100 | 0.7777 | |
|
| 0.5936 | 0.56 | 150 | 0.6507 | |
|
| 0.5449 | 0.74 | 200 | 0.6087 | |
|
| 0.501 | 0.93 | 250 | 0.5840 | |
|
| 0.5752 | 1.12 | 300 | 0.5552 | |
|
| 0.4542 | 1.3 | 350 | 0.5419 | |
|
| 0.5115 | 1.49 | 400 | 0.5243 | |
|
| 0.4224 | 1.67 | 450 | 0.5188 | |
|
| 0.4486 | 1.86 | 500 | 0.5055 | |
|
| 0.3865 | 2.04 | 550 | 0.5038 | |
|
| 0.4193 | 2.23 | 600 | 0.5048 | |
|
| 0.4294 | 2.42 | 650 | 0.4995 | |
|
| 0.4077 | 2.6 | 700 | 0.5014 | |
|
| 0.4667 | 2.79 | 750 | 0.4985 | |
|
| 0.4226 | 2.97 | 800 | 0.4937 | |
|
| 0.4195 | 3.16 | 850 | 0.4920 | |
|
| 0.338 | 3.35 | 900 | 0.4923 | |
|
| 0.3943 | 3.53 | 950 | 0.4926 | |
|
| 0.3953 | 3.72 | 1000 | 0.4927 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
