|
--- |
|
base_model: HuggingFaceH4/zephyr-7b-beta |
|
library_name: peft |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: experiments500czephymodel_v4 |
|
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. --> |
|
|
|
# experiments500czephymodel_v4 |
|
|
|
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: 0.2749 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 8 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.3561 | 1.0 | 50 | 0.3625 | |
|
| 0.2785 | 2.0 | 100 | 0.3014 | |
|
| 0.1976 | 3.0 | 150 | 0.2770 | |
|
| 0.1583 | 4.0 | 200 | 0.2718 | |
|
| 0.1064 | 5.0 | 250 | 0.2785 | |
|
| 0.0787 | 6.0 | 300 | 0.2934 | |
|
| 0.0523 | 7.0 | 350 | 0.3087 | |
|
| 0.0447 | 8.0 | 400 | 0.3199 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.36.0 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.15.2 |
