|
--- |
|
license: mit |
|
base_model: TheBloke/zephyr-7B-alpha-GPTQ |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: zephy_finetuned_nvidiaQA75k_chatbot |
|
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. --> |
|
|
|
# zephy_finetuned_nvidiaQA75k_chatbot |
|
|
|
This model is a fine-tuned version of [TheBloke/zephyr-7B-alpha-GPTQ](https://huggingface.co/TheBloke/zephyr-7B-alpha-GPTQ) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5038 |
|
|
|
## 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: 0.0002 |
|
- train_batch_size: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- training_steps: 7000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.6115 | 0.13 | 1000 | 1.6073 | |
|
| 1.5629 | 0.27 | 2000 | 1.5688 | |
|
| 1.5342 | 0.4 | 3000 | 1.5423 | |
|
| 1.5325 | 0.54 | 4000 | 1.5246 | |
|
| 1.5011 | 0.67 | 5000 | 1.5118 | |
|
| 1.511 | 0.81 | 6000 | 1.5053 | |
|
| 1.5 | 0.94 | 7000 | 1.5038 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.36.0.dev0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
