|
--- |
|
license: mit |
|
library_name: peft |
|
tags: |
|
- alignment-handbook |
|
- generated_from_trainer |
|
- trl |
|
- sft |
|
base_model: HuggingFaceH4/zephyr-7b-beta |
|
datasets: |
|
- erbacher/rag-and-roll |
|
model-index: |
|
- name: zephyr-rag-agent |
|
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. --> |
|
|
|
# zephyr-rag-agent |
|
|
|
This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the erbacher/rag-and-roll dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1829 |
|
|
|
## 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: 4e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- gradient_accumulation_steps: 16 |
|
- total_train_batch_size: 128 |
|
- total_eval_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: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.1559 | 0.99 | 27 | 1.1650 | |
|
| 1.0887 | 1.98 | 54 | 1.1555 | |
|
| 1.0566 | 2.97 | 81 | 1.1623 | |
|
| 1.0264 | 6.95 | 91 | 1.1689 | |
|
| 0.9977 | 7.97 | 105 | 1.1779 | |
|
| 0.9808 | 9.0 | 119 | 1.1820 | |
|
| 0.9791 | 9.8 | 130 | 1.1829 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.2.2+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.15.2 |
