|
--- |
|
license: other |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: IlyaGusev/saiga_llama3_8b |
|
model-index: |
|
- name: qdora |
|
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. --> |
|
|
|
# qdora |
|
|
|
This model is a fine-tuned version of [IlyaGusev/saiga_llama3_8b](https://huggingface.co/IlyaGusev/saiga_llama3_8b) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5287 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:----:|:---------------:| |
|
| 1.794 | 0.1389 | 25 | 1.6986 | |
|
| 1.6478 | 0.2778 | 50 | 1.6411 | |
|
| 1.5549 | 0.4167 | 75 | 1.5937 | |
|
| 1.4962 | 0.5556 | 100 | 1.5652 | |
|
| 1.4841 | 0.6944 | 125 | 1.5430 | |
|
| 1.563 | 0.8333 | 150 | 1.5320 | |
|
| 1.51 | 0.9722 | 175 | 1.5287 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1 |
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.0+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |