|
|
--- |
|
|
license: apache-2.0 |
|
|
library_name: peft |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
base_model: mistralai/Mistral-7B-Instruct-v0.2 |
|
|
model-index: |
|
|
- name: mistral-magyar-portas-lora |
|
|
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. --> |
|
|
|
|
|
# mistral-magyar-portas-lora |
|
|
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on the None dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.0117 |
|
|
|
|
|
## 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: 2 |
|
|
- eval_batch_size: 2 |
|
|
- seed: 42 |
|
|
- gradient_accumulation_steps: 4 |
|
|
- total_train_batch_size: 8 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_steps: 100 |
|
|
- num_epochs: 3 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|
|:-------------:|:------:|:----:|:---------------:| |
|
|
| 0.0323 | 0.3918 | 500 | 0.0634 | |
|
|
| 0.0123 | 0.7837 | 1000 | 0.0131 | |
|
|
| 0.0094 | 1.1755 | 1500 | 0.0121 | |
|
|
| 0.0093 | 1.5674 | 2000 | 0.0120 | |
|
|
| 0.0088 | 1.9592 | 2500 | 0.0111 | |
|
|
| 0.0065 | 2.3511 | 3000 | 0.0119 | |
|
|
| 0.0064 | 2.7429 | 3500 | 0.0117 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- PEFT 0.7.1 |
|
|
- Transformers 4.40.2 |
|
|
- Pytorch 2.1.1+cu121 |
|
|
- Datasets 2.16.1 |
|
|
- Tokenizers 0.19.1 |
