|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: Open-Orca/Mistral-7B-OpenOrca |
|
model-index: |
|
- name: mistral-sigoIAspirantes |
|
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-sigoIAspirantes |
|
|
|
This model is a fine-tuned version of [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1297 |
|
|
|
## 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: 2.5e-05 |
|
- train_batch_size: 2 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1 |
|
- training_steps: 500 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.2813 | 0.35 | 25 | 0.3234 | |
|
| 0.2254 | 0.7 | 50 | 0.2505 | |
|
| 0.2004 | 1.06 | 75 | 0.2275 | |
|
| 0.1896 | 1.41 | 100 | 0.2154 | |
|
| 0.1498 | 1.76 | 125 | 0.1824 | |
|
| 0.1481 | 2.11 | 150 | 0.1689 | |
|
| 0.0907 | 2.46 | 175 | 0.1623 | |
|
| 0.1363 | 2.82 | 200 | 0.1265 | |
|
| 0.0874 | 3.17 | 225 | 0.1557 | |
|
| 0.0816 | 3.52 | 250 | 0.1375 | |
|
| 0.0907 | 3.87 | 275 | 0.1193 | |
|
| 0.066 | 4.23 | 300 | 0.1427 | |
|
| 0.0758 | 4.58 | 325 | 0.1412 | |
|
| 0.0686 | 4.93 | 350 | 0.1305 | |
|
| 0.0673 | 5.28 | 375 | 0.1251 | |
|
| 0.0551 | 5.63 | 400 | 0.1283 | |
|
| 0.0641 | 5.99 | 425 | 0.1270 | |
|
| 0.0577 | 6.34 | 450 | 0.1310 | |
|
| 0.0518 | 6.69 | 475 | 0.1294 | |
|
| 0.0534 | 7.04 | 500 | 0.1297 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.9.1.dev0 |
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
