|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- trl |
|
- sft |
|
- generated_from_trainer |
|
base_model: Felladrin/TinyMistral-248M-SFT-v4 |
|
datasets: |
|
- generator |
|
model-index: |
|
- name: mistral_instruct_generation |
|
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_instruct_generation |
|
|
|
This model is a fine-tuned version of [Felladrin/TinyMistral-248M-SFT-v4](https://huggingface.co/Felladrin/TinyMistral-248M-SFT-v4) on the generator dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0138 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant |
|
- lr_scheduler_warmup_steps: 0.03 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 2.5295 | 1.0 | 123 | 2.1771 | |
|
| 2.4314 | 2.0 | 246 | 2.0629 | |
|
| 2.403 | 3.0 | 369 | 2.0354 | |
|
| 2.3605 | 4.0 | 492 | 2.0222 | |
|
| 2.3647 | 5.0 | 615 | 2.0138 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.1 |
|
- Transformers 4.36.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
