|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: mistralai/Mistral-7B-v0.1 |
|
model-index: |
|
- name: mistral-7b-brian-clough-ft |
|
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-7b-brian-clough-ft |
|
|
|
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0344 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.8109 | 12.5 | 25 | 0.0686 | |
|
| 0.0523 | 25.0 | 50 | 0.0304 | |
|
| 0.0357 | 37.5 | 75 | 0.0344 | |
|
| 0.0366 | 50.0 | 100 | 0.0390 | |
|
| 0.035 | 62.5 | 125 | 0.0330 | |
|
| 0.0346 | 75.0 | 150 | 0.0347 | |
|
| 0.0346 | 87.5 | 175 | 0.0356 | |
|
| 0.0338 | 100.0 | 200 | 0.0355 | |
|
| 0.0341 | 112.5 | 225 | 0.0363 | |
|
| 0.0325 | 125.0 | 250 | 0.0376 | |
|
| 0.0333 | 137.5 | 275 | 0.0341 | |
|
| 0.0332 | 150.0 | 300 | 0.0348 | |
|
| 0.0332 | 162.5 | 325 | 0.0346 | |
|
| 0.0334 | 175.0 | 350 | 0.0345 | |
|
| 0.0333 | 187.5 | 375 | 0.0325 | |
|
| 0.033 | 200.0 | 400 | 0.0347 | |
|
| 0.0328 | 212.5 | 425 | 0.0338 | |
|
| 0.0331 | 225.0 | 450 | 0.0343 | |
|
| 0.0339 | 237.5 | 475 | 0.0343 | |
|
| 0.0324 | 250.0 | 500 | 0.0344 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.7.2.dev0 |
|
- Transformers 4.37.0.dev0 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.0 |
