metadata
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: []
mistral-7b-brian-clough-ft
This model is a fine-tuned version of 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