lc_v7_select_half_lr
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: 1.3481
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: 1e-05
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4629 | 1.0 | 297 | 1.3980 |
| 1.3131 | 2.0 | 594 | 1.3670 |
| 1.3327 | 3.0 | 891 | 1.3556 |
| 1.3166 | 4.0 | 1188 | 1.3508 |
| 1.2953 | 5.0 | 1485 | 1.3491 |
| 1.3096 | 6.0 | 1782 | 1.3484 |
| 1.4526 | 7.0 | 2079 | 1.3482 |
| 1.4208 | 8.0 | 2376 | 1.3483 |
| 1.3046 | 9.0 | 2673 | 1.3484 |
| 1.3497 | 10.0 | 2970 | 1.3481 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu118
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for nerottt/lc_v7_select_half_lr
Base model
mistralai/Mistral-7B-v0.1