metadata
license: apache-2.0
base_model: mistralai/Mistral-7B-v0.1
tags:
- generated_from_trainer
model-index:
- name: out
results: []
out
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9838
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: 2e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.822 | 0.01 | 1 | 2.7914 |
| 2.4718 | 0.15 | 17 | 2.4825 |
| 2.4643 | 0.31 | 34 | 2.4859 |
| 2.4417 | 0.46 | 51 | 2.4764 |
| 2.4343 | 0.62 | 68 | 2.4696 |
| 2.4312 | 0.77 | 85 | 2.4645 |
| 2.385 | 0.92 | 102 | 2.4511 |
| 1.5771 | 1.05 | 119 | 2.5741 |
| 1.4889 | 1.21 | 136 | 2.5933 |
| 1.4574 | 1.36 | 153 | 2.6168 |
| 1.493 | 1.52 | 170 | 2.6088 |
| 1.4544 | 1.67 | 187 | 2.6049 |
| 1.4422 | 1.82 | 204 | 2.5967 |
| 1.3711 | 1.98 | 221 | 2.6013 |
| 0.7967 | 2.11 | 238 | 3.1609 |
| 0.7342 | 2.26 | 255 | 3.0085 |
| 0.7731 | 2.42 | 272 | 2.9758 |
| 0.7546 | 2.57 | 289 | 2.9832 |
| 0.7936 | 2.72 | 306 | 2.9837 |
| 0.7374 | 2.88 | 323 | 2.9838 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1