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: 1.3578
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: 6e-06
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 16
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0098 | 0.02 | 1 | 1.1120 |
| 1.0619 | 0.2 | 13 | 1.0209 |
| 0.9973 | 0.41 | 26 | 1.0142 |
| 0.9229 | 0.61 | 39 | 1.0068 |
| 0.9302 | 0.81 | 52 | 1.0037 |
| 0.6189 | 1.02 | 65 | 1.0103 |
| 0.5912 | 1.22 | 78 | 1.0485 |
| 0.5477 | 1.42 | 91 | 1.0665 |
| 0.6536 | 1.62 | 104 | 1.0594 |
| 0.5538 | 1.83 | 117 | 1.0684 |
| 0.3619 | 2.03 | 130 | 1.1095 |
| 0.3412 | 2.23 | 143 | 1.1854 |
| 0.2986 | 2.44 | 156 | 1.1898 |
| 0.3164 | 2.64 | 169 | 1.1895 |
| 0.326 | 2.84 | 182 | 1.1849 |
| 0.1795 | 3.05 | 195 | 1.2659 |
| 0.1595 | 3.25 | 208 | 1.3222 |
| 0.1765 | 3.45 | 221 | 1.3298 |
| 0.1417 | 3.66 | 234 | 1.3659 |
| 0.1282 | 3.86 | 247 | 1.3578 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.14.0