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: 1.3731
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 |
|---|---|---|---|
| 0.9422 | 0.02 | 1 | 1.0091 |
| 1.0215 | 0.2 | 13 | 1.0004 |
| 0.9933 | 0.41 | 26 | 1.0071 |
| 0.9197 | 0.61 | 39 | 1.0136 |
| 0.9285 | 0.81 | 52 | 1.0075 |
| 0.5858 | 1.02 | 65 | 1.0082 |
| 0.5522 | 1.22 | 78 | 1.0546 |
| 0.4992 | 1.42 | 91 | 1.0683 |
| 0.6085 | 1.62 | 104 | 1.0638 |
| 0.5118 | 1.83 | 117 | 1.0654 |
| 0.3243 | 2.03 | 130 | 1.1113 |
| 0.3196 | 2.23 | 143 | 1.1957 |
| 0.2582 | 2.44 | 156 | 1.2038 |
| 0.273 | 2.64 | 169 | 1.1949 |
| 0.2818 | 2.84 | 182 | 1.2000 |
| 0.1427 | 3.05 | 195 | 1.2817 |
| 0.1246 | 3.25 | 208 | 1.3245 |
| 0.1394 | 3.45 | 221 | 1.3561 |
| 0.1088 | 3.66 | 234 | 1.3770 |
| 0.0985 | 3.86 | 247 | 1.3731 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.14.0