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: 6.8300
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- total_eval_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 |
|---|---|---|---|
| 1.2465 | 0.16 | 20 | 1.1498 |
| 8.597 | 0.32 | 40 | 8.5500 |
| 8.0391 | 0.48 | 60 | 7.6701 |
| 7.2703 | 0.65 | 80 | 7.4684 |
| 8.1368 | 0.81 | 100 | 7.7743 |
| 7.3305 | 0.97 | 120 | 7.3737 |
| 7.0599 | 1.13 | 140 | 7.2302 |
| 6.9011 | 1.29 | 160 | 7.1971 |
| 7.2194 | 1.45 | 180 | 7.0846 |
| 7.2281 | 1.61 | 200 | 7.0792 |
| 7.3379 | 1.77 | 220 | 7.0411 |
| 7.1461 | 1.94 | 240 | 7.0113 |
| 7.113 | 2.1 | 260 | 6.9626 |
| 6.7317 | 2.26 | 280 | 7.0031 |
| 6.8143 | 2.42 | 300 | 6.9219 |
| 6.9195 | 2.58 | 320 | 6.8336 |
| 6.3028 | 2.74 | 340 | 6.8596 |
| 6.8106 | 2.9 | 360 | 6.8300 |
Framework versions
- Transformers 4.34.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.14.0