Mists-7B-v01-single-turn
This model is a fine-tuned version of HachiML/Mists-7B-v01-projector-trained on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4305
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.7872 | 0.0420 | 400 | 1.0558 |
0.7703 | 0.0841 | 800 | 0.8494 |
0.6751 | 0.1261 | 1200 | 0.7353 |
0.6225 | 0.1682 | 1600 | 0.6600 |
0.5783 | 0.2102 | 2000 | 0.6104 |
0.5582 | 0.2523 | 2400 | 0.5712 |
0.5334 | 0.2943 | 2800 | 0.5482 |
0.5182 | 0.3363 | 3200 | 0.5290 |
0.4979 | 0.3784 | 3600 | 0.5098 |
0.4848 | 0.4204 | 4000 | 0.4933 |
0.4745 | 0.4625 | 4400 | 0.4821 |
0.4637 | 0.5045 | 4800 | 0.4730 |
0.4601 | 0.5466 | 5200 | 0.4633 |
0.4552 | 0.5886 | 5600 | 0.4562 |
0.4486 | 0.6306 | 6000 | 0.4503 |
0.441 | 0.6727 | 6400 | 0.4449 |
0.4425 | 0.7147 | 6800 | 0.4398 |
0.4306 | 0.7568 | 7200 | 0.4372 |
0.4246 | 0.7988 | 7600 | 0.4344 |
0.4232 | 0.8409 | 8000 | 0.4325 |
0.4279 | 0.8829 | 8400 | 0.4315 |
0.4274 | 0.9250 | 8800 | 0.4307 |
0.4224 | 0.9670 | 9200 | 0.4305 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.0.1
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 0