shawgpt-ft
This model is a fine-tuned version of TheBloke/Mistral-7B-Instruct-v0.2-GPTQ on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9102
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: 24
- eval_batch_size: 24
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 96
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 20
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.5215 | 1.0 | 1 | 3.3144 |
1.1816 | 2.0 | 3 | 3.0479 |
1.0977 | 3.0 | 5 | 2.7926 |
2.0195 | 4.0 | 6 | 2.6715 |
2.0273 | 5.0 | 7 | 2.5671 |
0.8926 | 6.0 | 9 | 2.3771 |
0.8271 | 7.0 | 11 | 2.2092 |
1.5869 | 8.0 | 12 | 2.1461 |
1.5469 | 9.0 | 13 | 2.0923 |
0.709 | 10.0 | 15 | 2.0085 |
0.75 | 11.0 | 17 | 1.9511 |
1.3555 | 12.0 | 18 | 1.9306 |
1.3994 | 13.0 | 19 | 1.9170 |
0.4607 | 13.3333 | 20 | 1.9102 |
Framework versions
- PEFT 0.13.0
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Downloads last month
- 6
Model tree for MathiasBrussow/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ