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: 1.9186
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 2
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
2.0455 | 0.9231 | 3 | 1.9867 |
1.9444 | 1.8462 | 6 | 1.9560 |
1.8382 | 2.7692 | 9 | 1.9454 |
1.324 | 4.0 | 13 | 1.9323 |
1.6615 | 4.9231 | 16 | 1.9238 |
1.6217 | 5.8462 | 19 | 1.9199 |
1.5301 | 6.7692 | 22 | 1.9186 |
1.1204 | 8.0 | 26 | 1.9189 |
1.4765 | 8.9231 | 29 | 1.9188 |
0.94 | 9.2308 | 30 | 1.9186 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.1.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for Dantewada/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
Adapter
this model