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: 0.5705
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 |
|---|---|---|---|
| 2.4224 | 1.0 | 5 | 2.0833 |
| 1.8303 | 2.0 | 10 | 1.6150 |
| 1.4466 | 3.0 | 15 | 1.3017 |
| 1.1519 | 4.0 | 20 | 1.0420 |
| 0.8828 | 5.0 | 25 | 0.8062 |
| 0.685 | 6.0 | 30 | 0.6994 |
| 0.5976 | 7.0 | 35 | 0.6398 |
| 0.5449 | 8.0 | 40 | 0.5994 |
| 0.509 | 9.0 | 45 | 0.5782 |
| 0.4907 | 10.0 | 50 | 0.5705 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.1.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for Gssmc/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ