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: 1.8863
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 |
|---|---|---|---|
| 4.5527 | 0.92 | 3 | 3.9210 |
| 4.0036 | 1.85 | 6 | 3.3876 |
| 3.4404 | 2.77 | 9 | 2.9613 |
| 2.2546 | 4.0 | 13 | 2.5594 |
| 2.6787 | 4.92 | 16 | 2.3233 |
| 2.3851 | 5.85 | 19 | 2.1505 |
| 2.1807 | 6.77 | 22 | 2.0285 |
| 1.5534 | 8.0 | 26 | 1.9624 |
| 2.0198 | 8.92 | 29 | 1.8983 |
| 1.384 | 9.23 | 30 | 1.8863 |
Framework versions
- PEFT 0.10.0
- Transformers 4.38.2
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 4
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
HF Inference API was unable to determine this model’s pipeline type.
Model tree for rumk78864/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ