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: 1.3191
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: 20
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.5905 | 0.9231 | 3 | 3.9593 |
| 4.025 | 1.8462 | 6 | 3.4099 |
| 3.4125 | 2.7692 | 9 | 2.9152 |
| 2.1722 | 4.0 | 13 | 2.4169 |
| 2.4691 | 4.9231 | 16 | 2.1005 |
| 2.0548 | 5.8462 | 19 | 1.8257 |
| 1.7281 | 6.7692 | 22 | 1.6290 |
| 1.1606 | 8.0 | 26 | 1.4558 |
| 1.4189 | 8.9231 | 29 | 1.4021 |
| 1.3437 | 9.8462 | 32 | 1.3720 |
| 1.3363 | 10.7692 | 35 | 1.3524 |
| 0.9514 | 12.0 | 39 | 1.3344 |
| 1.2724 | 12.9231 | 42 | 1.3275 |
| 1.2308 | 13.8462 | 45 | 1.3237 |
| 1.2342 | 14.7692 | 48 | 1.3222 |
| 0.9248 | 16.0 | 52 | 1.3202 |
| 1.2053 | 16.9231 | 55 | 1.3195 |
| 1.1905 | 17.8462 | 58 | 1.3191 |
Framework versions
- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1
- Downloads last month
- 11
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for timewanderer/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ