Configuration Parsing Warning:In adapter_config.json: "peft.base_model_name_or_path" must be a string
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: 1.3107
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: 0.0005
- 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: 19
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.5248 | 0.9231 | 3 | 3.6325 |
| 3.4333 | 1.8462 | 6 | 2.6427 |
| 2.5371 | 2.7692 | 9 | 2.1463 |
| 1.5835 | 4.0 | 13 | 1.8295 |
| 1.8678 | 4.9231 | 16 | 1.6911 |
| 1.6588 | 5.8462 | 19 | 1.5402 |
| 1.451 | 6.7692 | 22 | 1.4409 |
| 1.068 | 8.0 | 26 | 1.4267 |
| 1.4077 | 8.9231 | 29 | 1.3988 |
| 1.344 | 9.8462 | 32 | 1.3837 |
| 1.3474 | 10.7692 | 35 | 1.3684 |
| 0.9643 | 12.0 | 39 | 1.3498 |
| 1.2937 | 12.9231 | 42 | 1.3398 |
| 1.245 | 13.8462 | 45 | 1.3290 |
| 1.2369 | 14.7692 | 48 | 1.3259 |
| 0.919 | 16.0 | 52 | 1.3188 |
| 1.1832 | 16.9231 | 55 | 1.3132 |
| 0.8962 | 17.5385 | 57 | 1.3107 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.2
- Pytorch 2.1.0+cu121
- Datasets 3.0.1
- Tokenizers 0.20.1
- Downloads last month
- 10
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for mariatveen/shawgpt-ft
Base model
mistralai/Mistral-7B-Instruct-v0.2 Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ