DorskGPT
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: 1.0333
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: 30
- eval_batch_size: 30
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 120
- 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 |
|---|---|---|---|
| 1.2314 | 1.0 | 528 | 1.1214 |
| 1.0924 | 2.0 | 1056 | 1.0800 |
| 1.0569 | 3.0 | 1584 | 1.0614 |
| 1.0364 | 4.0 | 2112 | 1.0510 |
| 1.0221 | 5.0 | 2640 | 1.0442 |
| 1.0113 | 6.0 | 3168 | 1.0399 |
| 1.0031 | 7.0 | 3696 | 1.0371 |
| 0.9962 | 8.0 | 4224 | 1.0352 |
| 0.9909 | 9.0 | 4752 | 1.0337 |
| 0.9867 | 10.0 | 5280 | 1.0333 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 1
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for mikeriess/DorskGPT
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ