results
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: 1.5440
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: 0.00021062244157922272
- 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: 11.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.5904 | 0.9231 | 3 | 3.9595 |
| 4.0281 | 1.8462 | 6 | 3.4214 |
| 3.4235 | 2.7692 | 9 | 2.9421 |
| 2.2012 | 4.0 | 13 | 2.4836 |
| 2.5714 | 4.9231 | 16 | 2.2112 |
| 2.2112 | 5.8462 | 19 | 1.9773 |
| 1.9154 | 6.7692 | 22 | 1.7870 |
| 1.3261 | 8.0 | 26 | 1.6553 |
| 1.658 | 8.9231 | 29 | 1.5874 |
| 1.5641 | 9.8462 | 32 | 1.5487 |
| 0.6679 | 10.1538 | 33 | 1.5440 |
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
- -
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for oliverhoffmann/results
Base model
mistralai/Mistral-7B-Instruct-v0.2
Quantized
TheBloke/Mistral-7B-Instruct-v0.2-GPTQ