QSolver_Encoder
This model is a fine-tuned version of microsoft/deberta-v2-xxlarge on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0060
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 12.3802 | 0.8889 | 200 | 1.3449 |
| 5.3176 | 1.7778 | 400 | 0.3203 |
| 1.9803 | 2.6667 | 600 | 0.0597 |
| 1.4256 | 3.5556 | 800 | 0.0158 |
| 1.0413 | 4.4444 | 1000 | 0.0069 |
| 0.6325 | 5.0 | 1125 | 0.0060 |
Framework versions
- PEFT 0.19.1
- Transformers 5.9.0
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2
- Downloads last month
- 254
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for dahaludba/QSolver_Encoder
Base model
microsoft/deberta-v2-xxlarge