deberta-tweetqa-5ep
This model is a fine-tuned version of microsoft/deberta-v3-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.7168
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: 3e-05
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.7783 | 1.0 | 1 | 3.8975 |
| 2.8494 | 2.0 | 2 | 3.8975 |
| 2.8872 | 3.0 | 3 | 3.8877 |
| 2.854 | 4.0 | 4 | 3.8198 |
| 2.6379 | 5.0 | 5 | 3.7168 |
Framework versions
- Transformers 4.52.2
- Pytorch 2.6.0+cu124
- Datasets 2.14.4
- Tokenizers 0.21.1