dkt-t5-base-400students-aug3x
This model is a fine-tuned version of google-t5/t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4505
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 500
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0007 | 0.3743 | 500 | 0.8384 |
| 0.7874 | 0.7485 | 1000 | 0.6599 |
| 0.6773 | 1.1228 | 1500 | 0.5739 |
| 0.6226 | 1.4970 | 2000 | 0.5158 |
| 0.6037 | 1.8713 | 2500 | 0.4747 |
| 0.5697 | 2.2455 | 3000 | 0.4505 |
| 0.5548 | 2.6198 | 3500 | 0.4462 |
| 0.5628 | 2.9940 | 4000 | 0.4528 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.1+cu128
- Datasets 4.4.2
- Tokenizers 0.22.2