T5-finetuned
This model is a fine-tuned version of google-t5/t5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.7703
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: 2e-05
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 12
- 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
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3233 | 1.0 | 834 | 1.8919 |
| 2.0564 | 2.0 | 1668 | 1.8428 |
| 1.985 | 3.0 | 2502 | 1.8123 |
| 1.9679 | 4.0 | 3336 | 1.7954 |
| 1.9379 | 5.0 | 4170 | 1.7824 |
| 1.9227 | 6.0 | 5004 | 1.7742 |
| 1.918 | 7.0 | 5838 | 1.7723 |
| 1.9017 | 8.0 | 6672 | 1.7703 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 3.6.0
- Tokenizers 0.22.1
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for DougVo/T5-finetuned
Base model
google-t5/t5-small