t5-base-finetuned-anaphora_czech
This model is a fine-tuned version of t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1172
- Exact Match: 16.231
- Gen Len: 15.2479
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match | Gen Len |
|---|---|---|---|---|---|
| 0.1033 | 1.0 | 2105 | 0.1164 | 15.7082 | 15.3201 |
| 0.098 | 2.0 | 4210 | 0.1183 | 16.326 | 15.0791 |
| 0.1067 | 3.0 | 6315 | 0.1172 | 16.231 | 15.2479 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1