t5-small-finetuned-pubmedqa-longanswer-persona
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.4263
- Bertscore F1: 0.6058
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: 0.0003
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use 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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Bertscore F1 |
|---|---|---|---|---|
| No log | 1.0 | 219 | 2.4691 | 0.5946 |
| No log | 2.0 | 438 | 2.4390 | 0.6038 |
| 2.6114 | 3.0 | 657 | 2.4219 | 0.6049 |
| 2.6114 | 4.0 | 876 | 2.4232 | 0.6044 |
| 2.3885 | 5.0 | 1095 | 2.4263 | 0.6058 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1