biorecall-flan-t5-small-reasoning
This model is a fine-tuned version of google/flan-t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3262
- Bertscore F1: 0.5967
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 | 2.3386 | 0.5943 |
| No log | 2.0 | 438 | 2.3287 | 0.5959 |
| 2.4809 | 3.0 | 657 | 2.3181 | 0.5977 |
| 2.4809 | 4.0 | 876 | 2.3200 | 0.5991 |
| 2.2488 | 5.0 | 1095 | 2.3262 | 0.5967 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1