kaggle-ICU-Readmission-classification-ClinicalT5-T4.3-2025
This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.2602
- F1: 59.5471
- Gen Len: 2.4956
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Gen Len |
|---|
| 0.3653 | 1.0 | 3281 | 0.2636 | 63.0732 | 2.5515 |
| 0.2588 | 2.0 | 6562 | 0.2598 | 64.0693 | 2.3984 |
| 0.2409 | 3.0 | 9843 | 0.2693 | 62.8036 | 2.3438 |
| 0.2146 | 4.0 | 13124 | 0.2981 | 62.7141 | 2.5492 |
| 0.1784 | 5.0 | 16405 | 0.3648 | 62.0885 | 2.4511 |
| 0.1423 | 6.0 | 19686 | 0.5066 | 60.9978 | 2.4956 |
| 0.1109 | 7.0 | 22967 | 0.6761 | 60.6441 | 2.4432 |
| 0.0904 | 8.0 | 26248 | 0.8635 | 60.2367 | 2.4630 |
| 0.0731 | 9.0 | 29529 | 1.1035 | 59.3468 | 2.5084 |
| 0.0542 | 10.0 | 32810 | 1.2602 | 59.5471 | 2.4956 |
Framework versions
- Transformers 4.28.1
- Pytorch 2.5.1+cu124
- Datasets 3.5.0
- Tokenizers 0.13.3
