metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: synthea_t5_summarization_model
results: []
synthea_t5_summarization_model
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9861
- Rouge1: 0.2074
- Rouge2: 0.0273
- Rougel: 0.2024
- Rougelsum: 0.2028
- Gen Len: 12.3023
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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 22 | 3.8819 | 0.0 | 0.0 | 0.0 | 0.0 | 19.0 |
| No log | 2.0 | 44 | 3.2929 | 0.0162 | 0.004 | 0.0152 | 0.0151 | 18.907 |
| No log | 3.0 | 66 | 3.0590 | 0.1333 | 0.0162 | 0.1317 | 0.1322 | 14.9651 |
| No log | 4.0 | 88 | 2.9861 | 0.2074 | 0.0273 | 0.2024 | 0.2028 | 12.3023 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2