metadata
license: apache-2.0
base_model: t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: t5-small-MedicoSummarizer
results: []
t5-small-MedicoSummarizer
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.9737
- Rouge1: 0.3207
- Rouge2: 0.0752
- Rougel: 0.1949
- Rougelsum: 0.1947
- Gen Len: 122.586
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: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
---|---|---|---|---|---|---|---|---|
3.4289 | 1.0 | 625 | 3.0929 | 0.3181 | 0.0722 | 0.1893 | 0.1893 | 122.637 |
3.2654 | 2.0 | 1250 | 3.0531 | 0.3199 | 0.0733 | 0.1915 | 0.1916 | 122.072 |
3.2288 | 3.0 | 1875 | 3.0245 | 0.317 | 0.0725 | 0.1917 | 0.1917 | 122.153 |
3.178 | 4.0 | 2500 | 3.0097 | 0.3161 | 0.0724 | 0.1907 | 0.1907 | 122.398 |
3.16 | 5.0 | 3125 | 2.9940 | 0.3162 | 0.0722 | 0.192 | 0.1918 | 122.114 |
3.1517 | 6.0 | 3750 | 2.9869 | 0.3165 | 0.0728 | 0.1928 | 0.1926 | 122.652 |
3.1429 | 7.0 | 4375 | 2.9815 | 0.3189 | 0.0741 | 0.1935 | 0.1933 | 122.481 |
3.1226 | 8.0 | 5000 | 2.9761 | 0.3195 | 0.0755 | 0.194 | 0.1938 | 122.724 |
3.1259 | 9.0 | 5625 | 2.9747 | 0.3208 | 0.0755 | 0.1949 | 0.1947 | 122.551 |
3.1151 | 10.0 | 6250 | 2.9737 | 0.3207 | 0.0752 | 0.1949 | 0.1947 | 122.586 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0