metadata
license: apache-2.0
base_model: google/flan-t5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: finetuned-t5-medical
results: []
finetuned-t5-medical
This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8686
- Rouge1: 0.1114
- Rouge2: 0.0304
- Rougel: 0.0872
- Rougelsum: 0.1020
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: 5
- eval_batch_size: 5
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 85 | 2.0499 | 0.1186 | 0.0307 | 0.0940 | 0.1071 |
| No log | 2.0 | 170 | 1.9463 | 0.1021 | 0.0251 | 0.0838 | 0.0926 |
| No log | 3.0 | 255 | 1.8942 | 0.1158 | 0.0324 | 0.0934 | 0.1083 |
| No log | 4.0 | 340 | 1.8706 | 0.1101 | 0.0279 | 0.0860 | 0.1017 |
| No log | 5.0 | 425 | 1.8686 | 0.1114 | 0.0304 | 0.0872 | 0.1020 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0