metadata
license: apache-2.0
base_model: google-t5/t5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: test_sum_1_model
results: []
test_sum_1_model
This model is a fine-tuned version of google-t5/t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8708
- Rouge1: 0.3843
- Rouge2: 0.2726
- Rougel: 0.3466
- Rougelsum: 0.3464
- Gen Len: 18.9887
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 |
|---|---|---|---|---|---|---|---|---|
| 1.0502 | 1.0 | 1764 | 0.9356 | 0.3818 | 0.2695 | 0.3439 | 0.3438 | 18.9816 |
| 0.9636 | 2.0 | 3528 | 0.8917 | 0.3838 | 0.2717 | 0.3461 | 0.3461 | 18.9851 |
| 0.9552 | 3.0 | 5292 | 0.8762 | 0.3839 | 0.272 | 0.346 | 0.3458 | 18.9877 |
| 0.9289 | 4.0 | 7056 | 0.8708 | 0.3843 | 0.2726 | 0.3466 | 0.3464 | 18.9887 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2