metadata
license: apache-2.0
base_model: google/mt5-small
tags:
- summarization
- generated_from_trainer
metrics:
- rouge
model-index:
- name: mt5-small-finetuned-cnndailymail-en
results: []
datasets:
- cnn_dailymail
library_name: transformers
mt5-small-finetuned-cnndailymail-en
This model is a fine-tuned version of google/mt5-small on an cnn_dailymail dataset. It achieves the following results on the evaluation set:
- Loss: 1.9001
- Rouge1: 0.2945
- Rouge2: 0.1496
- Rougel: 0.2717
- Rougelsum: 0.2755
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: 5.6e-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
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 3.108 | 1.0 | 6250 | 2.1633 | 0.2817 | 0.1398 | 0.2595 | 0.2633 |
| 2.3974 | 2.0 | 12500 | 2.0337 | 0.2894 | 0.1451 | 0.2671 | 0.2709 |
| 2.2688 | 3.0 | 18750 | 1.9802 | 0.2906 | 0.1454 | 0.2682 | 0.2720 |
| 2.1937 | 4.0 | 25000 | 1.9602 | 0.2899 | 0.1451 | 0.2674 | 0.2711 |
| 2.1403 | 5.0 | 31250 | 1.9341 | 0.2882 | 0.1442 | 0.2663 | 0.2702 |
| 2.1005 | 6.0 | 37500 | 1.9161 | 0.2931 | 0.1477 | 0.2705 | 0.2743 |
| 2.071 | 7.0 | 43750 | 1.9145 | 0.2929 | 0.1487 | 0.2706 | 0.2745 |
| 2.0476 | 8.0 | 50000 | 1.9088 | 0.2940 | 0.1495 | 0.2715 | 0.2752 |
| 2.0323 | 9.0 | 56250 | 1.9074 | 0.2943 | 0.1497 | 0.2717 | 0.2755 |
| 2.0203 | 10.0 | 62500 | 1.9001 | 0.2945 | 0.1496 | 0.2717 | 0.2755 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2