|
|
--- |
|
|
license: apache-2.0 |
|
|
tags: |
|
|
- summarization |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- rouge |
|
|
model-index: |
|
|
- name: mt5-small-text-sum-11 |
|
|
results: [] |
|
|
--- |
|
|
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
|
|
# mt5-small-text-sum-11 |
|
|
|
|
|
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 2.3761 |
|
|
- Rouge1: 20.13 |
|
|
- Rouge2: 6.41 |
|
|
- Rougel: 19.84 |
|
|
|
|
|
## 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: 0.0001 |
|
|
- train_batch_size: 9 |
|
|
- eval_batch_size: 9 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- num_epochs: 40 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:| |
|
|
| 4.558 | 1.45 | 500 | 2.6110 | 16.89 | 4.81 | 16.86 | |
|
|
| 3.1188 | 2.9 | 1000 | 2.5397 | 17.58 | 5.27 | 17.4 | |
|
|
| 2.8995 | 4.35 | 1500 | 2.4761 | 18.14 | 5.11 | 17.9 | |
|
|
| 2.7608 | 5.8 | 2000 | 2.4130 | 18.52 | 4.95 | 18.15 | |
|
|
| 2.644 | 7.25 | 2500 | 2.4375 | 18.82 | 5.25 | 18.51 | |
|
|
| 2.5836 | 8.7 | 3000 | 2.4034 | 19.18 | 5.54 | 18.89 | |
|
|
| 2.4949 | 10.14 | 3500 | 2.3703 | 19.4 | 5.84 | 18.98 | |
|
|
| 2.4081 | 11.59 | 4000 | 2.3847 | 19.93 | 6.13 | 19.56 | |
|
|
| 2.358 | 13.04 | 4500 | 2.3528 | 19.98 | 5.84 | 19.62 | |
|
|
| 2.2951 | 14.49 | 5000 | 2.3611 | 20.46 | 6.11 | 20.06 | |
|
|
| 2.2582 | 15.94 | 5500 | 2.3607 | 19.98 | 5.53 | 19.57 | |
|
|
| 2.2157 | 17.39 | 6000 | 2.3763 | 19.69 | 5.61 | 19.43 | |
|
|
| 2.1741 | 18.84 | 6500 | 2.3557 | 20.42 | 6.11 | 20.03 | |
|
|
| 2.1302 | 20.29 | 7000 | 2.3623 | 19.44 | 5.53 | 18.99 | |
|
|
| 2.1018 | 21.74 | 7500 | 2.3761 | 20.13 | 6.41 | 19.84 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.27.4 |
|
|
- Pytorch 1.13.1+cu116 |
|
|
- Datasets 2.11.0 |
|
|
- Tokenizers 0.13.2 |
|
|
|
