|
--- |
|
license: apache-2.0 |
|
tags: |
|
- summarization |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: mt5-small-text-sum-7 |
|
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-7 |
|
|
|
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: 2.3801 |
|
- Rouge1: 20.58 |
|
- Rouge2: 6.51 |
|
- Rougel: 20.26 |
|
|
|
## 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: 13 |
|
- eval_batch_size: 13 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:| |
|
| 4.4436 | 2.09 | 500 | 2.5528 | 17.73 | 5.9 | 17.55 | |
|
| 3.0439 | 4.18 | 1000 | 2.4974 | 18.76 | 5.73 | 18.64 | |
|
| 2.822 | 6.28 | 1500 | 2.4043 | 17.82 | 5.09 | 17.68 | |
|
| 2.6799 | 8.37 | 2000 | 2.3938 | 18.9 | 5.73 | 18.62 | |
|
| 2.5687 | 10.46 | 2500 | 2.3617 | 19.0 | 5.76 | 18.73 | |
|
| 2.4701 | 12.55 | 3000 | 2.3455 | 19.82 | 6.14 | 19.54 | |
|
| 2.3917 | 14.64 | 3500 | 2.3801 | 20.58 | 6.51 | 20.26 | |
|
| 2.3427 | 16.74 | 4000 | 2.3407 | 19.52 | 6.49 | 19.23 | |
|
| 2.2811 | 18.83 | 4500 | 2.3544 | 18.82 | 5.75 | 18.43 | |
|
| 2.2347 | 20.92 | 5000 | 2.3503 | 20.17 | 6.08 | 19.76 | |
|
| 2.1884 | 23.01 | 5500 | 2.3586 | 20.25 | 6.06 | 19.9 | |
|
| 2.1414 | 25.1 | 6000 | 2.3507 | 19.94 | 6.31 | 19.61 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.1 |
|
- Pytorch 1.13.1+cu116 |
|
- Datasets 2.10.1 |
|
- Tokenizers 0.13.2 |
|
|
