|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-small |
|
tags: |
|
- summarization |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: mT5 |
|
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 |
|
|
|
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 7.3770 |
|
- Rouge1: 7.972 |
|
- Rouge2: 1.6667 |
|
- Rougel: 7.972 |
|
- Rougelsum: 6.4336 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 8 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
| 22.553 | 1.0 | 7 | 12.1593 | 7.972 | 1.6667 | 7.972 | 6.4336 | |
|
| 20.0448 | 2.0 | 14 | 8.1176 | 7.972 | 1.6667 | 7.972 | 6.4336 | |
|
| 17.5194 | 3.0 | 21 | 7.7753 | 7.972 | 1.6667 | 7.972 | 6.4336 | |
|
| 18.608 | 4.0 | 28 | 7.6868 | 7.972 | 1.6667 | 7.972 | 6.4336 | |
|
| 15.8009 | 5.0 | 35 | 7.4422 | 7.972 | 1.6667 | 7.972 | 6.4336 | |
|
| 16.2277 | 6.0 | 42 | 7.8053 | 7.972 | 1.6667 | 7.972 | 6.4336 | |
|
| 16.2949 | 7.0 | 49 | 7.8086 | 7.972 | 1.6667 | 7.972 | 6.4336 | |
|
| 15.1347 | 8.0 | 56 | 7.3770 | 7.972 | 1.6667 | 7.972 | 6.4336 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
