|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: google/mt5-small |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- rouge |
|
|
model-index: |
|
|
- name: mt5-small-lower |
|
|
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-lower |
|
|
|
|
|
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: 2.2645 |
|
|
- Rouge1: 21.3986 |
|
|
- Rouge2: 0.0 |
|
|
- Rougel: 21.4078 |
|
|
- Rougelsum: 21.5242 |
|
|
- Gen Len: 14.4947 |
|
|
|
|
|
## 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: 5e-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: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:| |
|
|
| 2.9469 | 1.0 | 6877 | 2.5088 | 21.3986 | 0.0 | 21.4078 | 21.5242 | 10.4989 | |
|
|
| 2.6632 | 2.0 | 13754 | 2.3772 | 21.3986 | 0.0 | 21.4078 | 21.5242 | 14.1979 | |
|
|
| 2.5438 | 3.0 | 20631 | 2.3055 | 21.3986 | 0.0 | 21.4078 | 21.5242 | 14.1095 | |
|
|
| 2.5355 | 4.0 | 27508 | 2.2747 | 21.3986 | 0.0 | 21.4078 | 21.5242 | 14.3832 | |
|
|
| 2.4597 | 5.0 | 34385 | 2.2645 | 21.3986 | 0.0 | 21.4078 | 21.5242 | 14.4947 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.41.2 |
|
|
- Pytorch 2.1.2 |
|
|
- Datasets 2.19.2 |
|
|
- Tokenizers 0.19.1 |
|
|
|
