|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: google/mt5-small |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- rouge |
|
|
model-index: |
|
|
- name: mt5-small-dataset3 |
|
|
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-dataset3 |
|
|
|
|
|
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: 1.4341 |
|
|
- Rouge1: 0.5489 |
|
|
- Rouge2: 0.2033 |
|
|
- Rougel: 0.5208 |
|
|
- Rougelsum: 0.5212 |
|
|
|
|
|
## 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 | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
|
| 4.1512 | 1.0 | 500 | 2.0642 | 0.503 | 0.172 | 0.4893 | 0.4899 | |
|
|
| 2.1206 | 2.0 | 1000 | 1.7535 | 0.5288 | 0.1861 | 0.5137 | 0.5143 | |
|
|
| 1.8841 | 3.0 | 1500 | 1.6171 | 0.5293 | 0.1798 | 0.5069 | 0.5072 | |
|
|
| 1.7527 | 4.0 | 2000 | 1.5333 | 0.5335 | 0.1837 | 0.5069 | 0.507 | |
|
|
| 1.6573 | 5.0 | 2500 | 1.4857 | 0.5444 | 0.1941 | 0.5165 | 0.5163 | |
|
|
| 1.6073 | 6.0 | 3000 | 1.4628 | 0.5405 | 0.197 | 0.5133 | 0.5136 | |
|
|
| 1.5703 | 7.0 | 3500 | 1.4368 | 0.5519 | 0.2097 | 0.5267 | 0.5271 | |
|
|
| 1.5415 | 8.0 | 4000 | 1.4341 | 0.5489 | 0.2033 | 0.5208 | 0.5212 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.35.2 |
|
|
- Pytorch 2.1.0+cu118 |
|
|
- Datasets 2.15.0 |
|
|
- Tokenizers 0.15.0 |
|
|
|
