|
--- |
|
license: apache-2.0 |
|
base_model: google/mt5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: mt5-small-dataset2 |
|
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-dataset2 |
|
|
|
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: 1.5680 |
|
- Rouge1: 0.556 |
|
- Rouge2: 0.2002 |
|
- Rougel: 0.5256 |
|
- Rougelsum: 0.5248 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
| 4.4723 | 1.0 | 500 | 2.1274 | 0.3988 | 0.082 | 0.373 | 0.3729 | |
|
| 2.2471 | 2.0 | 1000 | 1.8718 | 0.4855 | 0.1556 | 0.4623 | 0.4617 | |
|
| 2.0198 | 3.0 | 1500 | 1.7499 | 0.5365 | 0.1946 | 0.5122 | 0.5112 | |
|
| 1.8858 | 4.0 | 2000 | 1.6731 | 0.5431 | 0.1957 | 0.5179 | 0.5174 | |
|
| 1.803 | 5.0 | 2500 | 1.6180 | 0.5562 | 0.2093 | 0.5296 | 0.5294 | |
|
| 1.7344 | 6.0 | 3000 | 1.5948 | 0.5561 | 0.2008 | 0.5254 | 0.5249 | |
|
| 1.7034 | 7.0 | 3500 | 1.5644 | 0.5608 | 0.2069 | 0.5314 | 0.5305 | |
|
| 1.6794 | 8.0 | 4000 | 1.5680 | 0.556 | 0.2002 | 0.5256 | 0.5248 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|