|
--- |
|
license: apache-2.0 |
|
base_model: t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: 7epochisdabest |
|
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. --> |
|
|
|
# 7epochisdabest |
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.6723 |
|
- Rouge1: 0.1892 |
|
- Rouge2: 0.0723 |
|
- Rougel: 0.1517 |
|
- Rougelsum: 0.1515 |
|
- Gen Len: 19.0 |
|
|
|
## 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: 7 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 3.0939 | 1.0 | 1370 | 2.7942 | 0.1877 | 0.0727 | 0.1506 | 0.1505 | 18.894 | |
|
| 2.9829 | 2.0 | 2740 | 2.7420 | 0.1901 | 0.0734 | 0.1523 | 0.152 | 19.0 | |
|
| 2.9343 | 3.0 | 4110 | 2.7119 | 0.1898 | 0.0733 | 0.1522 | 0.1521 | 19.0 | |
|
| 2.9013 | 4.0 | 5480 | 2.6937 | 0.1891 | 0.0723 | 0.1514 | 0.1512 | 19.0 | |
|
| 2.8908 | 5.0 | 6850 | 2.6799 | 0.1895 | 0.0723 | 0.1515 | 0.1513 | 19.0 | |
|
| 2.8676 | 6.0 | 8220 | 2.6749 | 0.1889 | 0.0722 | 0.1518 | 0.1517 | 19.0 | |
|
| 2.8433 | 7.0 | 9590 | 2.6723 | 0.1892 | 0.0723 | 0.1517 | 0.1515 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
