|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: t5-small-med-term-conditional-masking-0 |
|
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. --> |
|
|
|
# t5-small-med-term-conditional-masking-0 |
|
|
|
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: 0.6688 |
|
- Rouge2 Precision: 0.694 |
|
- Rouge2 Recall: 0.4781 |
|
- Rouge2 Fmeasure: 0.5479 |
|
|
|
## 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: 2e-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: 10 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge2 Precision | Rouge2 Recall | Rouge2 Fmeasure | |
|
|:-------------:|:-----:|:------:|:---------------:|:----------------:|:-------------:|:---------------:| |
|
| 0.9525 | 1.0 | 13915 | 0.8148 | 0.6657 | 0.4581 | 0.5252 | |
|
| 0.8541 | 2.0 | 27830 | 0.7562 | 0.6779 | 0.4694 | 0.5371 | |
|
| 0.8183 | 3.0 | 41745 | 0.7268 | 0.6827 | 0.4722 | 0.5405 | |
|
| 0.8033 | 4.0 | 55660 | 0.7074 | 0.6861 | 0.4729 | 0.5419 | |
|
| 0.7727 | 5.0 | 69575 | 0.6934 | 0.6872 | 0.4726 | 0.5419 | |
|
| 0.7704 | 6.0 | 83490 | 0.6832 | 0.6901 | 0.4742 | 0.544 | |
|
| 0.7485 | 7.0 | 97405 | 0.6771 | 0.6926 | 0.4772 | 0.5469 | |
|
| 0.7528 | 8.0 | 111320 | 0.6722 | 0.6934 | 0.4782 | 0.5478 | |
|
| 0.7535 | 9.0 | 125235 | 0.6696 | 0.6944 | 0.4782 | 0.5481 | |
|
| 0.7444 | 10.0 | 139150 | 0.6688 | 0.694 | 0.4781 | 0.5479 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0 |
|
- Pytorch 1.10.0+cu111 |
|
- Datasets 2.0.0 |
|
- Tokenizers 0.11.6 |
|
|