|
--- |
|
base_model: mrm8488/t5-base-finetuned-common_gen |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: T5-based-keywords-to-sentence-Epoch-10 |
|
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-based-keywords-to-sentence-Epoch-10 |
|
|
|
This model is a fine-tuned version of [mrm8488/t5-base-finetuned-common_gen](https://huggingface.co/mrm8488/t5-base-finetuned-common_gen) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.9915 |
|
- Bleu: 10.3156 |
|
- Gen Len: 13.7832 |
|
|
|
## 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: 128 |
|
- eval_batch_size: 128 |
|
- 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 | Bleu | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:| |
|
| 1.83 | 1.0 | 527 | 1.9997 | 10.4298 | 13.7036 | |
|
| 1.816 | 2.0 | 1054 | 1.9972 | 10.5072 | 13.6857 | |
|
| 1.8084 | 3.0 | 1581 | 2.0045 | 10.4912 | 13.6837 | |
|
| 1.7929 | 4.0 | 2108 | 2.0073 | 10.3682 | 13.662 | |
|
| 1.7902 | 5.0 | 2635 | 2.0089 | 10.3812 | 13.7352 | |
|
| 1.7793 | 6.0 | 3162 | 2.0100 | 10.4598 | 13.7103 | |
|
| 1.7754 | 7.0 | 3689 | 2.0091 | 10.4524 | 13.6598 | |
|
| 1.7686 | 8.0 | 4216 | 2.0050 | 10.4623 | 13.674 | |
|
| 1.7706 | 9.0 | 4743 | 1.9850 | 10.5107 | 13.67 | |
|
| 1.7755 | 10.0 | 5270 | 1.9915 | 10.3156 | 13.7832 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.2.2+cu118 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.1 |
|
|
