|
--- |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
base_model: t5-base |
|
model-index: |
|
- name: t5-base-finetuned-keyword-to-text-generation |
|
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-base-finetuned-keyword-to-text-generation |
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.4643 |
|
- Rouge1: 2.1108 |
|
- Rouge2: 0.3331 |
|
- Rougel: 1.7368 |
|
- Rougelsum: 1.7391 |
|
- Gen Len: 16.591 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 8 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| No log | 1.0 | 375 | 3.4862 | 2.0718 | 0.326 | 1.7275 | 1.7308 | 16.7995 | |
|
| 3.5928 | 2.0 | 750 | 3.4761 | 2.0829 | 0.3253 | 1.7192 | 1.7224 | 16.773 | |
|
| 3.5551 | 3.0 | 1125 | 3.4701 | 2.1028 | 0.3272 | 1.7274 | 1.7296 | 16.6505 | |
|
| 3.5225 | 4.0 | 1500 | 3.4671 | 2.11 | 0.3305 | 1.7343 | 1.7362 | 16.699 | |
|
| 3.5225 | 5.0 | 1875 | 3.4653 | 2.1134 | 0.3319 | 1.7418 | 1.7437 | 16.5485 | |
|
| 3.4987 | 6.0 | 2250 | 3.4643 | 2.1108 | 0.3331 | 1.7368 | 1.7391 | 16.591 | |
|
| 3.4939 | 7.0 | 2625 | 3.4643 | 2.1108 | 0.3331 | 1.7368 | 1.7391 | 16.591 | |
|
| 3.498 | 8.0 | 3000 | 3.4643 | 2.1108 | 0.3331 | 1.7368 | 1.7391 | 16.591 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.21.2 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.4.0 |
|
- Tokenizers 0.12.1 |
|
|
