|
--- |
|
license: apache-2.0 |
|
base_model: t5-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: pargraphs_titles |
|
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. --> |
|
|
|
# pargraphs_titles |
|
|
|
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: 0.2408 |
|
- Rouge1: 68.8334 |
|
- Rouge2: 59.1001 |
|
- Rougel: 67.5283 |
|
- Rougelsum: 67.6312 |
|
- Gen Len: 13.7977 |
|
|
|
## 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: 4e-05 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:| |
|
| No log | 1.0 | 455 | 0.4086 | 56.8689 | 47.8503 | 56.3172 | 56.1544 | 13.7393 | |
|
| 0.2169 | 2.0 | 910 | 0.1848 | 66.7857 | 58.5467 | 65.8133 | 65.7037 | 13.8604 | |
|
| 0.1629 | 3.0 | 1365 | 0.1768 | 67.5534 | 59.4926 | 66.5736 | 66.5271 | 13.7222 | |
|
| 0.1347 | 4.0 | 1820 | 0.2881 | 67.7423 | 58.9397 | 66.4095 | 66.5328 | 13.8362 | |
|
| 0.1277 | 5.0 | 2275 | 0.2408 | 68.8334 | 59.1001 | 67.5283 | 67.6312 | 13.7977 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Tokenizers 0.15.0 |
|
|
