|
--- |
|
license: apache-2.0 |
|
base_model: t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: Summary |
|
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. --> |
|
|
|
# Summary |
|
|
|
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: 1.7430 |
|
- Rouge1: 0.2448 |
|
- Rouge2: 0.1173 |
|
- Rougel: 0.2028 |
|
- Rougelsum: 0.2029 |
|
- 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: 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: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| No log | 1.0 | 282 | 1.7743 | 0.2429 | 0.1151 | 0.2007 | 0.2008 | 18.9976 | |
|
| 2.0101 | 2.0 | 564 | 1.7550 | 0.2448 | 0.1169 | 0.203 | 0.2032 | 18.9976 | |
|
| 2.0101 | 3.0 | 846 | 1.7477 | 0.2451 | 0.1178 | 0.2034 | 0.2036 | 18.9976 | |
|
| 1.9145 | 4.0 | 1128 | 1.7441 | 0.2449 | 0.1173 | 0.2028 | 0.203 | 18.9976 | |
|
| 1.9145 | 5.0 | 1410 | 1.7430 | 0.2448 | 0.1173 | 0.2028 | 0.2029 | 19.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
