|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: t5-base |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- glue |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: t5-base_cola_dense_epochs-5 |
|
|
results: |
|
|
- task: |
|
|
name: Text Classification |
|
|
type: text-classification |
|
|
dataset: |
|
|
name: glue |
|
|
type: glue |
|
|
config: cola |
|
|
split: validation |
|
|
args: cola |
|
|
metrics: |
|
|
- name: Accuracy |
|
|
type: accuracy |
|
|
value: 0.822627037392138 |
|
|
--- |
|
|
|
|
|
<!-- 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_cola_dense_epochs-5 |
|
|
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the glue dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.5026 |
|
|
- Accuracy: 0.8226 |
|
|
|
|
|
## 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: 5e-05 |
|
|
- train_batch_size: 32 |
|
|
- eval_batch_size: 64 |
|
|
- seed: 0 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: linear |
|
|
- lr_scheduler_warmup_steps: 20 |
|
|
- num_epochs: 5 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
|
| 0.5712 | 0.19 | 50 | 0.5805 | 0.6913 | |
|
|
| 0.4693 | 0.37 | 100 | 0.6260 | 0.7661 | |
|
|
| 0.4731 | 0.56 | 150 | 0.5279 | 0.8054 | |
|
|
| 0.3707 | 0.75 | 200 | 0.5165 | 0.8025 | |
|
|
| 0.4729 | 0.93 | 250 | 0.5145 | 0.8102 | |
|
|
| 0.3929 | 1.12 | 300 | 0.4773 | 0.8188 | |
|
|
| 0.3369 | 1.31 | 350 | 0.5014 | 0.8198 | |
|
|
| 0.3757 | 1.49 | 400 | 0.5183 | 0.8188 | |
|
|
| 0.4206 | 1.68 | 450 | 0.5743 | 0.8198 | |
|
|
| 0.4196 | 1.87 | 500 | 0.5026 | 0.8226 | |
|
|
| 0.3098 | 2.05 | 550 | 0.5289 | 0.8236 | |
|
|
| 0.2852 | 2.24 | 600 | 0.5562 | 0.8265 | |
|
|
| 0.2936 | 2.43 | 650 | 0.5312 | 0.8303 | |
|
|
| 0.2072 | 2.61 | 700 | 0.4904 | 0.8313 | |
|
|
| 0.2809 | 2.8 | 750 | 0.5394 | 0.8341 | |
|
|
| 0.2685 | 2.99 | 800 | 0.5905 | 0.8332 | |
|
|
| 0.2215 | 3.17 | 850 | 0.5835 | 0.8341 | |
|
|
| 0.3543 | 3.36 | 900 | 0.5556 | 0.8332 | |
|
|
| 0.239 | 3.54 | 950 | 0.5419 | 0.8351 | |
|
|
| 0.257 | 3.73 | 1000 | 0.5587 | 0.8351 | |
|
|
| 0.2958 | 3.92 | 1050 | 0.5982 | 0.8341 | |
|
|
| 0.2785 | 4.1 | 1100 | 0.5978 | 0.8360 | |
|
|
| 0.1975 | 4.29 | 1150 | 0.6067 | 0.8341 | |
|
|
| 0.2222 | 4.48 | 1200 | 0.5947 | 0.8380 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.34.1 |
|
|
- Pytorch 2.1.0+cu118 |
|
|
- Datasets 2.14.6 |
|
|
- Tokenizers 0.14.1 |
|
|
|
