|
--- |
|
license: apache-2.0 |
|
base_model: t5-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: t5-base_cola_dense_epochs-3 |
|
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: 0.8283796740172579 |
|
--- |
|
|
|
<!-- 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-3 |
|
|
|
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: 0.5042 |
|
- Accuracy: 0.8284 |
|
|
|
## 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: 3 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.5796 | 0.19 | 50 | 0.5780 | 0.6913 | |
|
| 0.4821 | 0.37 | 100 | 0.6683 | 0.7546 | |
|
| 0.4703 | 0.56 | 150 | 0.4976 | 0.8035 | |
|
| 0.4252 | 0.75 | 200 | 0.4958 | 0.8150 | |
|
| 0.4915 | 0.93 | 250 | 0.5360 | 0.8044 | |
|
| 0.3812 | 1.12 | 300 | 0.4645 | 0.8322 | |
|
| 0.3603 | 1.31 | 350 | 0.4788 | 0.8293 | |
|
| 0.3336 | 1.49 | 400 | 0.5135 | 0.8245 | |
|
| 0.4157 | 1.68 | 450 | 0.5311 | 0.8322 | |
|
| 0.4094 | 1.87 | 500 | 0.5042 | 0.8284 | |
|
| 0.2836 | 2.05 | 550 | 0.5277 | 0.8313 | |
|
| 0.2993 | 2.24 | 600 | 0.5515 | 0.8341 | |
|
| 0.2843 | 2.43 | 650 | 0.5195 | 0.8332 | |
|
| 0.2288 | 2.61 | 700 | 0.5129 | 0.8332 | |
|
| 0.3165 | 2.8 | 750 | 0.5126 | 0.8360 | |
|
| 0.2717 | 2.99 | 800 | 0.5083 | 0.8332 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
