|
--- |
|
license: apache-2.0 |
|
base_model: t5-large |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: t5-large_rte_sp0_ar0 |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: glue |
|
type: glue |
|
config: rte |
|
split: validation |
|
args: rte |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.859375 |
|
--- |
|
|
|
<!-- 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-large_rte_sp0_ar0 |
|
|
|
This model is a fine-tuned version of [t5-large](https://huggingface.co/t5-large) on the glue dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.5699 |
|
- Accuracy: 0.8594 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 32 |
|
- seed: 1 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 20 |
|
- training_steps: 750 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.6946 | 0.27 | 25 | 0.6855 | 0.5271 | |
|
| 0.6855 | 0.54 | 50 | 0.6477 | 0.6354 | |
|
| 0.5931 | 0.82 | 75 | 0.4711 | 0.7942 | |
|
| 0.4206 | 1.09 | 100 | 0.5129 | 0.8159 | |
|
| 0.4076 | 1.36 | 125 | 0.4682 | 0.8375 | |
|
| 0.2787 | 1.63 | 150 | 0.4392 | 0.8484 | |
|
| 0.2772 | 1.9 | 175 | 0.4809 | 0.8520 | |
|
| 0.2214 | 2.17 | 200 | 0.8655 | 0.8448 | |
|
| 0.1505 | 2.45 | 225 | 0.9392 | 0.8628 | |
|
| 0.1502 | 2.72 | 250 | 1.2747 | 0.8664 | |
|
| 0.1149 | 2.99 | 275 | 3.4780 | 0.8448 | |
|
| 0.1074 | 3.26 | 300 | 2.8125 | 0.8484 | |
|
| 0.1359 | 3.53 | 325 | 3.0765 | 0.8448 | |
|
| 0.0577 | 3.8 | 350 | 3.1358 | 0.8592 | |
|
| 0.0212 | 4.08 | 375 | 3.3075 | 0.8520 | |
|
| 0.0251 | 4.35 | 400 | 5.9088 | 0.8736 | |
|
| 0.0532 | 4.62 | 425 | 5.5508 | 0.8700 | |
|
| 0.0229 | 4.89 | 450 | 4.6194 | 0.8700 | |
|
| 0.0517 | 5.16 | 475 | 3.2927 | 0.8592 | |
|
| 0.0182 | 5.43 | 500 | 4.5065 | 0.8773 | |
|
| 0.2538 | 5.71 | 525 | 4.5460 | 0.8809 | |
|
| 0.0162 | 5.98 | 550 | 4.2678 | 0.8700 | |
|
| 0.0221 | 6.25 | 575 | 4.6268 | 0.8664 | |
|
| 0.007 | 6.52 | 600 | 4.3411 | 0.8664 | |
|
| 0.0038 | 6.79 | 625 | 5.0136 | 0.8664 | |
|
| 0.036 | 7.07 | 650 | 5.6308 | 0.8736 | |
|
| 0.0064 | 7.34 | 675 | 5.9644 | 0.8736 | |
|
| 0.0037 | 7.61 | 700 | 5.3223 | 0.8736 | |
|
| 0.0121 | 7.88 | 725 | 5.3345 | 0.8736 | |
|
| 0.0251 | 8.15 | 750 | 4.9899 | 0.8736 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.14.1 |
|
|
