|
--- |
|
license: apache-2.0 |
|
base_model: t5-large |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: t5-large_cola_sp0_ar0_one |
|
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: 0.87890625 |
|
--- |
|
|
|
<!-- 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_cola_sp0_ar0_one |
|
|
|
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: 0.4212 |
|
- Accuracy: 0.8789 |
|
|
|
## 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: 0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.6975 | 0.05 | 25 | 0.6708 | 0.6913 | |
|
| 0.5747 | 0.11 | 50 | 0.5123 | 0.7210 | |
|
| 0.4924 | 0.16 | 75 | 0.5004 | 0.7939 | |
|
| 0.4259 | 0.21 | 100 | 0.4760 | 0.7987 | |
|
| 0.3834 | 0.27 | 125 | 0.5001 | 0.8111 | |
|
| 0.3942 | 0.32 | 150 | 0.4982 | 0.8092 | |
|
| 0.4213 | 0.37 | 175 | 0.5078 | 0.8150 | |
|
| 0.3845 | 0.42 | 200 | 0.4346 | 0.8092 | |
|
| 0.4145 | 0.48 | 225 | 0.4562 | 0.8150 | |
|
| 0.3751 | 0.53 | 250 | 0.4948 | 0.8169 | |
|
| 0.4134 | 0.58 | 275 | 0.4356 | 0.8236 | |
|
| 0.3777 | 0.64 | 300 | 0.4627 | 0.8188 | |
|
| 0.3815 | 0.69 | 325 | 0.4772 | 0.8226 | |
|
| 0.367 | 0.74 | 350 | 0.4117 | 0.8313 | |
|
| 0.342 | 0.8 | 375 | 0.4177 | 0.8351 | |
|
| 0.3136 | 0.85 | 400 | 0.5026 | 0.8265 | |
|
| 0.3222 | 0.9 | 425 | 0.5323 | 0.8303 | |
|
| 0.3863 | 0.96 | 450 | 0.4937 | 0.8245 | |
|
| 0.348 | 1.01 | 475 | 0.4704 | 0.8188 | |
|
| 0.2134 | 1.06 | 500 | 0.6430 | 0.8207 | |
|
| 0.2671 | 1.11 | 525 | 0.5518 | 0.8226 | |
|
| 0.1892 | 1.17 | 550 | 0.5869 | 0.8370 | |
|
| 0.2184 | 1.22 | 575 | 0.5816 | 0.8332 | |
|
| 0.22 | 1.27 | 600 | 0.5451 | 0.8274 | |
|
| 0.1982 | 1.33 | 625 | 0.7300 | 0.8313 | |
|
| 0.2734 | 1.38 | 650 | 0.7040 | 0.8351 | |
|
| 0.2186 | 1.43 | 675 | 0.6650 | 0.8341 | |
|
| 0.2835 | 1.49 | 700 | 0.6628 | 0.8322 | |
|
| 0.2503 | 1.54 | 725 | 0.5194 | 0.8341 | |
|
| 0.2438 | 1.59 | 750 | 0.5362 | 0.8313 | |
|
| 0.2307 | 1.65 | 775 | 0.5405 | 0.8293 | |
|
| 0.2111 | 1.7 | 800 | 0.6129 | 0.8265 | |
|
| 0.1952 | 1.75 | 825 | 0.6411 | 0.8255 | |
|
| 0.2873 | 1.8 | 850 | 0.6279 | 0.8245 | |
|
| 0.295 | 1.86 | 875 | 0.5938 | 0.8236 | |
|
| 0.2967 | 1.91 | 900 | 0.5694 | 0.8265 | |
|
| 0.2128 | 1.96 | 925 | 0.5576 | 0.8265 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.11.6 |
|
|
