|
--- |
|
license: apache-2.0 |
|
base_model: t5-large |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: t5-large_cola_dense_epochs-7_decoder_all_sparsity10 |
|
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: 0.837967401725791 |
|
--- |
|
|
|
<!-- 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_dense_epochs-7_decoder_all_sparsity10 |
|
|
|
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: 4.6969 |
|
- Accuracy: 0.8380 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 128 |
|
- seed: 1 |
|
- distributed_type: multi-GPU |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 128 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 20 |
|
- num_epochs: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.5441 | 0.37 | 25 | 0.5813 | 0.6913 | |
|
| 0.3969 | 0.75 | 50 | 0.5219 | 0.8044 | |
|
| 0.3537 | 1.12 | 75 | 0.4713 | 0.8313 | |
|
| 0.2905 | 1.49 | 100 | 0.6308 | 0.8150 | |
|
| 0.3157 | 1.87 | 125 | 0.4301 | 0.8341 | |
|
| 0.2208 | 2.24 | 150 | 2.3147 | 0.8332 | |
|
| 0.2231 | 2.61 | 175 | 0.4612 | 0.8341 | |
|
| 0.2404 | 2.99 | 200 | 1.5471 | 0.8265 | |
|
| 0.1697 | 3.36 | 225 | 0.8701 | 0.8313 | |
|
| 0.131 | 3.73 | 250 | 1.2642 | 0.8380 | |
|
| 0.1219 | 4.1 | 275 | 0.9926 | 0.8370 | |
|
| 0.2647 | 4.48 | 300 | 5.1919 | 0.8341 | |
|
| 0.1329 | 4.85 | 325 | 2.2726 | 0.8418 | |
|
| 0.0857 | 5.22 | 350 | 4.2193 | 0.8370 | |
|
| 0.0989 | 5.6 | 375 | 5.3604 | 0.8389 | |
|
| 0.2557 | 5.97 | 400 | 3.0246 | 0.8341 | |
|
| 0.2617 | 6.34 | 425 | 5.6630 | 0.8456 | |
|
| 0.2526 | 6.72 | 450 | 6.0474 | 0.8360 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.1 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.9.0 |
|
- Tokenizers 0.14.1 |
|
|
