|
--- |
|
license: apache-2.0 |
|
base_model: t5-large |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: t5-large_rte_dense_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: 0.0 |
|
--- |
|
|
|
<!-- 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_dense_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: 0.9322 |
|
- Accuracy: 0.0 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 16 |
|
- seed: 1 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 16 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| 0.6781 | 0.16 | 25 | 0.6834 | 0.5487 | |
|
| 0.7041 | 0.32 | 50 | 0.6878 | 0.5523 | |
|
| 0.689 | 0.48 | 75 | 0.6836 | 0.6065 | |
|
| 0.6902 | 0.64 | 100 | 0.6630 | 0.5740 | |
|
| 0.6458 | 0.8 | 125 | 0.5695 | 0.7112 | |
|
| 0.5973 | 0.96 | 150 | 0.6138 | 0.6823 | |
|
| 0.5697 | 1.12 | 175 | 0.5707 | 0.7581 | |
|
| 0.4567 | 1.28 | 200 | 0.6558 | 0.7256 | |
|
| 0.3796 | 1.44 | 225 | 0.4968 | 0.7870 | |
|
| 0.3749 | 1.6 | 250 | 0.5082 | 0.8123 | |
|
| 0.5187 | 1.76 | 275 | 0.4428 | 0.8123 | |
|
| 0.4176 | 1.92 | 300 | 0.3940 | 0.8556 | |
|
| 0.2678 | 2.08 | 325 | 0.4938 | 0.8484 | |
|
| 0.0761 | 2.24 | 350 | 0.6533 | 0.8520 | |
|
| 0.2082 | 2.4 | 375 | 0.5901 | 0.8484 | |
|
| 0.4081 | 2.56 | 400 | 0.5939 | 0.8520 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.2 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.11.6 |
|
|
