|
--- |
|
license: apache-2.0 |
|
base_model: t5-base |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- bigbench |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: bigbench_entailedpolarity-t5-base |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: bigbench |
|
type: bigbench |
|
config: entailed_polarity |
|
split: train |
|
args: entailed_polarity |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9583333333333334 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# bigbench_entailedpolarity-t5-base |
|
|
|
This model is a fine-tuned version of [t5-base](https://huggingface.co/t5-base) on the bigbench dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3881 |
|
- Accuracy: 0.9583 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:| |
|
| No log | 1.0 | 24 | 0.4860 | 0.875 | |
|
| No log | 2.0 | 48 | 0.3200 | 0.875 | |
|
| No log | 3.0 | 72 | 0.3107 | 0.9167 | |
|
| No log | 4.0 | 96 | 0.3666 | 0.9167 | |
|
| No log | 5.0 | 120 | 0.5273 | 0.9167 | |
|
| No log | 6.0 | 144 | 0.3190 | 0.9583 | |
|
| No log | 7.0 | 168 | 0.3328 | 0.9583 | |
|
| No log | 8.0 | 192 | 0.5994 | 0.9167 | |
|
| No log | 9.0 | 216 | 0.6515 | 0.9167 | |
|
| No log | 10.0 | 240 | 0.6435 | 0.9167 | |
|
| No log | 11.0 | 264 | 0.6450 | 0.9167 | |
|
| No log | 12.0 | 288 | 0.6565 | 0.9167 | |
|
| No log | 13.0 | 312 | 0.6484 | 0.9167 | |
|
| No log | 14.0 | 336 | 0.6376 | 0.9167 | |
|
| No log | 15.0 | 360 | 0.6808 | 0.9167 | |
|
| No log | 16.0 | 384 | 0.6884 | 0.9167 | |
|
| No log | 17.0 | 408 | 0.6502 | 0.9167 | |
|
| No log | 18.0 | 432 | 0.6781 | 0.9167 | |
|
| No log | 19.0 | 456 | 0.3894 | 0.9583 | |
|
| No log | 20.0 | 480 | 0.3881 | 0.9583 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 1.10.1+cu102 |
|
- Datasets 2.15.0 |
|
- Tokenizers 0.15.0 |
|
|
