|
--- |
|
language: |
|
- en |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- glue |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: roberta-base-qnli |
|
results: |
|
- task: |
|
name: Text Classification |
|
type: text-classification |
|
dataset: |
|
name: GLUE QNLI |
|
type: glue |
|
args: qnli |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.9245835621453414 |
|
- task: |
|
type: natural-language-inference |
|
name: Natural Language Inference |
|
dataset: |
|
name: glue |
|
type: glue |
|
config: qnli |
|
split: validation |
|
metrics: |
|
- name: Accuracy |
|
type: accuracy |
|
value: 0.924400512538898 |
|
verified: true |
|
- name: Precision |
|
type: precision |
|
value: 0.9171997157071784 |
|
verified: true |
|
- name: Recall |
|
type: recall |
|
value: 0.9348062296269467 |
|
verified: true |
|
- name: AUC |
|
type: auc |
|
value: 0.9744865501321541 |
|
verified: true |
|
- name: F1 |
|
type: f1 |
|
value: 0.9259192825112107 |
|
verified: true |
|
- name: loss |
|
type: loss |
|
value: 0.2990749478340149 |
|
verified: true |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# roberta-base-qnli |
|
|
|
This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on the GLUE QNLI dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2992 |
|
- Accuracy: 0.9246 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.06 |
|
- num_epochs: 10.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
| 0.2986 | 1.0 | 6547 | 0.2215 | 0.9171 | |
|
| 0.243 | 2.0 | 13094 | 0.2321 | 0.9173 | |
|
| 0.2048 | 3.0 | 19641 | 0.2992 | 0.9246 | |
|
| 0.1629 | 4.0 | 26188 | 0.3538 | 0.9220 | |
|
| 0.1308 | 5.0 | 32735 | 0.3533 | 0.9209 | |
|
| 0.0846 | 6.0 | 39282 | 0.4277 | 0.9229 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.20.0.dev0 |
|
- Pytorch 1.11.0+cu113 |
|
- Datasets 2.1.0 |
|
- Tokenizers 0.12.1 |
|
|
