metadata
tags:
- generated_from_trainer
datasets:
- klue
metrics:
- accuracy
model_index:
- name: bert-base-finetuned-nli
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: klue
type: klue
args: nli
metric:
name: Accuracy
type: accuracy
value: 0.32566666666666666
bert-base-finetuned-nli
This model is a fine-tuned version of klue/bert-base on the klue dataset. It achieves the following results on the evaluation set:
- Loss: 0.9635
- Accuracy: 0.3257
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: 128
- eval_batch_size: 128
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 196 | 0.9635 | 0.3257 |
| No log | 2.0 | 392 | 0.6451 | 0.107 |
| 0.7364 | 3.0 | 588 | 0.5975 | 0.0987 |
| 0.7364 | 4.0 | 784 | 0.5967 | 0.0867 |
| 0.7364 | 5.0 | 980 | 0.6034 | 0.087 |
Framework versions
- Transformers 4.9.2
- Pytorch 1.9.0+cu102
- Datasets 1.11.0
- Tokenizers 0.10.3