metadata
license: mit
tags:
- generated_from_trainer
datasets:
- super_glue
metrics:
- accuracy
model-index:
- name: finetune_deberta_small_model
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: super_glue
type: super_glue
config: boolq
split: train
args: boolq
metrics:
- name: Accuracy
type: accuracy
value: 0.7926605504587156
finetune_deberta_small_model
This model is a fine-tuned version of microsoft/deberta-v3-xsmall on the super_glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.4789
- Accuracy: 0.7927
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6336 | 1.0 | 590 | 0.5304 | 0.7425 |
0.5098 | 2.0 | 1180 | 0.4992 | 0.7807 |
0.4304 | 3.0 | 1770 | 0.4789 | 0.7927 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.0+cu116
- Datasets 2.8.0
- Tokenizers 0.13.2