metadata
language:
- en
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model-index:
- name: jpqd-bert-base-ft-sst2
results:
- task:
name: Text Classification
type: text-classification
dataset:
name: GLUE SST2
type: glue
args: sst2
metrics:
- name: Accuracy
type: accuracy
value: 0.9254587155963303
jpqd-bert-base-ft-sst2
Note This model was trained for only 1 epoch and is shared for testing purposes
This model is a fine-tuned version of bert-base-uncased on the GLUE SST2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2181
- Accuracy: 0.9255
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: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4129 | 0.12 | 250 | 0.4416 | 0.8761 |
| 0.412 | 0.24 | 500 | 0.4969 | 0.8899 |
| 0.3191 | 0.36 | 750 | 0.2717 | 0.9163 |
| 0.2688 | 0.48 | 1000 | 0.2432 | 0.9117 |
| 0.3306 | 0.59 | 1250 | 0.2033 | 0.9243 |
| 0.224 | 0.71 | 1500 | 0.2383 | 0.9243 |
| 0.2082 | 0.83 | 1750 | 0.2233 | 0.9255 |
| 0.2161 | 0.95 | 2000 | 0.2207 | 0.9255 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.2