metadata
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- glue
metrics:
- accuracy
model_index:
- name: bert-base-uncased-finetuned-sst2
results:
- dataset:
name: glue
type: glue
args: sst2
metric:
name: Accuracy
type: accuracy
value: 0.9220183486238532
bert-base-uncased-finetuned-sst2
This model is a fine-tuned version of bert-base-uncased on the glue dataset. It achieves the following results on the evaluation set:
- Loss: 0.3912
- Accuracy: 0.9220
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.4005 | 1.0 | 4210 | 0.4058 | 0.9025 |
| 0.3707 | 2.0 | 8420 | 0.4141 | 0.8968 |
| 0.3554 | 3.0 | 12630 | 0.3978 | 0.9151 |
| 0.3551 | 4.0 | 16840 | 0.3912 | 0.9220 |
| 0.353 | 5.0 | 21050 | 0.3930 | 0.9209 |
Framework versions
- Transformers 4.9.1
- Pytorch 1.9.0+cu102
- Datasets 1.11.0
- Tokenizers 0.10.3