metadata
license: mit
tags:
- generated_from_trainer
datasets:
- sst2
metrics:
- accuracy
base_model: prajjwal1/bert-tiny
model-index:
- name: sentiment-model-saagie
results:
- task:
type: text-classification
name: Text Classification
dataset:
name: sst2
type: sst2
args: default
metrics:
- type: accuracy
value: 0.7766666666666666
name: Accuracy
sentiment-model-saagie
This model is a fine-tuned version of prajjwal1/bert-tiny on the sst2 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5524
- Accuracy: 0.7767
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- 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 |
|---|---|---|---|---|
| 0.5173 | 1.0 | 1500 | 0.4780 | 0.775 |
| 0.3824 | 2.0 | 3000 | 0.5339 | 0.7767 |
| 0.3359 | 3.0 | 4500 | 0.5524 | 0.7767 |
Framework versions
- Transformers 4.18.0
- Pytorch 1.8.1
- Datasets 2.12.0
- Tokenizers 0.12.1