metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: imdb_classification_roberta
results: []
imdb_classification_roberta
This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2211
- Accuracy: 0.9531
- F1 Macro: 0.9531
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=(0.9,0.98) and epsilon=1e-06
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.06
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro |
|---|---|---|---|---|---|
| 0.224 | 1.0 | 1250 | 0.2058 | 0.9396 | 0.9396 |
| 0.1363 | 2.0 | 2500 | 0.1882 | 0.9494 | 0.9494 |
| 0.093 | 3.0 | 3750 | 0.2286 | 0.9506 | 0.9506 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2