metadata
library_name: transformers
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
- sentiment-analysis
metrics:
- accuracy
model-index:
- name: roberta-imdb
results: []
roberta-imdb
This model is a fine-tuned version of FacebookAI/roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1680
- Accuracy: 0.9561
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: 24
- eval_batch_size: 24
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.2052 | 0.4997 | 833 | 0.1646 | 0.9435 |
| 0.1565 | 0.9994 | 1666 | 0.1862 | 0.9421 |
| 0.2213 | 1.4991 | 2499 | 0.1759 | 0.9547 |
| 0.1314 | 1.9988 | 3332 | 0.1680 | 0.9561 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2