metadata
license: mit
base_model: FacebookAI/roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: roberta-large-olid
results: []
roberta-large-olid
This model is a fine-tuned version of FacebookAI/roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4942
- Accuracy: 0.8439
- F1: 0.8438
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- 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 | F1 |
|---|---|---|---|---|---|
| 0.4501 | 1.0 | 884 | 0.3906 | 0.8374 | 0.8373 |
| 0.3826 | 2.0 | 1768 | 0.3949 | 0.8173 | 0.8157 |
| 0.3604 | 3.0 | 2652 | 0.3810 | 0.8405 | 0.8404 |
| 0.3456 | 4.0 | 3536 | 0.4027 | 0.8419 | 0.8419 |
| 0.2784 | 5.0 | 4420 | 0.4942 | 0.8439 | 0.8438 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.0+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2