metadata
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: Roberta_base_all_original_cols
results: []
Roberta_base_all_original_cols
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: 0.9894
- Accuracy: 0.7839
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
- distributed_type: multi-GPU
- 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 |
|---|---|---|---|---|
| 1.0468 | 1.0 | 4188 | 0.8295 | 0.7591 |
| 0.8904 | 2.0 | 8376 | 0.8266 | 0.7583 |
| 0.5917 | 3.0 | 12564 | 0.8416 | 0.7804 |
| 0.6865 | 4.0 | 16752 | 0.8817 | 0.7841 |
| 0.2668 | 5.0 | 20940 | 0.9894 | 0.7839 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.0