metadata
library_name: transformers
license: mit
base_model: FacebookAI/roberta-base
tags:
- generated_from_trainer
model-index:
- name: fun-wolf-403
results: []
fun-wolf-403
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: 0.1834
- Hamming Loss: 0.0494
- Zero One Loss: 1.0
- Jaccard Score: 1.0
- Hamming Loss Optimised: 0.0494
- Hamming Loss Threshold: 0.9000
- Zero One Loss Optimised: 1.0
- Zero One Loss Threshold: 0.9000
- Jaccard Score Optimised: 1.0
- Jaccard Score Threshold: 0.9000
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: 0.0011128424281972827
- train_batch_size: 20
- eval_batch_size: 20
- seed: 2024
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss | Hamming Loss | Zero One Loss | Jaccard Score | Hamming Loss Optimised | Hamming Loss Threshold | Zero One Loss Optimised | Zero One Loss Threshold | Jaccard Score Optimised | Jaccard Score Threshold |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 160 | 0.1902 | 0.0497 | 1.0 | 1.0 | 0.0497 | 0.9000 | 1.0 | 0.9000 | 1.0 | 0.9000 |
| No log | 2.0 | 320 | 0.1868 | 0.0497 | 1.0 | 1.0 | 0.0497 | 0.9000 | 1.0 | 0.9000 | 1.0 | 0.9000 |
| No log | 3.0 | 480 | 0.1852 | 0.0497 | 1.0 | 1.0 | 0.0497 | 0.9000 | 1.0 | 0.9000 | 1.0 | 0.9000 |
| 0.2032 | 4.0 | 640 | 0.1842 | 0.0497 | 1.0 | 1.0 | 0.0497 | 0.9000 | 1.0 | 0.9000 | 1.0 | 0.9000 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu118
- Datasets 3.1.0
- Tokenizers 0.20.3