metadata
license: mit
base_model: roberta-base
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: RewardModel_RobertaBase
results: []
RewardModel_RobertaBase
This model is a fine-tuned version of roberta-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1047
- F1: 0.9722
- Roc Auc: 0.9792
- Accuracy: 0.9722
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=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 15 | 0.6256 | 0.0 | 0.5 | 0.0 |
| No log | 2.0 | 30 | 0.5210 | 0.3448 | 0.6042 | 0.2083 |
| No log | 3.0 | 45 | 0.3479 | 0.8143 | 0.8576 | 0.7639 |
| No log | 4.0 | 60 | 0.2431 | 0.9241 | 0.9444 | 0.9167 |
| No log | 5.0 | 75 | 0.1917 | 0.9315 | 0.9514 | 0.9167 |
| No log | 6.0 | 90 | 0.1364 | 0.9655 | 0.9757 | 0.9583 |
| 0.3628 | 7.0 | 105 | 0.1120 | 0.9583 | 0.9688 | 0.9583 |
| 0.3628 | 8.0 | 120 | 0.0967 | 0.9655 | 0.9757 | 0.9583 |
| 0.3628 | 9.0 | 135 | 0.1047 | 0.9722 | 0.9792 | 0.9722 |
| 0.3628 | 10.0 | 150 | 0.0928 | 0.9722 | 0.9792 | 0.9722 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1