metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: RewardModelOnlyOnAnswer
results: []
RewardModelOnlyOnAnswer
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6051
- F1: 0.5377
- Roc Auc: 0.6538
- Accuracy: 0.53
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
- 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 | F1 | Roc Auc | Accuracy |
|---|---|---|---|---|---|---|
| No log | 1.0 | 258 | 0.6315 | 0.0 | 0.5 | 0.0 |
| 0.6039 | 2.0 | 516 | 0.6412 | 0.3732 | 0.5613 | 0.32 |
| 0.6039 | 3.0 | 774 | 0.6051 | 0.5377 | 0.6538 | 0.53 |
| 0.3801 | 4.0 | 1032 | 0.7261 | 0.5163 | 0.6375 | 0.51 |
| 0.3801 | 5.0 | 1290 | 0.8381 | 0.4792 | 0.6062 | 0.46 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3