metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
- accuracy
model-index:
- name: RewardModelSmallerQuestionWithTwoLabels
results: []
RewardModelSmallerQuestionWithTwoLabels
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: 0.6213
- F1: 0.6909
- Roc Auc: 0.6913
- Accuracy: 0.6875
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 | 233 | 0.6765 | 0.5447 | 0.5675 | 0.5175 |
| No log | 2.0 | 466 | 0.6107 | 0.6767 | 0.6775 | 0.665 |
| 0.6569 | 3.0 | 699 | 0.6213 | 0.6909 | 0.6913 | 0.6875 |
| 0.6569 | 4.0 | 932 | 0.9449 | 0.6683 | 0.6687 | 0.6675 |
| 0.3594 | 5.0 | 1165 | 1.0846 | 0.6816 | 0.6812 | 0.6775 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3