metadata
library_name: transformers
license: mit
base_model: roberta-large
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: FairnessReciprocity_binary
results: []
FairnessReciprocity_binary
This model is a fine-tuned version of roberta-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6999
- Accuracy: 0.5972
- Precision: 0.5651
- Recall: 0.6674
- F1: 0.6120
- Auc: 0.6004
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: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | Auc |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 125 | 0.6727 | 0.5782 | 0.5754 | 0.4337 | 0.4946 | 0.5715 |
| No log | 2.0 | 250 | 0.6749 | 0.5912 | 0.5579 | 0.68 | 0.6129 | 0.5953 |
| No log | 3.0 | 375 | 0.6999 | 0.5972 | 0.5651 | 0.6674 | 0.6120 | 0.6004 |
Framework versions
- Transformers 4.44.1
- Pytorch 1.11.0
- Datasets 2.12.0
- Tokenizers 0.19.1