metadata
license: cc
base_model: davidmasip/racism
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: racism-finetuned-detests-wandb
results: []
racism-finetuned-detests-wandb
This model is a fine-tuned version of davidmasip/racism on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4148
- Accuracy: 0.8265
- F1-score: 0.7569
- Precision: 0.7532
- Recall: 0.7608
- Auc: 0.7608
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: 3e-05
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1-score | Precision | Recall | Auc |
|---|---|---|---|---|---|---|---|---|
| 0.3742 | 1.0 | 44 | 0.3319 | 0.8412 | 0.7461 | 0.7899 | 0.7221 | 0.7221 |
| 0.092 | 2.0 | 88 | 0.4148 | 0.8265 | 0.7569 | 0.7532 | 0.7608 | 0.7608 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0