model_gpt2_large_d_hate_bias_political_bias_ep_1_a_sqn_a_b_p_100_3_v_9
This model is a fine-tuned version of BogdanTurbal/model_gpt2_large_d_hate_bias_ep_1_sqn_a_p_100_v_9 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.4822
- Balanced Accuracy: 0.6877
- Accuracy: 0.6873
- F1 Micro: 0.6873
- F1 Macro: 0.6852
- Precision Micro: 0.6873
- Precision Macro: 0.6931
- Recall Micro: 0.6873
- Recall Macro: 0.6877
- Auc: 0.7503
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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Balanced Accuracy | Accuracy | F1 Micro | F1 Macro | Precision Micro | Precision Macro | Recall Micro | Recall Macro | Auc |
---|---|---|---|---|---|---|---|---|---|---|---|---|
0.8058 | 1.0 | 44 | 0.6132 | 0.6588 | 0.6598 | 0.6598 | 0.6462 | 0.6598 | 0.6867 | 0.6598 | 0.6588 | 0.7368 |
0.4142 | 2.0 | 88 | 1.1763 | 0.6648 | 0.6641 | 0.6641 | 0.6582 | 0.6641 | 0.6775 | 0.6641 | 0.6648 | 0.7409 |
0.1926 | 3.0 | 132 | 1.2947 | 0.6962 | 0.6959 | 0.6959 | 0.6949 | 0.6959 | 0.6990 | 0.6959 | 0.6962 | 0.7478 |
0.0786 | 4.0 | 176 | 1.4822 | 0.6877 | 0.6873 | 0.6873 | 0.6852 | 0.6873 | 0.6931 | 0.6873 | 0.6877 | 0.7503 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2