model_gpt2_d_political_bias_hate_bias_ep_1_a_sqn_a_b_p_100_3_v_9
This model is a fine-tuned version of BogdanTurbal/model_gpt2_d_political_bias_ep_1_sqn_a_p_100_v_9 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5998
- Balanced Accuracy: 0.7632
- Accuracy: 0.7632
- F1 Micro: 0.7632
- F1 Macro: 0.7631
- Precision Micro: 0.7632
- Precision Macro: 0.7634
- Recall Micro: 0.7632
- Recall Macro: 0.7632
- Auc: 0.8430
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 |
---|---|---|---|---|---|---|---|---|---|---|---|---|
0.5859 | 1.0 | 46 | 0.5608 | 0.7319 | 0.7319 | 0.7319 | 0.7313 | 0.7319 | 0.7339 | 0.7319 | 0.7319 | 0.8005 |
0.4048 | 2.0 | 92 | 0.5554 | 0.7508 | 0.7508 | 0.7508 | 0.7489 | 0.7508 | 0.7588 | 0.7508 | 0.7508 | 0.8308 |
0.2903 | 3.0 | 138 | 0.5764 | 0.7640 | 0.7640 | 0.7640 | 0.7640 | 0.7640 | 0.7640 | 0.7640 | 0.7640 | 0.8385 |
0.2319 | 4.0 | 184 | 0.5998 | 0.7632 | 0.7632 | 0.7632 | 0.7631 | 0.7632 | 0.7634 | 0.7632 | 0.7632 | 0.8430 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 9
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.