model_gpt2_medium_d_political_bias_hate_bias_ep_1_3_a_sqn_a_b_p_100_5_v_10
This model is a fine-tuned version of BogdanTurbal/model_gpt2_medium_d_political_bias_ep_1_sqn_a_p_100_v_10 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5910
- Accuracy: 0.8166
- F1 Micro: 0.8166
- Auc: 0.9075
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: 0.0001
- train_batch_size: 16
- eval_batch_size: 64
- 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 | F1 Micro | Auc |
---|---|---|---|---|---|---|
0.9814 | 0.2632 | 10 | 0.7889 | 0.5222 | 0.5222 | 0.7777 |
0.5654 | 0.5263 | 20 | 0.5613 | 0.7204 | 0.7204 | 0.8755 |
0.4463 | 0.7895 | 30 | 0.5279 | 0.7738 | 0.7738 | 0.8951 |
0.4933 | 1.0526 | 40 | 0.6827 | 0.7303 | 0.7303 | 0.8942 |
0.3232 | 1.3158 | 50 | 0.5549 | 0.7993 | 0.7993 | 0.9079 |
0.3523 | 1.5789 | 60 | 0.5806 | 0.7755 | 0.7755 | 0.9047 |
0.2513 | 1.8421 | 70 | 0.5066 | 0.7870 | 0.7870 | 0.9079 |
0.1752 | 2.1053 | 80 | 0.4613 | 0.8191 | 0.8191 | 0.9058 |
0.0931 | 2.3684 | 90 | 0.5810 | 0.8207 | 0.8207 | 0.9037 |
0.0851 | 2.6316 | 100 | 0.5982 | 0.8224 | 0.8224 | 0.9055 |
0.0748 | 2.8947 | 110 | 0.5910 | 0.8166 | 0.8166 | 0.9075 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for BogdanTurbal/model_gpt2_medium_d_political_bias_hate_bias_ep_1_3_a_sqn_a_b_p_100_5_v_10
Base model
openai-community/gpt2-medium
Finetuned
this model