model_gpt2_medium_d_gender_bias_gender_bias_ep_1_3_a_sqn_a_b_p_100_5_v_11
This model is a fine-tuned version of openai-community/gpt2-medium on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6101
- Accuracy: 0.7977
- F1 Micro: 0.7977
- Auc: 0.8712
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: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Micro | Auc |
---|---|---|---|---|---|---|
0.9644 | 0.2632 | 10 | 0.5790 | 0.7224 | 0.7224 | 0.7750 |
0.8837 | 0.5263 | 20 | 0.8352 | 0.6572 | 0.6572 | 0.7773 |
0.6475 | 0.7895 | 30 | 0.8138 | 0.6104 | 0.6104 | 0.8098 |
0.9531 | 1.0526 | 40 | 0.6666 | 0.6279 | 0.6279 | 0.8220 |
0.5224 | 1.3158 | 50 | 0.6191 | 0.5811 | 0.5811 | 0.8281 |
0.5109 | 1.5789 | 60 | 0.4978 | 0.7726 | 0.7726 | 0.8422 |
0.3572 | 1.8421 | 70 | 0.4681 | 0.7793 | 0.7793 | 0.8522 |
0.373 | 2.1053 | 80 | 0.6220 | 0.7676 | 0.7676 | 0.8605 |
0.2852 | 2.3684 | 90 | 0.5094 | 0.7625 | 0.7625 | 0.8496 |
0.2492 | 2.6316 | 100 | 0.5516 | 0.7876 | 0.7876 | 0.8585 |
0.281 | 2.8947 | 110 | 0.4923 | 0.7851 | 0.7851 | 0.8639 |
0.1238 | 3.1579 | 120 | 0.5431 | 0.7876 | 0.7876 | 0.8662 |
0.1179 | 3.4211 | 130 | 0.6330 | 0.7960 | 0.7960 | 0.8688 |
0.0439 | 3.6842 | 140 | 0.5822 | 0.7893 | 0.7893 | 0.8691 |
0.0865 | 3.9474 | 150 | 0.6101 | 0.7977 | 0.7977 | 0.8712 |
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_gender_bias_gender_bias_ep_1_3_a_sqn_a_b_p_100_5_v_11
Base model
openai-community/gpt2-medium
Finetuned
this model