model_gpt2_medium_d_hate_bias_hate_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: 0.8683
- Accuracy: 0.8289
- F1 Micro: 0.8289
- Auc: 0.9128
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 |
---|---|---|---|---|---|---|
2.7943 | 0.2632 | 10 | 0.8383 | 0.5584 | 0.5584 | 0.6700 |
0.8548 | 0.5263 | 20 | 0.6880 | 0.6645 | 0.6645 | 0.8221 |
0.6474 | 0.7895 | 30 | 0.6203 | 0.7459 | 0.7459 | 0.8654 |
0.5014 | 1.0526 | 40 | 0.4418 | 0.7977 | 0.7977 | 0.8901 |
0.3187 | 1.3158 | 50 | 0.4189 | 0.8133 | 0.8133 | 0.9005 |
0.2558 | 1.5789 | 60 | 0.4661 | 0.8002 | 0.8002 | 0.8976 |
0.3011 | 1.8421 | 70 | 0.4252 | 0.8183 | 0.8183 | 0.9019 |
0.1769 | 2.1053 | 80 | 0.5639 | 0.8067 | 0.8067 | 0.9017 |
0.1421 | 2.3684 | 90 | 0.6957 | 0.8002 | 0.8002 | 0.8998 |
0.1403 | 2.6316 | 100 | 0.7930 | 0.8133 | 0.8133 | 0.9043 |
0.0684 | 2.8947 | 110 | 0.6532 | 0.8273 | 0.8273 | 0.9103 |
0.0109 | 3.1579 | 120 | 0.8349 | 0.8257 | 0.8257 | 0.9110 |
0.0012 | 3.4211 | 130 | 0.8420 | 0.8273 | 0.8273 | 0.9119 |
0.0366 | 3.6842 | 140 | 0.8717 | 0.8265 | 0.8265 | 0.9128 |
0.0149 | 3.9474 | 150 | 0.8683 | 0.8289 | 0.8289 | 0.9128 |
Framework versions
- Transformers 4.44.0
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 2
Model tree for BogdanTurbal/model_gpt2_medium_d_hate_bias_hate_bias_ep_1_3_a_sqn_a_b_p_100_5_v_11
Base model
openai-community/gpt2-medium
Finetuned
this model