model_gpt2_medium_d_hate_bias_hate_bias_ep_1_2_a_sqn_a_b_p_100_5_v_12

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: 0.4078
• Accuracy: 0.8191
• F1 Micro: 0.8191
• Auc: 0.9066

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: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Micro	Auc
2.7961	0.2632	10	0.8537	0.5526	0.5526	0.6776
0.8907	0.5263	20	0.7972	0.6225	0.6225	0.8131
0.685	0.7895	30	0.5160	0.7722	0.7722	0.8594
0.6299	1.0526	40	0.5377	0.7475	0.7475	0.8868
0.3763	1.3158	50	0.5010	0.7714	0.7714	0.8987
0.3101	1.5789	60	0.3968	0.8232	0.8232	0.9037
0.2572	1.8421	70	0.4078	0.8191	0.8191	0.9066

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1