model_phi_2_d_political_bias_gender_bias_ep_2_6_a_sqn_a_b_p_100_5_v_17

This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6606
• Accuracy: 0.7926
• F1 Micro: 0.7926
• Auc: 0.8779

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: 0.0002
• train_batch_size: 16
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Micro	Auc
0.5586	1.0	38	0.5896	0.6856	0.6856	0.7590
0.3323	2.0	76	0.4793	0.7751	0.7751	0.8590
0.3061	3.0	114	0.4818	0.7734	0.7734	0.8673
0.0758	4.0	152	0.7178	0.7818	0.7818	0.8571
0.0272	5.0	190	0.6673	0.7868	0.7868	0.8750
0.0447	6.0	228	0.6606	0.7926	0.7926	0.8779

Framework versions

• PEFT 0.11.1
• Transformers 4.44.0
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1