model_gpt2_medium_d_political_bias_political_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: 1.2735
• Accuracy: 0.7053
• F1 Micro: 0.7053
• Auc: 0.7807

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
1.1051	0.2703	10	0.6701	0.5945	0.5945	0.6855
0.6657	0.5405	20	0.6342	0.6426	0.6426	0.7489
0.6544	0.8108	30	0.6950	0.6469	0.6469	0.7466
0.6954	1.0811	40	0.5734	0.6847	0.6847	0.7750
0.4412	1.3514	50	0.6375	0.6804	0.6804	0.7636
0.5728	1.6216	60	0.6858	0.6675	0.6675	0.7579
0.5021	1.8919	70	0.6092	0.6701	0.6701	0.7617
0.3721	2.1622	80	0.6150	0.6967	0.6967	0.7791
0.2674	2.4324	90	0.7439	0.6701	0.6701	0.7544
0.2516	2.7027	100	0.7179	0.7027	0.7027	0.7769
0.3177	2.9730	110	0.6977	0.7148	0.7148	0.7880
0.0615	3.2432	120	0.8305	0.6993	0.6993	0.7870
0.0492	3.5135	130	1.0983	0.7088	0.7088	0.7854
0.0793	3.7838	140	1.2735	0.7053	0.7053	0.7807

Framework versions

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