politicalbias-2label-c03_lib07-model

This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.9355

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: 2e-05
• train_batch_size: 8
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 10
• num_epochs: 30
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
3.5244	1.0	28	2.5668
2.2692	2.0	56	2.1853
2.0836	3.0	84	2.0283
1.7754	4.0	112	1.9467
1.5982	5.0	140	1.8749
1.4859	6.0	168	1.8285
1.3411	7.0	196	1.8039
1.297	8.0	224	1.8076
1.2421	9.0	252	1.7796
1.15	10.0	280	1.7774
1.1074	11.0	308	1.7635
1.047	12.0	336	1.8137
1.0428	13.0	364	1.7921
0.9604	14.0	392	1.8193
0.8682	15.0	420	1.8181
0.8917	16.0	448	1.8343
0.8894	17.0	476	1.8326
0.8294	18.0	504	1.8490
0.7678	19.0	532	1.8554
0.7505	20.0	560	1.8810
0.8025	21.0	588	1.8835
0.7605	22.0	616	1.8865
0.7012	23.0	644	1.9070
0.7109	24.0	672	1.9196
0.7366	25.0	700	1.9230
0.6955	26.0	728	1.9331
0.697	27.0	756	1.9366
0.7307	28.0	784	1.9354
0.6852	29.0	812	1.9360
0.7243	30.0	840	1.9355

Framework versions

• Transformers 4.46.3
• Pytorch 2.1.2+cu121
• Datasets 2.19.1
• Tokenizers 0.20.3