politicalbias-2label-c06_lib04-model

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

• Loss: 1.9510

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
2.7117	1.0	43	2.5012
2.1744	2.0	86	2.1418
1.844	3.0	129	1.9773
1.7269	4.0	172	1.8822
1.6296	5.0	215	1.8444
1.4019	6.0	258	1.8117
1.3364	7.0	301	1.7717
1.2672	8.0	344	1.7761
1.2142	9.0	387	1.7653
1.2244	10.0	430	1.7933
1.013	11.0	473	1.8102
1.0625	12.0	516	1.8175
1.0465	13.0	559	1.8040
0.9684	14.0	602	1.8050
0.878	15.0	645	1.8497
0.8575	16.0	688	1.8653
0.8921	17.0	731	1.8690
0.8228	18.0	774	1.8827
0.8195	19.0	817	1.8867
0.8023	20.0	860	1.8986
0.8454	21.0	903	1.9080
0.7601	22.0	946	1.9123
0.7895	23.0	989	1.9237
0.7638	24.0	1032	1.9318
0.6976	25.0	1075	1.9352
0.7686	26.0	1118	1.9414
0.7517	27.0	1161	1.9522
0.6651	28.0	1204	1.9467
0.7287	29.0	1247	1.9515
0.7296	30.0	1290	1.9510

Framework versions

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