politicalbias-2label-c02_lib08-model

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

• Loss: 1.9989

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
3.4184	1.0	24	2.5696
2.399	2.0	48	2.1705
1.9579	3.0	72	2.0155
1.7103	4.0	96	1.9817
1.4601	5.0	120	1.9368
1.4049	6.0	144	1.9166
1.2141	7.0	168	1.8883
1.2901	8.0	192	1.8794
1.2296	9.0	216	1.9140
1.101	10.0	240	1.9274
0.9861	11.0	264	1.8927
0.8986	12.0	288	1.9040
0.9725	13.0	312	1.9189
0.9132	14.0	336	1.9123
0.9385	15.0	360	1.8960
0.8448	16.0	384	1.9573
0.8788	17.0	408	1.9421
0.8335	18.0	432	1.9645
0.8074	19.0	456	1.9654
0.8154	20.0	480	1.9659
0.8075	21.0	504	1.9653
0.686	22.0	528	1.9951
0.7481	23.0	552	1.9915
0.6736	24.0	576	1.9843
0.6759	25.0	600	1.9867
0.7015	26.0	624	1.9918
0.6593	27.0	648	1.9967
0.6904	28.0	672	2.0025
0.7149	29.0	696	1.9984
0.6115	30.0	720	1.9989

Framework versions

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