ft-GPT2-with-lyrics

This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.1112

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss
2.0058	1.0	71	1.5293
1.5797	2.0	142	1.3814
1.4549	3.0	213	1.3093
1.3837	4.0	284	1.2661
1.3354	5.0	355	1.2328
1.2976	6.0	426	1.2142
1.2678	7.0	497	1.1973
1.2401	8.0	568	1.1825
1.2168	9.0	639	1.1737
1.1971	10.0	710	1.1604
1.1797	11.0	781	1.1529
1.1671	12.0	852	1.1451
1.1517	13.0	923	1.1395
1.1389	14.0	994	1.1357
1.1267	15.0	1065	1.1325
1.1189	16.0	1136	1.1278
1.1076	17.0	1207	1.1246
1.1019	18.0	1278	1.1201
1.0925	19.0	1349	1.1201
1.0885	20.0	1420	1.1159
1.0806	21.0	1491	1.1165
1.0785	22.0	1562	1.1178
1.0703	23.0	1633	1.1171
1.0674	24.0	1704	1.1130
1.0604	25.0	1775	1.1132
1.062	26.0	1846	1.1120
1.0545	27.0	1917	1.1123
1.0534	28.0	1988	1.1106
1.0528	29.0	2059	1.1115
1.0516	30.0	2130	1.1112

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.2
• Datasets 2.15.0
• Tokenizers 0.15.1