lyric-gpt

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

• Loss: 5.4529

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: 8
• eval_batch_size: 8
• 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
3.406	1.0	92	3.1840
2.8788	2.0	184	3.2090
2.92	3.0	276	3.2549
2.8856	4.0	368	3.2943
2.5725	5.0	460	3.3856
2.3395	6.0	552	3.5080
2.167	7.0	644	3.6203
1.9773	8.0	736	3.7681
1.9391	9.0	828	3.8787
1.6115	10.0	920	4.0798
1.6445	11.0	1012	4.1552
1.528	12.0	1104	4.3184
1.3714	13.0	1196	4.4737
1.269	14.0	1288	4.5747
1.0994	15.0	1380	4.6625
1.0443	16.0	1472	4.8032
0.9456	17.0	1564	4.9048
0.8008	18.0	1656	4.9934
0.8819	19.0	1748	5.0594
0.8631	20.0	1840	5.1399
0.7939	21.0	1932	5.1844
0.717	22.0	2024	5.2256
0.8029	23.0	2116	5.2945
0.7064	24.0	2208	5.3211
0.6867	25.0	2300	5.3637
0.6398	26.0	2392	5.3977
0.5992	27.0	2484	5.4118
0.5986	28.0	2576	5.4357
0.5909	29.0	2668	5.4557
0.512	30.0	2760	5.4529

Framework versions

• Transformers 4.41.1
• Pytorch 2.3.0+cu121
• Datasets 2.19.1
• Tokenizers 0.19.1