syncopation-transformer-combined

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

• Loss: 0.0537

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: 5e-05
• train_batch_size: 5
• eval_batch_size: 8
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss
0.1919	1.0	4350	0.0718
0.0072	2.0	8700	0.0734
0.0009	3.0	13050	0.0603
0.049	4.0	17400	0.0770
0.0496	5.0	21750	0.0554
0.001	6.0	26100	0.0565
0.0027	7.0	30450	0.0561
0.0041	8.0	34800	0.0607
0.0273	9.0	39150	0.0565
0.0344	10.0	43500	0.0580
0.0246	11.0	47850	0.0557
0.0187	12.0	52200	0.0624
0.0828	13.0	56550	0.0523
0.059	14.0	60900	0.0537
0.2687	15.0	65250	0.0561
0.0593	16.0	69600	0.0565
0.0015	17.0	73950	0.0541
0.0023	18.0	78300	0.0558
0.0001	19.0	82650	0.0532
0.0026	20.0	87000	0.0547
0.0339	21.0	91350	0.0543
0.001	22.0	95700	0.0567
0.0553	23.0	100050	0.0545
0.0038	24.0	104400	0.0536
0.012	25.0	108750	0.0537

Framework versions

• Transformers 4.51.3
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1