syncopation-transformer-spectral

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

• Loss: 0.0560

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss
0.0027	1.0	4355	0.0656
0.1182	2.0	8710	0.0776
0.0195	3.0	13065	0.0601
0.0502	4.0	17420	0.0657
0.0307	5.0	21775	0.0571
0.0	6.0	26130	0.0618
0.2242	7.0	30485	0.0675
0.0	8.0	34840	0.0628
0.0056	9.0	39195	0.0656
0.0008	10.0	43550	0.0572
0.0781	11.0	47905	0.0580
0.0007	12.0	52260	0.0566
0.023	13.0	56615	0.0574
0.0012	14.0	60970	0.0568
0.0083	15.0	65325	0.0653
0.0	16.0	69680	0.0571
0.0022	17.0	74035	0.0579
0.0007	18.0	78390	0.0566
0.0016	19.0	82745	0.0603
0.0	20.0	87100	0.0580
0.0015	21.0	91455	0.0564
0.003	22.0	95810	0.0598
0.0051	23.0	100165	0.0598
0.3308	24.0	104520	0.0580
0.0008	25.0	108875	0.0591
0.0009	26.0	113230	0.0586
0.0058	27.0	117585	0.0580
0.0004	28.0	121940	0.0574
0.0044	29.0	126295	0.0625
0.0	30.0	130650	0.0583
0.0	31.0	135005	0.0577
0.0073	32.0	139360	0.0604
0.0	33.0	143715	0.0581
0.0012	34.0	148070	0.0589
0.3239	35.0	152425	0.0565
0.0001	36.0	156780	0.0603
0.0069	37.0	161135	0.0576
0.0	38.0	165490	0.0612
0.0055	39.0	169845	0.0585
0.0013	40.0	174200	0.0564
0.003	41.0	178555	0.0570
0.0014	42.0	182910	0.0590
0.0029	43.0	187265	0.0594
0.0017	44.0	191620	0.0596
0.0009	45.0	195975	0.0570
0.0879	46.0	200330	0.0543
0.019	47.0	204685	0.0563
0.0002	48.0	209040	0.0573
0.0008	49.0	213395	0.0559
0.0001	50.0	217750	0.0560

Framework versions

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