syncopation-transformer-metric-disentagled

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

• Loss: 0.0888

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
0.2002	1.0	4350	0.1469
0.0081	2.0	8700	0.1376
0.1583	3.0	13050	0.1229
0.13	4.0	17400	0.1156
0.1405	5.0	21750	0.1053
0.0125	6.0	26100	0.1015
0.0147	7.0	30450	0.0969
0.0023	8.0	34800	0.0973
0.0914	9.0	39150	0.0944
0.0287	10.0	43500	0.0958
0.0355	11.0	47850	0.0943
0.029	12.0	52200	0.0972
0.0927	13.0	56550	0.0910
0.0487	14.0	60900	0.0958
0.5498	15.0	65250	0.0974
0.0859	16.0	69600	0.0990
0.0321	17.0	73950	0.0944
0.0314	18.0	78300	0.0932
0.0017	19.0	82650	0.0946
0.0043	20.0	87000	0.0919
0.0617	21.0	91350	0.0942
0.0026	22.0	95700	0.0912
0.1839	23.0	100050	0.0906
0.0059	24.0	104400	0.0903
0.0469	25.0	108750	0.0964
0.0632	26.0	113100	0.0935
0.3662	27.0	117450	0.0911
0.0097	28.0	121800	0.0929
0.0441	29.0	126150	0.0903
0.0297	30.0	130500	0.0904
0.0791	31.0	134850	0.0919
0.0286	32.0	139200	0.0932
0.4319	33.0	143550	0.0894
0.1246	34.0	147900	0.0902
0.0876	35.0	152250	0.0882
0.0029	36.0	156600	0.0907
0.0065	37.0	160950	0.0907
0.027	38.0	165300	0.0905
0.0006	39.0	169650	0.0895
0.0024	40.0	174000	0.0881
0.0646	41.0	178350	0.0886
0.0041	42.0	182700	0.0886
0.2318	43.0	187050	0.0890
0.1015	44.0	191400	0.0889
0.0168	45.0	195750	0.0880
0.012	46.0	200100	0.0900
0.4302	47.0	204450	0.0880
0.0059	48.0	208800	0.0889
0.0298	49.0	213150	0.0883
0.0221	50.0	217500	0.0888

Framework versions

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