learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
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: 40

Training Loss	Epoch	Step	Validation Loss	Gen Len
No log	1.0	57	0.4015	20.0
No log	2.0	114	0.3978	20.0
No log	3.0	171	0.3930	20.0
No log	4.0	228	0.3895	20.0
No log	5.0	285	0.3871	20.0
No log	6.0	342	0.3858	20.0
No log	7.0	399	0.3805	20.0
No log	8.0	456	0.3795	20.0
0.443	9.0	513	0.3781	20.0
0.443	10.0	570	0.3762	20.0
0.443	11.0	627	0.3745	20.0
0.443	12.0	684	0.3724	20.0
0.443	13.0	741	0.3715	20.0
0.443	14.0	798	0.3696	20.0
0.443	15.0	855	0.3695	20.0
0.443	16.0	912	0.3676	20.0
0.443	17.0	969	0.3671	20.0
0.4172	18.0	1026	0.3657	20.0
0.4172	19.0	1083	0.3649	20.0
0.4172	20.0	1140	0.3641	20.0
0.4172	21.0	1197	0.3641	20.0
0.4172	22.0	1254	0.3643	20.0
0.4172	23.0	1311	0.3621	20.0
0.4172	24.0	1368	0.3616	20.0
0.4172	25.0	1425	0.3614	20.0
0.4172	26.0	1482	0.3612	20.0
0.406	27.0	1539	0.3603	20.0
0.406	28.0	1596	0.3606	20.0
0.406	29.0	1653	0.3600	20.0
0.406	30.0	1710	0.3599	20.0
0.406	31.0	1767	0.3592	20.0
0.406	32.0	1824	0.3588	20.0
0.406	33.0	1881	0.3582	20.0
0.406	34.0	1938	0.3585	20.0
0.406	35.0	1995	0.3583	20.0
0.401	36.0	2052	0.3580	20.0
0.401	37.0	2109	0.3578	20.0
0.401	38.0	2166	0.3579	20.0
0.401	39.0	2223	0.3578	20.0
0.401	40.0	2280	0.3579	20.0

JannikAhlers/groove_midi

groove_midi