learning_rate: 1e-06
train_batch_size: 512
eval_batch_size: 1024
seed: 42
optimizer: Use 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: 30

Training Loss	Epoch	Step	Validation Loss
0.6351	1.0	576	0.4929
0.4755	2.0	1152	0.4313
0.4406	3.0	1728	0.4136
0.4208	4.0	2304	0.4072
0.4089	5.0	2880	0.3982
0.3989	6.0	3456	0.3869
0.3913	7.0	4032	0.3837
0.3836	8.0	4608	0.3793
0.3766	9.0	5184	0.3793
0.3715	10.0	5760	0.3754
0.3669	11.0	6336	0.3726
0.3653	12.0	6912	0.3681
0.3594	13.0	7488	0.3697
0.3534	14.0	8064	0.3725
0.353	15.0	8640	0.3678
0.3509	16.0	9216	0.3651
0.3474	17.0	9792	0.3635
0.3467	18.0	10368	0.3676
0.3428	19.0	10944	0.3631
0.3408	20.0	11520	0.3668
0.3373	21.0	12096	0.3645
0.3397	22.0	12672	0.3645

mhr2004/roberta-largemhr2004-atomic.anion.train.no1e-06-128

roberta-largemhr2004-atomic.anion.train.no1e-06-128