learning_rate: 1e-06
train_batch_size: 256
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
0.5529	1.0	795	0.4975
0.4983	2.0	1590	0.4678
0.4798	3.0	2385	0.4578
0.4627	4.0	3180	0.4466
0.4588	5.0	3975	0.4402
0.4464	6.0	4770	0.4374
0.4416	7.0	5565	0.4325
0.4364	8.0	6360	0.4280
0.4341	9.0	7155	0.4276
0.4251	10.0	7950	0.4265
0.4204	11.0	8745	0.4225
0.4179	12.0	9540	0.4236
0.4158	13.0	10335	0.4199
0.4135	14.0	11130	0.4192
0.4097	15.0	11925	0.4173
0.4058	16.0	12720	0.4181
0.4064	17.0	13515	0.4158
0.4021	18.0	14310	0.4148
0.4006	19.0	15105	0.4143
0.3978	20.0	15900	0.4118
0.3971	21.0	16695	0.4149
0.3965	22.0	17490	0.4125
0.3939	23.0	18285	0.4113
0.393	24.0	19080	0.4141
0.3904	25.0	19875	0.4126
0.3963	26.0	20670	0.4113
0.3944	27.0	21465	0.4106
0.3918	28.0	22260	0.4121
0.3896	29.0	23055	0.4115
0.3905	30.0	23850	0.4115

mhr2004/roberta-base-atomic.train.no.negation.true.irrelevant1e-06-64

roberta-base-atomic.train.no.negation.true.irrelevant1e-06-64