learning_rate: 2e-05
train_batch_size: 64
eval_batch_size: 64
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: 150

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	2	7.5283	0.0018	7.5283	2.7438
No log	2.0	4	6.5425	0.0018	6.5425	2.5578
No log	3.0	6	5.6293	0.0083	5.6293	2.3726
No log	4.0	8	4.7951	0.0079	4.7951	2.1898
No log	5.0	10	4.1132	0.0040	4.1132	2.0281
No log	6.0	12	3.2959	0.0040	3.2959	1.8155
No log	7.0	14	2.5217	0.0189	2.5217	1.5880
No log	8.0	16	1.9036	0.0484	1.9036	1.3797
No log	9.0	18	1.5189	0.0316	1.5189	1.2325
No log	10.0	20	1.2294	0.0213	1.2294	1.1088
No log	11.0	22	1.0365	0.0316	1.0365	1.0181
No log	12.0	24	1.0093	0.0407	1.0093	1.0047
No log	13.0	26	0.8400	0.2431	0.8400	0.9165
No log	14.0	28	0.9086	0.2672	0.9086	0.9532
No log	15.0	30	0.6757	0.4940	0.6757	0.8220
No log	16.0	32	0.8145	0.4607	0.8145	0.9025
No log	17.0	34	1.7485	0.2294	1.7485	1.3223
No log	18.0	36	1.6231	0.2445	1.6231	1.2740
No log	19.0	38	1.3258	0.2934	1.3258	1.1514
No log	20.0	40	1.0978	0.3512	1.0978	1.0478
No log	21.0	42	1.1588	0.3419	1.1588	1.0765
No log	22.0	44	1.0123	0.3873	1.0123	1.0061
No log	23.0	46	0.8562	0.4707	0.8562	0.9253
No log	24.0	48	1.4548	0.2827	1.4548	1.2061
No log	25.0	50	0.9478	0.4410	0.9478	0.9735
No log	26.0	52	0.6630	0.4707	0.6630	0.8143
No log	27.0	54	0.6587	0.4832	0.6587	0.8116
No log	28.0	56	1.2249	0.3523	1.2249	1.1068
No log	29.0	58	1.7318	0.2350	1.7318	1.3160
No log	30.0	60	0.7788	0.4626	0.7788	0.8825

genki10/BERT_AugV8_k1_task1_organization_sp020_lw030_fold4

BERT_AugV8_k1_task1_organization_sp020_lw030_fold4