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	3	9.6457	0.0018	9.6457	3.1058
No log	2.0	6	5.6775	0.0456	5.6775	2.3827
No log	3.0	9	4.3274	0.0079	4.3274	2.0802
No log	4.0	12	3.0328	0.0040	3.0328	1.7415
No log	5.0	15	2.1165	0.1280	2.1165	1.4548
No log	6.0	18	1.5648	0.0420	1.5648	1.2509
No log	7.0	21	1.2350	0.0316	1.2350	1.1113
No log	8.0	24	1.1836	0.0420	1.1836	1.0879
No log	9.0	27	1.4158	0.0682	1.4158	1.1899
No log	10.0	30	0.8569	0.2819	0.8569	0.9257
No log	11.0	33	1.2077	0.0443	1.2077	1.0990
No log	12.0	36	0.8765	0.3568	0.8765	0.9362
No log	13.0	39	0.8106	0.3746	0.8106	0.9003
No log	14.0	42	0.9535	0.2331	0.9535	0.9765
No log	15.0	45	0.6859	0.3802	0.6859	0.8282
No log	16.0	48	0.8905	0.3256	0.8905	0.9437
No log	17.0	51	0.8292	0.3451	0.8292	0.9106
No log	18.0	54	0.8833	0.3852	0.8833	0.9399
No log	19.0	57	1.0731	0.4033	1.0731	1.0359
No log	20.0	60	0.7841	0.4924	0.7841	0.8855
No log	21.0	63	1.3109	0.3446	1.3109	1.1450
No log	22.0	66	0.8184	0.4624	0.8184	0.9047
No log	23.0	69	0.9968	0.3546	0.9968	0.9984
No log	24.0	72	0.9281	0.3628	0.9281	0.9634
No log	25.0	75	0.8949	0.3956	0.8949	0.9460
No log	26.0	78	1.2873	0.3053	1.2873	1.1346
No log	27.0	81	0.7669	0.4422	0.7669	0.8757
No log	28.0	84	1.1956	0.3254	1.1956	1.0934
No log	29.0	87	1.1042	0.3809	1.1042	1.0508
No log	30.0	90	0.7421	0.4309	0.7421	0.8614
No log	31.0	93	1.2770	0.3043	1.2770	1.1300
No log	32.0	96	1.2581	0.3198	1.2581	1.1216
No log	33.0	99	0.6902	0.4574	0.6902	0.8308
No log	34.0	102	0.7767	0.4344	0.7767	0.8813
No log	35.0	105	1.2160	0.3465	1.2160	1.1027

genki10/BERT_AugV8_k3_task1_organization_sp010_lw060_fold4

BERT_AugV8_k3_task1_organization_sp010_lw060_fold4