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	12.8893	0.0	12.8871	3.5899
No log	2.0	6	11.1586	-0.0030	11.1568	3.3402
No log	3.0	9	7.7772	0.0	7.7754	2.7884
No log	4.0	12	5.5188	0.0171	5.5174	2.3489
No log	5.0	15	4.0776	0.0	4.0766	2.0191
No log	6.0	18	2.6626	0.0164	2.6617	1.6315
No log	7.0	21	1.5513	0.0463	1.5507	1.2453
No log	8.0	24	1.1454	0.0202	1.1450	1.0700
No log	9.0	27	1.4457	0.0574	1.4452	1.2022
No log	10.0	30	2.0833	0.1705	2.0828	1.4432
No log	11.0	33	1.1171	0.1022	1.1171	1.0569
No log	12.0	36	1.5906	0.1391	1.5907	1.2612
No log	13.0	39	2.3794	0.0867	2.3795	1.5426
No log	14.0	42	1.1456	0.2435	1.1460	1.0705
No log	15.0	45	3.3196	0.0306	3.3196	1.8220
No log	16.0	48	2.6247	0.0721	2.6248	1.6201
No log	17.0	51	1.2032	0.2195	1.2035	1.0971
No log	18.0	54	2.3020	0.0806	2.3022	1.5173
No log	19.0	57	1.8129	0.0979	1.8132	1.3466
No log	20.0	60	3.2365	0.0047	3.2366	1.7991
No log	21.0	63	2.0586	0.0779	2.0587	1.4348
No log	22.0	66	3.2944	0.0026	3.2943	1.8150
No log	23.0	69	1.9447	0.1384	1.9449	1.3946
No log	24.0	72	2.4175	0.0924	2.4178	1.5549
No log	25.0	75	2.1504	0.1158	2.1507	1.4665
No log	26.0	78	1.8290	0.1324	1.8294	1.3525
No log	27.0	81	3.1617	0.0442	3.1618	1.7781
No log	28.0	84	1.7230	0.1482	1.7233	1.3127
No log	29.0	87	2.1873	0.1069	2.1875	1.4790

genki10/BERT_AugV8_k3_task1_organization_sp060_lw010_fold3

BERT_AugV8_k3_task1_organization_sp060_lw010_fold3