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	4	9.0858	0.0	9.0842	3.0140
No log	2.0	8	6.7977	0.0	6.7962	2.6069
No log	3.0	12	4.4133	0.0076	4.4116	2.1004
No log	4.0	16	2.9030	-0.0030	2.9022	1.7036
No log	5.0	20	1.6957	0.0329	1.6950	1.3019
No log	6.0	24	1.9975	0.0671	1.9968	1.4131
No log	7.0	28	1.2303	0.0391	1.2300	1.1091
No log	8.0	32	1.3231	0.0816	1.3231	1.1502
No log	9.0	36	0.8929	0.3517	0.8932	0.9451
No log	10.0	40	0.8282	0.3376	0.8285	0.9102
No log	11.0	44	0.8643	0.3374	0.8650	0.9300
No log	12.0	48	0.6828	0.4096	0.6833	0.8266
No log	13.0	52	0.9951	0.3240	0.9957	0.9979
No log	14.0	56	0.7410	0.3749	0.7420	0.8614
No log	15.0	60	1.6599	0.1334	1.6604	1.2886
No log	16.0	64	0.8431	0.3634	0.8441	0.9188
No log	17.0	68	1.8235	0.1689	1.8241	1.3506
No log	18.0	72	1.2911	0.2213	1.2919	1.1366
No log	19.0	76	1.2140	0.2492	1.2150	1.1023
No log	20.0	80	2.1440	0.1343	2.1445	1.4644
No log	21.0	84	1.6022	0.1884	1.6031	1.2661
No log	22.0	88	1.2860	0.2167	1.2870	1.1345
No log	23.0	92	2.2653	0.1096	2.2656	1.5052
No log	24.0	96	1.2731	0.2180	1.2738	1.1286
No log	25.0	100	1.6343	0.1787	1.6349	1.2786
No log	26.0	104	1.7583	0.0987	1.7590	1.3263
No log	27.0	108	1.7531	0.1686	1.7538	1.3243

genki10/BERT_AugV8_k5_task1_organization_sp060_lw040_fold3

BERT_AugV8_k5_task1_organization_sp060_lw040_fold3