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	8	5.0037	0.0485	5.0018	2.2365
No log	2.0	16	3.2071	-0.0202	3.2052	1.7903
No log	3.0	24	1.2580	0.0211	1.2568	1.1211
No log	4.0	32	1.3589	0.0211	1.3571	1.1650
No log	5.0	40	1.5075	-0.0019	1.5055	1.2270
No log	6.0	48	1.5018	0.0194	1.5000	1.2247
No log	7.0	56	1.2929	0.1056	1.2912	1.1363
No log	8.0	64	2.3355	0.0409	2.3326	1.5273
No log	9.0	72	3.0333	-0.0230	3.0298	1.7406
No log	10.0	80	2.0201	0.0511	2.0170	1.4202
No log	11.0	88	1.6142	0.1057	1.6113	1.2694
No log	12.0	96	1.3840	0.1475	1.3813	1.1753
No log	13.0	104	2.0175	0.0364	2.0139	1.4191
No log	14.0	112	2.2639	0.0330	2.2604	1.5035
No log	15.0	120	1.4920	0.1196	1.4891	1.2203
No log	16.0	128	1.2201	0.1681	1.2177	1.1035
No log	17.0	136	1.1455	0.1670	1.1431	1.0691
No log	18.0	144	1.0960	0.2005	1.0937	1.0458
No log	19.0	152	1.1589	0.1623	1.1563	1.0753
No log	20.0	160	1.1729	0.1651	1.1703	1.0818
No log	21.0	168	1.2221	0.1695	1.2193	1.1042
No log	22.0	176	1.3089	0.1395	1.3062	1.1429
No log	23.0	184	2.8080	0.0252	2.8045	1.6747
No log	24.0	192	1.3671	0.1105	1.3642	1.1680
No log	25.0	200	1.2377	0.1215	1.2352	1.1114
No log	26.0	208	1.0874	0.1603	1.0851	1.0417
No log	27.0	216	1.6377	0.0956	1.6347	1.2786
No log	28.0	224	1.7887	0.0664	1.7858	1.3363
No log	29.0	232	1.6206	0.1172	1.6177	1.2719
No log	30.0	240	1.3438	0.1301	1.3411	1.1581
No log	31.0	248	1.3834	0.1174	1.3806	1.1750
No log	32.0	256	1.4161	0.1232	1.4133	1.1888
No log	33.0	264	1.3562	0.1598	1.3535	1.1634

genki10/BERT_AugV8_k10_task1_organization_sp040_lw040_fold1

BERT_AugV8_k10_task1_organization_sp040_lw040_fold1