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	11.8084	-0.0151	11.8065	3.4361
No log	2.0	4	10.0004	0.0	9.9987	3.1621
No log	3.0	6	8.4013	0.0	8.3997	2.8982
No log	4.0	8	6.4821	0.0016	6.4807	2.5457
No log	5.0	10	4.7334	0.0144	4.7322	2.1754
No log	6.0	12	3.6883	0.0049	3.6871	1.9202
No log	7.0	14	2.9701	0.0020	2.9693	1.7232
No log	8.0	16	2.0942	0.0502	2.0934	1.4469
No log	9.0	18	1.6326	0.0371	1.6319	1.2774
No log	10.0	20	1.3283	0.0229	1.3278	1.1523
No log	11.0	22	1.3516	0.0505	1.3511	1.1624
No log	12.0	24	1.4246	0.0717	1.4242	1.1934
No log	13.0	26	1.2874	0.0796	1.2870	1.1344
No log	14.0	28	1.1747	0.0928	1.1743	1.0837
No log	15.0	30	1.6122	0.1603	1.6121	1.2697
No log	16.0	32	2.1692	0.1563	2.1693	1.4728
No log	17.0	34	1.4053	0.2019	1.4056	1.1856
No log	18.0	36	1.1594	0.3007	1.1597	1.0769
No log	19.0	38	2.5930	0.1122	2.5932	1.6103
No log	20.0	40	2.8942	0.1006	2.8943	1.7013
No log	21.0	42	1.2033	0.2844	1.2036	1.0971
No log	22.0	44	0.9865	0.3097	0.9867	0.9933
No log	23.0	46	2.2788	0.1045	2.2787	1.5095
No log	24.0	48	2.5690	0.1063	2.5687	1.6027
No log	25.0	50	1.2065	0.2581	1.2066	1.0984
No log	26.0	52	1.0646	0.2867	1.0647	1.0318
No log	27.0	54	2.3675	0.0985	2.3670	1.5385
No log	28.0	56	2.6359	0.0812	2.6351	1.6233
No log	29.0	58	1.2336	0.1992	1.2335	1.1106
No log	30.0	60	1.2238	0.2136	1.2236	1.1062
No log	31.0	62	2.0804	0.1137	2.0798	1.4422
No log	32.0	64	1.4056	0.1772	1.4053	1.1855
No log	33.0	66	1.3607	0.1897	1.3605	1.1664
No log	34.0	68	2.2211	0.1153	2.2208	1.4902
No log	35.0	70	1.7608	0.1378	1.7609	1.3270
No log	36.0	72	1.0773	0.2854	1.0777	1.0381
No log	37.0	74	1.5221	0.2049	1.5224	1.2339

genki10/Trial3BERT_AugV8_k1_task1_organization_sp020_lw060_fold3

Trial3BERT_AugV8_k1_task1_organization_sp020_lw060_fold3