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	10.1069	0.0	10.1049	3.1788
No log	2.0	8	7.3883	0.0	7.3868	2.7179
No log	3.0	12	4.9368	0.0076	4.9357	2.2216
No log	4.0	16	2.7428	0.0	2.7421	1.6559
No log	5.0	20	1.5454	0.0202	1.5446	1.2428
No log	6.0	24	1.3513	0.0	1.3505	1.1621
No log	7.0	28	1.0897	0.0717	1.0899	1.0440
No log	8.0	32	0.9567	0.1980	0.9575	0.9785
No log	9.0	36	0.7941	0.1985	0.7945	0.8913
No log	10.0	40	1.0665	0.0036	1.0665	1.0327
No log	11.0	44	0.8777	0.1667	0.8785	0.9373
No log	12.0	48	1.4244	-0.0351	1.4252	1.1938
No log	13.0	52	0.8806	0.1948	0.8814	0.9388
No log	14.0	56	0.8391	0.2319	0.8398	0.9164
No log	15.0	60	1.5255	-0.0054	1.5260	1.2353
No log	16.0	64	0.8484	0.2699	0.8490	0.9214
No log	17.0	68	0.8613	0.2826	0.8618	0.9283
No log	18.0	72	0.8850	0.3354	0.8855	0.9410
No log	19.0	76	0.8248	0.4333	0.8253	0.9085
No log	20.0	80	1.5254	0.1074	1.5260	1.2353
No log	21.0	84	0.7770	0.4968	0.7773	0.8817
No log	22.0	88	1.8201	0.0108	1.8203	1.3492
No log	23.0	92	1.2639	0.2212	1.2645	1.1245
No log	24.0	96	0.8043	0.4589	0.8046	0.8970
No log	25.0	100	1.4249	0.1400	1.4253	1.1939
No log	26.0	104	0.8372	0.4245	0.8376	0.9152
No log	27.0	108	1.2231	0.2568	1.2239	1.1063
No log	28.0	112	0.8965	0.4085	0.8972	0.9472
No log	29.0	116	1.0452	0.2848	1.0458	1.0226
No log	30.0	120	1.3751	0.1494	1.3758	1.1729
No log	31.0	124	1.0711	0.3293	1.0717	1.0352
No log	32.0	128	1.2707	0.2094	1.2711	1.1274
No log	33.0	132	1.0629	0.3424	1.0636	1.0313
No log	34.0	136	1.1774	0.2237	1.1781	1.0854
No log	35.0	140	1.1181	0.3084	1.1189	1.0578
No log	36.0	144	1.4964	0.1184	1.4975	1.2237

genki10/Trial3BERT_AugV8_k5_task1_organization_sp060_lw010_fold3

Trial3BERT_AugV8_k5_task1_organization_sp060_lw010_fold3