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	8.1676	0.0	8.1676	2.8579
No log	2.0	6	5.0961	0.0109	5.0961	2.2575
No log	3.0	9	3.3772	0.0040	3.3772	1.8377
No log	4.0	12	2.3051	0.0968	2.3051	1.5183
No log	5.0	15	1.5809	0.0316	1.5809	1.2573
No log	6.0	18	1.1181	0.0212	1.1181	1.0574
No log	7.0	21	1.3419	0.0212	1.3419	1.1584
No log	8.0	24	1.0849	0.0212	1.0849	1.0416
No log	9.0	27	0.8878	0.1167	0.8878	0.9422
No log	10.0	30	1.1003	0.0710	1.1003	1.0490
No log	11.0	33	1.2634	0.1369	1.2634	1.1240
No log	12.0	36	1.0065	0.2035	1.0065	1.0033
No log	13.0	39	1.3067	0.1891	1.3067	1.1431
No log	14.0	42	0.9691	0.2744	0.9691	0.9844
No log	15.0	45	1.0201	0.3096	1.0201	1.0100
No log	16.0	48	0.9781	0.3856	0.9781	0.9890
No log	17.0	51	1.4560	0.2828	1.4560	1.2066
No log	18.0	54	0.8979	0.4571	0.8979	0.9476
No log	19.0	57	1.9622	0.2283	1.9622	1.4008
No log	20.0	60	0.8619	0.4669	0.8619	0.9284
No log	21.0	63	2.7354	0.1493	2.7354	1.6539
No log	22.0	66	2.0018	0.2278	2.0018	1.4148
No log	23.0	69	0.9274	0.4521	0.9274	0.9630
No log	24.0	72	2.6778	0.1401	2.6778	1.6364
No log	25.0	75	1.1096	0.3673	1.1096	1.0534
No log	26.0	78	1.3510	0.2708	1.3510	1.1623
No log	27.0	81	1.2302	0.2968	1.2302	1.1091
No log	28.0	84	1.4242	0.2523	1.4242	1.1934
No log	29.0	87	1.1854	0.2630	1.1854	1.0887
No log	30.0	90	1.4626	0.2386	1.4626	1.2094
No log	31.0	93	1.5074	0.2159	1.5074	1.2278
No log	32.0	96	1.3520	0.2561	1.3520	1.1628
No log	33.0	99	1.3053	0.2570	1.3053	1.1425
No log	34.0	102	1.5559	0.2308	1.5559	1.2473
No log	35.0	105	1.3099	0.2861	1.3099	1.1445

genki10/Trial3BERT_AugV8_k3_task1_organization_sp050_lw010_fold4

Trial3BERT_AugV8_k3_task1_organization_sp050_lw010_fold4