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	7.7037	0.0	7.7037	2.7756
No log	2.0	8	5.7928	0.0182	5.7928	2.4068
No log	3.0	12	4.0787	0.0039	4.0787	2.0196
No log	4.0	16	2.5044	0.0447	2.5044	1.5825
No log	5.0	20	1.5197	0.0316	1.5197	1.2328
No log	6.0	24	1.0422	0.0212	1.0422	1.0209
No log	7.0	28	0.9758	0.0382	0.9758	0.9878
No log	8.0	32	0.7540	0.3896	0.7540	0.8683
No log	9.0	36	1.4893	0.1246	1.4893	1.2204
No log	10.0	40	0.6754	0.4896	0.6754	0.8219
No log	11.0	44	1.0386	0.2286	1.0386	1.0191
No log	12.0	48	0.6242	0.4734	0.6242	0.7900
No log	13.0	52	0.6998	0.3925	0.6998	0.8366
No log	14.0	56	0.6626	0.4063	0.6626	0.8140
No log	15.0	60	0.6039	0.4407	0.6039	0.7771
No log	16.0	64	0.7498	0.3635	0.7498	0.8659
No log	17.0	68	0.8428	0.3539	0.8428	0.9180
No log	18.0	72	0.6660	0.5021	0.6660	0.8161
No log	19.0	76	0.9682	0.3104	0.9682	0.9840
No log	20.0	80	1.1654	0.2589	1.1654	1.0795
No log	21.0	84	0.7339	0.4287	0.7339	0.8567
No log	22.0	88	1.1939	0.2802	1.1939	1.0926
No log	23.0	92	1.1354	0.2609	1.1354	1.0655
No log	24.0	96	0.7952	0.3844	0.7952	0.8917
No log	25.0	100	0.7622	0.4067	0.7622	0.8730
No log	26.0	104	1.7104	0.1249	1.7104	1.3078
No log	27.0	108	0.9195	0.2963	0.9195	0.9589
No log	28.0	112	0.8138	0.4027	0.8138	0.9021
No log	29.0	116	0.9108	0.2970	0.9108	0.9544
No log	30.0	120	1.1203	0.2497	1.1203	1.0585
No log	31.0	124	0.7275	0.4101	0.7275	0.8529
No log	32.0	128	1.4482	0.2725	1.4482	1.2034
No log	33.0	132	0.6581	0.4876	0.6581	0.8112

genki10/Trial3BERT_AugV8_k5_task1_organization_sp010_lw030_fold0

Trial3BERT_AugV8_k5_task1_organization_sp010_lw030_fold0