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	7.7259	0.0	7.7264	2.7796
No log	2.0	8	4.4226	0.0078	4.4231	2.1031
No log	3.0	12	2.7422	0.0	2.7426	1.6561
No log	4.0	16	1.6858	0.0107	1.6862	1.2985
No log	5.0	20	1.1646	0.0029	1.1650	1.0794
No log	6.0	24	0.9397	0.0394	0.9400	0.9695
No log	7.0	28	0.7300	0.4352	0.7302	0.8545
No log	8.0	32	0.8728	0.3491	0.8730	0.9343
No log	9.0	36	0.5924	0.4499	0.5925	0.7698
No log	10.0	40	0.5765	0.3964	0.5767	0.7594
No log	11.0	44	0.6628	0.4623	0.6629	0.8142
No log	12.0	48	0.5919	0.4373	0.5919	0.7693
No log	13.0	52	0.8557	0.2978	0.8558	0.9251
No log	14.0	56	0.5569	0.4586	0.5571	0.7464
No log	15.0	60	0.8208	0.3498	0.8212	0.9062
No log	16.0	64	0.8838	0.3544	0.8846	0.9405
No log	17.0	68	0.9255	0.3573	0.9260	0.9623
No log	18.0	72	0.6204	0.5411	0.6208	0.7879
No log	19.0	76	0.8888	0.3909	0.8893	0.9430
No log	20.0	80	0.8622	0.3292	0.8629	0.9289
No log	21.0	84	0.7151	0.4104	0.7155	0.8459
No log	22.0	88	0.8866	0.3540	0.8870	0.9418
No log	23.0	92	1.3281	0.2086	1.3287	1.1527
No log	24.0	96	0.7368	0.3861	0.7374	0.8587
No log	25.0	100	1.2209	0.2126	1.2214	1.1051
No log	26.0	104	0.8161	0.3831	0.8167	0.9037
No log	27.0	108	0.8069	0.3849	0.8073	0.8985
No log	28.0	112	0.8268	0.3679	0.8271	0.9095
No log	29.0	116	1.1665	0.1750	1.1669	1.0803
No log	30.0	120	0.8055	0.3059	0.8062	0.8979
No log	31.0	124	1.5669	0.1183	1.5675	1.2520
No log	32.0	128	0.6854	0.4119	0.6859	0.8282
No log	33.0	132	0.6841	0.4157	0.6846	0.8274

genki10/BERT_AugV8_k5_task1_organization_sp040_lw010_fold2

BERT_AugV8_k5_task1_organization_sp040_lw010_fold2