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	8.6400	0.0	8.6402	2.9394
No log	2.0	8	5.4151	0.0260	5.4154	2.3271
No log	3.0	12	3.2728	0.0039	3.2732	1.8092
No log	4.0	16	1.9444	0.0873	1.9449	1.3946
No log	5.0	20	1.4267	0.0107	1.4271	1.1946
No log	6.0	24	1.0542	0.0107	1.0546	1.0269
No log	7.0	28	1.2484	0.0285	1.2488	1.1175
No log	8.0	32	1.1453	0.0665	1.1456	1.0703
No log	9.0	36	0.8988	0.2377	0.8989	0.9481
No log	10.0	40	0.8540	0.3046	0.8542	0.9242
No log	11.0	44	0.6143	0.3829	0.6144	0.7838
No log	12.0	48	1.1704	0.2065	1.1706	1.0819
No log	13.0	52	0.5357	0.5019	0.5356	0.7318
No log	14.0	56	1.1269	0.2719	1.1268	1.0615
No log	15.0	60	0.5579	0.4746	0.5578	0.7468
No log	16.0	64	1.2507	0.1841	1.2508	1.1184
No log	17.0	68	0.5722	0.5411	0.5723	0.7565
No log	18.0	72	1.5669	0.1829	1.5669	1.2518
No log	19.0	76	0.6957	0.4415	0.6957	0.8341
No log	20.0	80	1.3954	0.1644	1.3955	1.1813
No log	21.0	84	1.4538	0.1607	1.4539	1.2058
No log	22.0	88	0.8312	0.3379	0.8313	0.9117
No log	23.0	92	1.3922	0.1285	1.3922	1.1799
No log	24.0	96	1.1901	0.2489	1.1901	1.0909
No log	25.0	100	1.0934	0.2932	1.0936	1.0457
No log	26.0	104	1.3256	0.2085	1.3259	1.1515
No log	27.0	108	1.3550	0.1572	1.3554	1.1642
No log	28.0	112	1.4904	0.1196	1.4905	1.2208
No log	29.0	116	0.7907	0.3622	0.7906	0.8892
No log	30.0	120	1.2909	0.1637	1.2910	1.1362
No log	31.0	124	1.1357	0.2559	1.1358	1.0657
No log	32.0	128	1.0978	0.2685	1.0979	1.0478

genki10/BERT_AugV8_k5_task1_organization_sp030_lw050_fold2

BERT_AugV8_k5_task1_organization_sp030_lw050_fold2