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	9.5437	0.0036	9.5419	3.0890
No log	2.0	6	8.0271	0.0	8.0254	2.8329
No log	3.0	9	5.9342	0.0698	5.9328	2.4357
No log	4.0	12	4.4148	0.0	4.4136	2.1008
No log	5.0	15	3.0619	0.0	3.0609	1.7495
No log	6.0	18	2.2507	0.1047	2.2499	1.5000
No log	7.0	21	1.4895	0.0202	1.4890	1.2202
No log	8.0	24	1.1784	0.0	1.1780	1.0854
No log	9.0	27	0.9539	0.0645	0.9536	0.9765
No log	10.0	30	0.8631	0.3258	0.8629	0.9289
No log	11.0	33	1.1863	0.0102	1.1858	1.0890
No log	12.0	36	1.0843	0.0266	1.0839	1.0411
No log	13.0	39	1.0165	0.0453	1.0162	1.0081
No log	14.0	42	1.0042	0.1191	1.0041	1.0021
No log	15.0	45	0.7197	0.4099	0.7199	0.8485
No log	16.0	48	1.3579	0.2158	1.3581	1.1654
No log	17.0	51	3.1653	0.0262	3.1649	1.7790
No log	18.0	54	1.5631	0.1781	1.5632	1.2503
No log	19.0	57	1.7932	0.1690	1.7933	1.3392
No log	20.0	60	2.5755	0.0495	2.5755	1.6048
No log	21.0	63	1.8859	0.1425	1.8864	1.3735
No log	22.0	66	3.5878	-0.0018	3.5875	1.8941
No log	23.0	69	1.9990	0.1148	1.9994	1.4140
No log	24.0	72	2.5621	0.0713	2.5624	1.6007
No log	25.0	75	3.4277	0.0104	3.4276	1.8514
No log	26.0	78	1.6977	0.1655	1.6983	1.3032
No log	27.0	81	2.3516	0.0560	2.3516	1.5335
No log	28.0	84	3.3731	0.0180	3.3724	1.8364
No log	29.0	87	1.2259	0.2588	1.2263	1.1074
No log	30.0	90	1.4861	0.1748	1.4863	1.2191

genki10/Trial2BERT_AugV8_k3_task1_organization_sp010_lw040_fold3

Trial2BERT_AugV8_k3_task1_organization_sp010_lw040_fold3