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	11.7260	-0.0030	11.7232	3.4239
No log	2.0	8	8.0233	0.0	8.0210	2.8321
No log	3.0	12	5.0446	0.0152	5.0424	2.2455
No log	4.0	16	3.2779	0.0	3.2760	1.8100
No log	5.0	20	1.7577	0.0482	1.7560	1.3252
No log	6.0	24	1.3522	0.0106	1.3507	1.1622
No log	7.0	28	1.2796	0.0568	1.2781	1.1305
No log	8.0	32	1.2963	0.0630	1.2947	1.1378
No log	9.0	36	1.6029	0.0334	1.6011	1.2654
No log	10.0	40	1.4374	0.0649	1.4356	1.1982
No log	11.0	44	2.5620	0.0306	2.5598	1.5999
No log	12.0	48	1.4157	0.0288	1.4137	1.1890
No log	13.0	52	1.3743	-0.0127	1.3722	1.1714
No log	14.0	56	2.5991	-0.0249	2.5965	1.6114
No log	15.0	60	1.6151	-0.0080	1.6128	1.2700
No log	16.0	64	1.7554	-0.0093	1.7533	1.3241
No log	17.0	68	1.8891	-0.0357	1.8868	1.3736
No log	18.0	72	1.9875	-0.0356	1.9848	1.4088
No log	19.0	76	2.2589	-0.0322	2.2557	1.5019
No log	20.0	80	2.2761	-0.0683	2.2731	1.5077
No log	21.0	84	2.3936	-0.0578	2.3903	1.5460
No log	22.0	88	1.7017	-0.0078	1.6993	1.3036
No log	23.0	92	3.5959	-0.0597	3.5920	1.8953
No log	24.0	96	2.3404	-0.0283	2.3371	1.5288
No log	25.0	100	2.0114	-0.0046	2.0084	1.4172

genki10/BERT_AugV8_k5_task1_organization_sp010_lw070_fold1

BERT_AugV8_k5_task1_organization_sp010_lw070_fold1