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	8.3864	0.0	8.3868	2.8960
No log	2.0	8	5.1556	0.0139	5.1560	2.2707
No log	3.0	12	2.8379	0.0	2.8382	1.6847
No log	4.0	16	1.7886	0.0280	1.7890	1.3376
No log	5.0	20	1.1871	0.0029	1.1875	1.0897
No log	6.0	24	1.1369	0.0411	1.1371	1.0663
No log	7.0	28	1.1645	0.0774	1.1646	1.0791
No log	8.0	32	0.8139	0.3366	0.8141	0.9023
No log	9.0	36	0.9016	0.3283	0.9017	0.9496
No log	10.0	40	0.6302	0.4661	0.6304	0.7940
No log	11.0	44	0.6171	0.3658	0.6173	0.7857
No log	12.0	48	0.6889	0.3261	0.6890	0.8301
No log	13.0	52	0.6624	0.4548	0.6623	0.8138
No log	14.0	56	0.6713	0.4532	0.6713	0.8193
No log	15.0	60	0.9157	0.2535	0.9159	0.9570
No log	16.0	64	0.7994	0.4084	0.7994	0.8941
No log	17.0	68	0.5462	0.5651	0.5463	0.7391
No log	18.0	72	0.8109	0.4001	0.8109	0.9005
No log	19.0	76	0.6225	0.4851	0.6227	0.7891
No log	20.0	80	0.8347	0.3225	0.8351	0.9138
No log	21.0	84	1.0509	0.2145	1.0513	1.0253
No log	22.0	88	0.7143	0.4201	0.7144	0.8452
No log	23.0	92	0.7016	0.4214	0.7018	0.8377
No log	24.0	96	0.9377	0.2461	0.9382	0.9686
No log	25.0	100	0.7864	0.3322	0.7868	0.8870
No log	26.0	104	0.7932	0.3609	0.7937	0.8909
No log	27.0	108	0.8641	0.3087	0.8646	0.9298
No log	28.0	112	1.0225	0.2165	1.0232	1.0115
No log	29.0	116	0.7517	0.3801	0.7523	0.8673
No log	30.0	120	0.8383	0.2735	0.8388	0.9159
No log	31.0	124	0.8301	0.2815	0.8306	0.9114
No log	32.0	128	0.8534	0.2797	0.8537	0.9240

genki10/BERT_AugV8_k5_task1_organization_sp010_lw060_fold2

BERT_AugV8_k5_task1_organization_sp010_lw060_fold2