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	7.5129	0.0	7.5129	2.7410
No log	2.0	8	5.8632	0.0182	5.8632	2.4214
No log	3.0	12	4.1257	0.0039	4.1257	2.0312
No log	4.0	16	2.5135	0.0408	2.5135	1.5854
No log	5.0	20	1.4873	0.0316	1.4873	1.2195
No log	6.0	24	1.1446	0.0212	1.1446	1.0699
No log	7.0	28	0.9153	0.1259	0.9153	0.9567
No log	8.0	32	0.8437	0.2327	0.8437	0.9185
No log	9.0	36	1.0412	0.2817	1.0412	1.0204
No log	10.0	40	1.0444	0.0118	1.0444	1.0220
No log	11.0	44	0.6526	0.4031	0.6526	0.8078
No log	12.0	48	1.1051	0.3471	1.1051	1.0513
No log	13.0	52	0.6267	0.3825	0.6267	0.7917
No log	14.0	56	0.7105	0.2858	0.7105	0.8429
No log	15.0	60	0.8393	0.2517	0.8393	0.9162
No log	16.0	64	0.6107	0.3876	0.6107	0.7815
No log	17.0	68	0.6513	0.3772	0.6513	0.8070
No log	18.0	72	0.7242	0.3304	0.7242	0.8510
No log	19.0	76	0.6533	0.4667	0.6533	0.8083
No log	20.0	80	0.6247	0.5053	0.6247	0.7904
No log	21.0	84	0.9637	0.2993	0.9637	0.9817
No log	22.0	88	0.8123	0.4406	0.8123	0.9013
No log	23.0	92	0.7893	0.3487	0.7893	0.8885
No log	24.0	96	0.6755	0.4476	0.6755	0.8219
No log	25.0	100	0.9180	0.3321	0.9180	0.9581
No log	26.0	104	0.6771	0.4882	0.6771	0.8229
No log	27.0	108	0.9371	0.2840	0.9371	0.9680
No log	28.0	112	0.6725	0.4821	0.6725	0.8200
No log	29.0	116	0.7477	0.4044	0.7477	0.8647
No log	30.0	120	0.7257	0.4600	0.7257	0.8519
No log	31.0	124	0.8428	0.3148	0.8428	0.9180
No log	32.0	128	0.6902	0.4420	0.6902	0.8308
No log	33.0	132	0.7465	0.4774	0.7465	0.8640
No log	34.0	136	0.8923	0.3458	0.8923	0.9446
No log	35.0	140	0.7922	0.4694	0.7922	0.8901

genki10/BERT_AugV8_k5_task1_organization_sp040_lw010_fold0

BERT_AugV8_k5_task1_organization_sp040_lw010_fold0