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	8.4086	0.0	8.4086	2.8998
No log	2.0	8	5.0098	0.0157	5.0098	2.2383
No log	3.0	12	2.9170	0.0040	2.9170	1.7079
No log	4.0	16	1.9088	0.0555	1.9088	1.3816
No log	5.0	20	1.2557	0.0316	1.2557	1.1206
No log	6.0	24	1.1025	0.0316	1.1025	1.0500
No log	7.0	28	1.0730	0.0445	1.0730	1.0358
No log	8.0	32	1.2198	0.0752	1.2198	1.1044
No log	9.0	36	0.8883	0.2498	0.8883	0.9425
No log	10.0	40	0.8480	0.3102	0.8480	0.9208
No log	11.0	44	0.8848	0.3244	0.8848	0.9406
No log	12.0	48	0.7588	0.3908	0.7588	0.8711
No log	13.0	52	0.7390	0.4807	0.7390	0.8596
No log	14.0	56	0.8535	0.3767	0.8535	0.9238
No log	15.0	60	1.2363	0.2737	1.2363	1.1119
No log	16.0	64	0.9003	0.4003	0.9003	0.9488
No log	17.0	68	0.8238	0.4251	0.8238	0.9076
No log	18.0	72	1.5026	0.2162	1.5026	1.2258
No log	19.0	76	0.7094	0.4884	0.7094	0.8422
No log	20.0	80	1.5734	0.1867	1.5734	1.2543
No log	21.0	84	1.1182	0.3148	1.1182	1.0574
No log	22.0	88	0.7408	0.4493	0.7408	0.8607
No log	23.0	92	1.0968	0.3106	1.0968	1.0473
No log	24.0	96	1.0738	0.3382	1.0738	1.0362
No log	25.0	100	0.9284	0.3592	0.9284	0.9635
No log	26.0	104	1.1870	0.2808	1.1870	1.0895
No log	27.0	108	1.0779	0.2813	1.0779	1.0382
No log	28.0	112	1.0059	0.2368	1.0059	1.0029
No log	29.0	116	0.9243	0.3113	0.9243	0.9614
No log	30.0	120	1.3495	0.2486	1.3495	1.1617
No log	31.0	124	0.7888	0.4164	0.7888	0.8881
No log	32.0	128	1.3182	0.2379	1.3182	1.1481
No log	33.0	132	0.9284	0.3445	0.9284	0.9635
No log	34.0	136	1.3537	0.2048	1.3537	1.1635

genki10/BERT_AugV8_k5_task1_organization_sp030_lw040_fold4

BERT_AugV8_k5_task1_organization_sp030_lw040_fold4