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	5	7.3867	0.0	7.3867	2.7178
No log	2.0	10	4.7363	0.0115	4.7363	2.1763
No log	3.0	15	2.7468	0.0	2.7468	1.6574
No log	4.0	20	1.6573	0.0316	1.6573	1.2874
No log	5.0	25	1.2026	0.0212	1.2026	1.0966
No log	6.0	30	0.9070	0.0322	0.9070	0.9524
No log	7.0	35	1.0333	0.0316	1.0333	1.0165
No log	8.0	40	1.1382	0.0316	1.1382	1.0669
No log	9.0	45	1.1550	0.1366	1.1550	1.0747
No log	10.0	50	0.7839	0.3829	0.7839	0.8854
No log	11.0	55	0.7782	0.3973	0.7782	0.8822
No log	12.0	60	0.7137	0.3024	0.7137	0.8448
No log	13.0	65	0.5915	0.4575	0.5915	0.7691
No log	14.0	70	0.5843	0.4079	0.5843	0.7644
No log	15.0	75	0.5623	0.4534	0.5623	0.7498
No log	16.0	80	0.5902	0.4634	0.5902	0.7683
No log	17.0	85	0.6452	0.4511	0.6452	0.8032
No log	18.0	90	0.6749	0.4271	0.6749	0.8215
No log	19.0	95	0.7242	0.4079	0.7242	0.8510
No log	20.0	100	0.7621	0.3569	0.7621	0.8730
No log	21.0	105	0.6773	0.4561	0.6773	0.8230
No log	22.0	110	1.0353	0.2410	1.0353	1.0175
No log	23.0	115	0.6805	0.4976	0.6805	0.8250
No log	24.0	120	0.8535	0.3698	0.8535	0.9239
No log	25.0	125	0.7578	0.3984	0.7578	0.8705
No log	26.0	130	0.7979	0.3357	0.7979	0.8933
No log	27.0	135	0.6604	0.4756	0.6604	0.8127
No log	28.0	140	0.6789	0.4476	0.6789	0.8240
No log	29.0	145	0.7756	0.3784	0.7756	0.8807
No log	30.0	150	0.8116	0.3766	0.8116	0.9009
No log	31.0	155	0.8256	0.3758	0.8256	0.9086
No log	32.0	160	0.9418	0.2179	0.9418	0.9705
No log	33.0	165	0.7549	0.3762	0.7549	0.8688
No log	34.0	170	0.6789	0.4373	0.6789	0.8239
No log	35.0	175	0.8152	0.3158	0.8152	0.9029
No log	36.0	180	0.7067	0.4038	0.7067	0.8407
No log	37.0	185	0.6373	0.4659	0.6373	0.7983
No log	38.0	190	0.7574	0.3428	0.7574	0.8703

genki10/BERT_AugV8_k7_task1_organization_sp020_lw040_fold0

BERT_AugV8_k7_task1_organization_sp020_lw040_fold0