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	9.2753	0.0	9.2737	3.0453
No log	2.0	8	5.4526	0.0596	5.4513	2.3348
No log	3.0	12	3.4529	0.0038	3.4519	1.8579
No log	4.0	16	1.9273	0.0647	1.9266	1.3880
No log	5.0	20	1.3756	0.0202	1.3751	1.1726
No log	6.0	24	1.5363	0.0463	1.5357	1.2392
No log	7.0	28	1.1113	0.0829	1.1111	1.0541
No log	8.0	32	1.2581	0.0970	1.2581	1.1216
No log	9.0	36	0.8266	0.3485	0.8268	0.9093
No log	10.0	40	0.7056	0.4098	0.7059	0.8402
No log	11.0	44	0.8362	0.3708	0.8368	0.9148
No log	12.0	48	0.6891	0.3902	0.6895	0.8304
No log	13.0	52	0.9867	0.3484	0.9867	0.9933
No log	14.0	56	0.9211	0.3636	0.9209	0.9596
No log	15.0	60	0.8421	0.4165	0.8421	0.9177
No log	16.0	64	1.5322	0.2050	1.5315	1.2375
No log	17.0	68	0.8441	0.3704	0.8444	0.9189
No log	18.0	72	1.5556	0.1810	1.5550	1.2470
No log	19.0	76	1.1480	0.2642	1.1476	1.0713
No log	20.0	80	0.8731	0.3445	0.8733	0.9345
No log	21.0	84	1.2208	0.2193	1.2205	1.1048
No log	22.0	88	1.1610	0.2734	1.1605	1.0773
No log	23.0	92	1.2775	0.2681	1.2770	1.1301
No log	24.0	96	1.0710	0.2788	1.0708	1.0348
No log	25.0	100	1.1491	0.2304	1.1488	1.0718
No log	26.0	104	0.8326	0.3764	0.8327	0.9125
No log	27.0	108	1.1040	0.2664	1.1037	1.0506
No log	28.0	112	1.0459	0.2925	1.0458	1.0226
No log	29.0	116	0.9541	0.3502	0.9540	0.9767
No log	30.0	120	0.9561	0.3496	0.9559	0.9777

genki10/BERT_AugV8_k5_task1_organization_sp020_lw070_fold3

BERT_AugV8_k5_task1_organization_sp020_lw070_fold3