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	2	8.9774	0.0	8.9774	2.9962
No log	2.0	4	7.7978	0.0	7.7978	2.7925
No log	3.0	6	6.7972	0.0	6.7972	2.6071
No log	4.0	8	5.9844	0.0158	5.9844	2.4463
No log	5.0	10	5.2699	0.0115	5.2699	2.2956
No log	6.0	12	4.4047	0.0039	4.4047	2.0987
No log	7.0	14	3.7003	0.0	3.7003	1.9236
No log	8.0	16	2.9672	0.0	2.9672	1.7226
No log	9.0	18	2.2849	0.0722	2.2849	1.5116
No log	10.0	20	1.7608	0.0511	1.7608	1.3269
No log	11.0	22	1.4088	0.0382	1.4088	1.1869
No log	12.0	24	1.1609	0.0316	1.1609	1.0774
No log	13.0	26	0.9649	0.0382	0.9649	0.9823
No log	14.0	28	0.8708	0.0565	0.8708	0.9332
No log	15.0	30	0.8018	0.3867	0.8018	0.8955
No log	16.0	32	0.7386	0.4682	0.7386	0.8594
No log	17.0	34	0.8547	0.4264	0.8547	0.9245
No log	18.0	36	0.9213	0.4202	0.9213	0.9598
No log	19.0	38	0.7909	0.2578	0.7909	0.8893
No log	20.0	40	0.8308	0.4384	0.8308	0.9115
No log	21.0	42	1.1705	0.3325	1.1705	1.0819
No log	22.0	44	0.8606	0.3398	0.8606	0.9277
No log	23.0	46	0.8044	0.2488	0.8044	0.8969
No log	24.0	48	0.7519	0.3370	0.7519	0.8671
No log	25.0	50	1.0748	0.3680	1.0748	1.0367
No log	26.0	52	0.8642	0.3825	0.8642	0.9296
No log	27.0	54	0.8668	0.1256	0.8668	0.9310
No log	28.0	56	1.0234	-0.0550	1.0234	1.0116
No log	29.0	58	0.6501	0.3296	0.6501	0.8063
No log	30.0	60	0.6781	0.4152	0.6781	0.8234
No log	31.0	62	0.6029	0.4481	0.6029	0.7764

genki10/BERT_AugV8_k1_task1_organization_sp030_lw040_fold0

BERT_AugV8_k1_task1_organization_sp030_lw040_fold0