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	6.9087	0.0	6.9088	2.6285
No log	2.0	8	3.9733	0.0039	3.9738	1.9934
No log	3.0	12	2.4508	0.0345	2.4513	1.5657
No log	4.0	16	1.4912	0.0107	1.4917	1.2213
No log	5.0	20	0.9952	0.0107	0.9957	0.9979
No log	6.0	24	1.1464	0.0107	1.1469	1.0709
No log	7.0	28	0.7681	0.3599	0.7686	0.8767
No log	8.0	32	0.9157	0.2796	0.9162	0.9572
No log	9.0	36	0.9547	0.3033	0.9553	0.9774
No log	10.0	40	0.5855	0.4363	0.5858	0.7654
No log	11.0	44	0.6494	0.3860	0.6495	0.8059
No log	12.0	48	0.6928	0.4870	0.6927	0.8323
No log	13.0	52	0.9815	0.3924	0.9811	0.9905
No log	14.0	56	0.8378	0.4535	0.8378	0.9153
No log	15.0	60	0.7960	0.3761	0.7961	0.8923
No log	16.0	64	0.5996	0.5006	0.5995	0.7742
No log	17.0	68	0.5867	0.5098	0.5865	0.7659
No log	18.0	72	1.3013	0.2749	1.3013	1.1407
No log	19.0	76	0.6424	0.4741	0.6423	0.8014
No log	20.0	80	0.6135	0.4824	0.6134	0.7832
No log	21.0	84	1.0385	0.2778	1.0382	1.0189
No log	22.0	88	0.6906	0.4787	0.6904	0.8309
No log	23.0	92	1.0315	0.3766	1.0311	1.0154
No log	24.0	96	1.0074	0.2897	1.0072	1.0036
No log	25.0	100	0.6047	0.4799	0.6046	0.7776
No log	26.0	104	0.6468	0.4825	0.6467	0.8041
No log	27.0	108	0.9194	0.3067	0.9191	0.9587
No log	28.0	112	0.7106	0.4423	0.7103	0.8428
No log	29.0	116	0.9577	0.2625	0.9572	0.9784
No log	30.0	120	0.6475	0.4499	0.6473	0.8045
No log	31.0	124	0.6624	0.4574	0.6622	0.8137
No log	32.0	128	0.8962	0.3269	0.8959	0.9465

genki10/Trial3BERT_AugV8_k5_task1_organization_sp040_lw010_fold2

Trial3BERT_AugV8_k5_task1_organization_sp040_lw010_fold2