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	11.5558	-0.0099	11.5529	3.3989
No log	2.0	8	8.0482	0.0	8.0458	2.8365
No log	3.0	12	5.1945	0.0156	5.1923	2.2787
No log	4.0	16	3.4796	0.0	3.4777	1.8649
No log	5.0	20	1.9922	0.0894	1.9905	1.4108
No log	6.0	24	1.2625	0.0	1.2610	1.1229
No log	7.0	28	1.4308	0.0315	1.4293	1.1956
No log	8.0	32	1.3225	0.0568	1.3210	1.1493
No log	9.0	36	1.4630	0.0915	1.4613	1.2089
No log	10.0	40	1.8234	0.1253	1.8216	1.3497
No log	11.0	44	1.4943	0.1281	1.4925	1.2217
No log	12.0	48	1.2117	0.1217	1.2101	1.1000
No log	13.0	52	1.2449	0.1308	1.2435	1.1151
No log	14.0	56	0.8651	0.3150	0.8640	0.9295
No log	15.0	60	1.4360	0.1766	1.4350	1.1979
No log	16.0	64	1.1305	0.2667	1.1295	1.0628
No log	17.0	68	1.2488	0.2514	1.2481	1.1172
No log	18.0	72	1.8776	0.1295	1.8767	1.3699
No log	19.0	76	2.3186	0.0984	2.3173	1.5223
No log	20.0	80	1.5208	0.1843	1.5198	1.2328
No log	21.0	84	1.6693	0.1157	1.6683	1.2916
No log	22.0	88	2.2653	0.0544	2.2639	1.5046
No log	23.0	92	2.1003	0.1008	2.0991	1.4488
No log	24.0	96	1.6690	0.1615	1.6681	1.2916
No log	25.0	100	2.5386	0.0597	2.5375	1.5929
No log	26.0	104	1.7104	0.1084	1.7094	1.3074
No log	27.0	108	2.2872	0.1000	2.2858	1.5119
No log	28.0	112	1.9047	0.1335	1.9035	1.3797
No log	29.0	116	1.4756	0.1664	1.4746	1.2143

genki10/BERT_AugV8_k5_task1_organization_sp060_lw040_fold1

BERT_AugV8_k5_task1_organization_sp060_lw040_fold1