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	7.7650	0.0	7.7650	2.7866
No log	2.0	8	5.9189	0.0147	5.9189	2.4329
No log	3.0	12	4.2316	0.0039	4.2316	2.0571
No log	4.0	16	2.6897	0.0	2.6897	1.6400
No log	5.0	20	1.5728	0.0316	1.5728	1.2541
No log	6.0	24	1.0464	0.0316	1.0464	1.0230
No log	7.0	28	1.0343	0.0382	1.0343	1.0170
No log	8.0	32	0.8144	0.3797	0.8144	0.9024
No log	9.0	36	0.9565	0.2197	0.9565	0.9780
No log	10.0	40	0.7374	0.4189	0.7374	0.8587
No log	11.0	44	0.7212	0.4375	0.7212	0.8492
No log	12.0	48	0.6994	0.3762	0.6994	0.8363
No log	13.0	52	0.7809	0.3880	0.7809	0.8837
No log	14.0	56	0.7960	0.2678	0.7960	0.8922
No log	15.0	60	0.7078	0.3818	0.7078	0.8413
No log	16.0	64	1.1335	0.2394	1.1335	1.0646
No log	17.0	68	0.9353	0.2287	0.9353	0.9671
No log	18.0	72	0.8436	0.3084	0.8436	0.9185
No log	19.0	76	1.5705	0.1431	1.5705	1.2532
No log	20.0	80	0.8377	0.3180	0.8377	0.9152
No log	21.0	84	1.1620	0.1780	1.1620	1.0780
No log	22.0	88	0.7560	0.3845	0.7560	0.8695
No log	23.0	92	0.8394	0.3134	0.8394	0.9162
No log	24.0	96	0.9068	0.3046	0.9068	0.9523
No log	25.0	100	0.8311	0.3422	0.8311	0.9116
No log	26.0	104	1.2934	0.1855	1.2934	1.1373

genki10/BERT_AugV8_k5_task1_organization_sp010_lw050_fold0

BERT_AugV8_k5_task1_organization_sp010_lw050_fold0