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	7.5529	0.0	7.5503	2.7478
No log	2.0	8	4.5674	0.0118	4.5654	2.1367
No log	3.0	12	2.5899	0.0336	2.5881	1.6088
No log	4.0	16	1.4279	0.0237	1.4264	1.1943
No log	5.0	20	1.1549	0.0106	1.1535	1.0740
No log	6.0	24	1.0066	0.0222	1.0052	1.0026
No log	7.0	28	1.0369	0.0164	1.0354	1.0176
No log	8.0	32	1.1838	-0.0193	1.1821	1.0873
No log	9.0	36	0.8367	0.2295	0.8353	0.9139
No log	10.0	40	0.8055	0.2818	0.8042	0.8968
No log	11.0	44	0.6468	0.4219	0.6458	0.8036
No log	12.0	48	0.9570	0.4229	0.9557	0.9776
No log	13.0	52	0.7309	0.4655	0.7302	0.8545
No log	14.0	56	0.9337	0.3073	0.9329	0.9659
No log	15.0	60	0.7723	0.3634	0.7715	0.8783
No log	16.0	64	0.8293	0.3449	0.8282	0.9100
No log	17.0	68	0.7686	0.3962	0.7679	0.8763
No log	18.0	72	0.9443	0.3280	0.9432	0.9712
No log	19.0	76	0.7653	0.3893	0.7646	0.8744
No log	20.0	80	0.9873	0.3198	0.9862	0.9931
No log	21.0	84	0.8423	0.3315	0.8412	0.9172
No log	22.0	88	0.8427	0.3488	0.8413	0.9172
No log	23.0	92	0.7333	0.4424	0.7320	0.8556
No log	24.0	96	0.7100	0.4349	0.7088	0.8419
No log	25.0	100	0.8851	0.3010	0.8837	0.9401
No log	26.0	104	0.8105	0.3498	0.8093	0.8996
No log	27.0	108	0.7801	0.3909	0.7788	0.8825
No log	28.0	112	0.8331	0.3924	0.8317	0.9120

genki10/Trial3BERT_AugV8_k5_task1_organization_sp010_lw040_fold1

Trial3BERT_AugV8_k5_task1_organization_sp010_lw040_fold1