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: 100

Training Loss	Epoch	Step	Validation Loss	Qwk	Mse	Rmse
No log	1.0	4	8.8111	0.0	8.8086	2.9679
No log	2.0	8	5.1544	0.0666	5.1521	2.2698
No log	3.0	12	3.3499	0.0	3.3479	1.8297
No log	4.0	16	2.0097	0.0398	2.0082	1.4171
No log	5.0	20	1.2241	0.0315	1.2226	1.1057
No log	6.0	24	0.9523	0.0298	0.9511	0.9752
No log	7.0	28	0.7425	0.4112	0.7415	0.8611
No log	8.0	32	0.8087	0.2957	0.8076	0.8986
No log	9.0	36	0.6435	0.5316	0.6424	0.8015
No log	10.0	40	0.6318	0.5034	0.6307	0.7941
No log	11.0	44	0.6995	0.4341	0.6985	0.8357
No log	12.0	48	0.6801	0.5567	0.6790	0.8240
No log	13.0	52	0.6078	0.5844	0.6069	0.7791
No log	14.0	56	0.5454	0.5374	0.5448	0.7381
No log	15.0	60	1.0135	0.1546	1.0128	1.0064
No log	16.0	64	0.4786	0.6165	0.4780	0.6914
No log	17.0	68	0.9974	0.2107	0.9968	0.9984
No log	18.0	72	0.5573	0.5939	0.5568	0.7462
No log	19.0	76	0.6348	0.5236	0.6344	0.7965
No log	20.0	80	0.9286	0.3189	0.9281	0.9634
No log	21.0	84	0.5979	0.5805	0.5974	0.7729
No log	22.0	88	0.8473	0.3739	0.8466	0.9201
No log	23.0	92	0.7902	0.4828	0.7899	0.8888
No log	24.0	96	0.9060	0.2753	0.9053	0.9515
No log	25.0	100	0.7941	0.4799	0.7938	0.8910
No log	26.0	104	0.8065	0.4270	0.8059	0.8977
No log	27.0	108	1.2154	0.2557	1.2150	1.1023
No log	28.0	112	1.0322	0.3413	1.0317	1.0157
No log	29.0	116	0.8686	0.4189	0.8680	0.9317
No log	30.0	120	1.0072	0.3599	1.0066	1.0033
No log	31.0	124	0.8116	0.4993	0.8112	0.9007
No log	32.0	128	0.9664	0.3616	0.9658	0.9828
No log	33.0	132	0.9014	0.3479	0.9006	0.9490
No log	34.0	136	0.9763	0.3711	0.9758	0.9878
No log	35.0	140	1.0826	0.2580	1.0819	1.0401
No log	36.0	144	0.8403	0.4513	0.8399	0.9164

genki10/ASAP_FineTuningBERT_AugV16_k5_task1_organization_k5_k5_fold1

ASAP_FineTuningBERT_AugV16_k5_task1_organization_k5_k5_fold1