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	7	8.5575	0.0018	8.5574	2.9253
No log	2.0	14	4.5598	0.0079	4.5598	2.1354
No log	3.0	21	1.8578	0.0432	1.8578	1.3630
No log	4.0	28	1.4214	0.0304	1.4214	1.1922
No log	5.0	35	1.4908	0.1037	1.4908	1.2210
No log	6.0	42	2.2027	0.0915	2.2027	1.4842
No log	7.0	49	1.4386	0.1374	1.4386	1.1994
No log	8.0	56	1.0115	0.2591	1.0115	1.0057
No log	9.0	63	1.2837	0.2036	1.2837	1.1330
No log	10.0	70	2.3509	0.0861	2.3509	1.5333
No log	11.0	77	2.2664	0.0951	2.2664	1.5054
No log	12.0	84	1.8489	0.1069	1.8489	1.3597
No log	13.0	91	2.4447	0.0828	2.4447	1.5636
No log	14.0	98	2.2749	0.1198	2.2749	1.5083
No log	15.0	105	2.6675	0.0862	2.6675	1.6332
No log	16.0	112	2.2467	0.1149	2.2467	1.4989
No log	17.0	119	2.3739	0.1184	2.3739	1.5407
No log	18.0	126	1.9042	0.1799	1.9042	1.3799
No log	19.0	133	1.7681	0.1873	1.7681	1.3297
No log	20.0	140	1.8074	0.1440	1.8074	1.3444
No log	21.0	147	2.2400	0.1149	2.2400	1.4967
No log	22.0	154	2.2802	0.1149	2.2802	1.5100
No log	23.0	161	2.0188	0.0851	2.0188	1.4208

genki10/BERT_AugV8_k10_task1_organization_sp010_lw060_fold4

BERT_AugV8_k10_task1_organization_sp010_lw060_fold4