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	3	9.7098	0.0037	9.7098	3.1161
No log	2.0	6	7.5334	0.0018	7.5334	2.7447
No log	3.0	9	6.4713	0.0018	6.4713	2.5439
No log	4.0	12	4.9529	0.0166	4.9529	2.2255
No log	5.0	15	2.8325	0.0040	2.8325	1.6830
No log	6.0	18	2.0740	0.1158	2.0740	1.4401
No log	7.0	21	1.3855	0.0342	1.3855	1.1771
No log	8.0	24	1.6253	0.0558	1.6253	1.2749
No log	9.0	27	1.3239	0.0596	1.3239	1.1506
No log	10.0	30	1.0126	0.0705	1.0126	1.0063
No log	11.0	33	1.0482	0.1494	1.0482	1.0238
No log	12.0	36	0.9516	0.3044	0.9516	0.9755
No log	13.0	39	0.7914	0.4143	0.7914	0.8896
No log	14.0	42	0.9698	0.3843	0.9698	0.9848
No log	15.0	45	0.8511	0.4620	0.8511	0.9225
No log	16.0	48	0.7249	0.4886	0.7249	0.8514
No log	17.0	51	0.7316	0.4648	0.7316	0.8553
No log	18.0	54	0.7962	0.4462	0.7962	0.8923
No log	19.0	57	0.7661	0.4890	0.7661	0.8753
No log	20.0	60	1.3625	0.3250	1.3625	1.1672
No log	21.0	63	0.7904	0.5624	0.7904	0.8890
No log	22.0	66	0.9589	0.4822	0.9589	0.9792
No log	23.0	69	1.2360	0.3688	1.2360	1.1117
No log	24.0	72	0.7936	0.5559	0.7936	0.8908
No log	25.0	75	1.2761	0.3374	1.2761	1.1296
No log	26.0	78	0.8186	0.4608	0.8186	0.9048
No log	27.0	81	0.8114	0.4928	0.8114	0.9008
No log	28.0	84	1.2450	0.3604	1.2450	1.1158
No log	29.0	87	0.8205	0.5028	0.8205	0.9058
No log	30.0	90	1.0916	0.3603	1.0916	1.0448
No log	31.0	93	0.8294	0.4524	0.8294	0.9107
No log	32.0	96	0.9340	0.3907	0.9340	0.9665
No log	33.0	99	0.8088	0.4238	0.8088	0.8993
No log	34.0	102	0.9348	0.3947	0.9348	0.9669
No log	35.0	105	0.8826	0.4327	0.8826	0.9395
No log	36.0	108	0.9461	0.4124	0.9461	0.9727

genki10/Trial3BERT_AugV8_k3_task1_organization_sp060_lw010_fold4

Trial3BERT_AugV8_k3_task1_organization_sp060_lw010_fold4