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	10.1783	0.0018	10.1783	3.1903
No log	2.0	6	7.5031	0.0	7.5031	2.7392
No log	3.0	9	4.8363	0.0301	4.8363	2.1992
No log	4.0	12	3.2489	0.0040	3.2489	1.8025
No log	5.0	15	2.0728	0.0528	2.0728	1.4397
No log	6.0	18	1.3874	0.0316	1.3874	1.1779
No log	7.0	21	1.3410	0.0316	1.3410	1.1580
No log	8.0	24	1.0518	0.0406	1.0518	1.0256
No log	9.0	27	1.0818	0.0740	1.0818	1.0401
No log	10.0	30	1.1112	0.1345	1.1112	1.0541
No log	11.0	33	0.9554	0.3159	0.9554	0.9774
No log	12.0	36	1.0915	0.3297	1.0915	1.0448
No log	13.0	39	1.0637	0.3811	1.0637	1.0314
No log	14.0	42	0.9886	0.3518	0.9886	0.9943
No log	15.0	45	0.7617	0.4248	0.7617	0.8728
No log	16.0	48	1.0465	0.3773	1.0465	1.0230
No log	17.0	51	0.9273	0.4065	0.9273	0.9629
No log	18.0	54	0.8601	0.4694	0.8601	0.9274
No log	19.0	57	1.2844	0.3893	1.2844	1.1333
No log	20.0	60	0.8984	0.4966	0.8984	0.9479
No log	21.0	63	1.2678	0.4072	1.2678	1.1260
No log	22.0	66	1.5289	0.3708	1.5289	1.2365
No log	23.0	69	0.9306	0.4815	0.9306	0.9647
No log	24.0	72	0.9278	0.4743	0.9278	0.9632
No log	25.0	75	1.1258	0.4221	1.1258	1.0610
No log	26.0	78	1.1126	0.4054	1.1126	1.0548
No log	27.0	81	0.9501	0.4583	0.9501	0.9747
No log	28.0	84	1.2650	0.3792	1.2650	1.1247
No log	29.0	87	0.9962	0.4749	0.9962	0.9981
No log	30.0	90	1.5595	0.3150	1.5595	1.2488
No log	31.0	93	1.1054	0.4266	1.1054	1.0514
No log	32.0	96	1.0446	0.4387	1.0446	1.0221
No log	33.0	99	1.3009	0.3916	1.3009	1.1406
No log	34.0	102	1.5305	0.3441	1.5305	1.2371
No log	35.0	105	1.0015	0.4308	1.0015	1.0007

genki10/Trial2BERT_AugV8_k3_task1_organization_sp010_lw070_fold4

Trial2BERT_AugV8_k3_task1_organization_sp010_lw070_fold4