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	10.1947	0.0	10.1948	3.1929
No log	2.0	6	7.5146	0.0	7.5148	2.7413
No log	3.0	9	4.9355	0.0232	4.9358	2.2217
No log	4.0	12	3.4045	0.0	3.4048	1.8452
No log	5.0	15	2.2007	0.1314	2.2012	1.4836
No log	6.0	18	1.4352	0.0449	1.4356	1.1981
No log	7.0	21	1.0612	0.0345	1.0616	1.0303
No log	8.0	24	0.9041	0.0769	0.9044	0.9510
No log	9.0	27	1.1918	0.1220	1.1921	1.0919
No log	10.0	30	0.8296	0.4073	0.8298	0.9109
No log	11.0	33	1.1060	0.3746	1.1062	1.0518
No log	12.0	36	0.8791	0.4518	0.8794	0.9377
No log	13.0	39	1.1617	0.3558	1.1620	1.0780
No log	14.0	42	0.6771	0.5363	0.6773	0.8230
No log	15.0	45	0.8308	0.4757	0.8311	0.9116
No log	16.0	48	0.5357	0.5193	0.5358	0.7320
No log	17.0	51	0.5552	0.4649	0.5553	0.7452
No log	18.0	54	0.5570	0.5433	0.5571	0.7464
No log	19.0	57	1.0969	0.4077	1.0970	1.0474
No log	20.0	60	0.5970	0.6223	0.5969	0.7726
No log	21.0	63	0.9706	0.4900	0.9704	0.9851
No log	22.0	66	1.6225	0.3055	1.6225	1.2738
No log	23.0	69	0.5401	0.5949	0.5399	0.7348
No log	24.0	72	0.7568	0.5147	0.7567	0.8699
No log	25.0	75	0.8198	0.4887	0.8198	0.9054
No log	26.0	78	1.0746	0.3559	1.0747	1.0367
No log	27.0	81	0.6276	0.5375	0.6278	0.7923
No log	28.0	84	0.8648	0.4361	0.8650	0.9301
No log	29.0	87	0.7963	0.4782	0.7964	0.8924
No log	30.0	90	0.6994	0.5059	0.6994	0.8363
No log	31.0	93	0.7426	0.5105	0.7426	0.8618
No log	32.0	96	1.0025	0.4109	1.0026	1.0013
No log	33.0	99	0.8537	0.4687	0.8536	0.9239
No log	34.0	102	0.7426	0.4863	0.7425	0.8617
No log	35.0	105	1.0165	0.3304	1.0164	1.0082

genki10/Trial3BERT_AugV8_k3_task1_organization_sp050_lw010_fold2

Trial3BERT_AugV8_k3_task1_organization_sp050_lw010_fold2