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	9.8287	0.0	9.8260	3.1347
No log	2.0	6	7.4554	0.0	7.4531	2.7300
No log	3.0	9	4.7669	0.0258	4.7650	2.1829
No log	4.0	12	3.4910	0.0	3.4892	1.8679
No log	5.0	15	2.0919	0.1113	2.0902	1.4457
No log	6.0	18	1.3372	0.0	1.3358	1.1558
No log	7.0	21	0.9886	0.0	0.9873	0.9936
No log	8.0	24	0.8793	0.2267	0.8781	0.9371
No log	9.0	27	0.8698	0.2657	0.8685	0.9319
No log	10.0	30	0.8249	0.2904	0.8236	0.9075
No log	11.0	33	0.7011	0.5004	0.7000	0.8366
No log	12.0	36	0.8326	0.2968	0.8311	0.9117
No log	13.0	39	0.7705	0.2655	0.7694	0.8772
No log	14.0	42	0.7345	0.4122	0.7329	0.8561
No log	15.0	45	0.6229	0.4200	0.6216	0.7884
No log	16.0	48	0.7200	0.3835	0.7190	0.8479
No log	17.0	51	0.6172	0.4545	0.6160	0.7849
No log	18.0	54	0.5258	0.5117	0.5248	0.7244
No log	19.0	57	0.6070	0.5314	0.6061	0.7785
No log	20.0	60	0.8344	0.4687	0.8334	0.9129
No log	21.0	63	0.6975	0.4965	0.6962	0.8344
No log	22.0	66	0.6664	0.5464	0.6653	0.8157
No log	23.0	69	0.6704	0.5146	0.6690	0.8179
No log	24.0	72	0.6588	0.5071	0.6581	0.8113
No log	25.0	75	0.7490	0.4215	0.7483	0.8650
No log	26.0	78	0.8040	0.4326	0.8032	0.8962
No log	27.0	81	0.9812	0.3794	0.9798	0.9898
No log	28.0	84	0.7661	0.4658	0.7649	0.8746
No log	29.0	87	0.8067	0.4534	0.8059	0.8977
No log	30.0	90	0.8614	0.3951	0.8599	0.9273
No log	31.0	93	0.8061	0.4174	0.8051	0.8973
No log	32.0	96	0.6713	0.4853	0.6704	0.8188
No log	33.0	99	0.7072	0.4677	0.7062	0.8404
No log	34.0	102	0.8419	0.4303	0.8411	0.9171
No log	35.0	105	0.8273	0.4245	0.8263	0.9090
No log	36.0	108	0.7370	0.5228	0.7361	0.8580
No log	37.0	111	0.6957	0.5184	0.6946	0.8334

genki10/Trial3BERT_AugV8_k3_task1_organization_sp010_lw020_fold1

Trial3BERT_AugV8_k3_task1_organization_sp010_lw020_fold1