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	10.9846	0.0285	10.9849	3.3144
No log	2.0	6	7.5078	0.0	7.5082	2.7401
No log	3.0	9	5.2261	0.0288	5.2264	2.2861
No log	4.0	12	3.4131	0.0039	3.4135	1.8476
No log	5.0	15	2.2698	0.1273	2.2701	1.5067
No log	6.0	18	1.5311	0.0487	1.5315	1.2375
No log	7.0	21	1.2155	0.0422	1.2160	1.1027
No log	8.0	24	1.9511	0.0477	1.9516	1.3970
No log	9.0	27	1.3399	0.0241	1.3403	1.1577
No log	10.0	30	1.1050	0.0449	1.1054	1.0514
No log	11.0	33	1.2707	0.0956	1.2710	1.1274
No log	12.0	36	1.4488	0.2138	1.4489	1.2037
No log	13.0	39	1.5890	0.2182	1.5891	1.2606
No log	14.0	42	1.5292	0.2311	1.5293	1.2367
No log	15.0	45	0.7498	0.5126	0.7499	0.8660
No log	16.0	48	0.6688	0.5027	0.6689	0.8179
No log	17.0	51	0.6761	0.4542	0.6763	0.8224
No log	18.0	54	0.5996	0.5179	0.5995	0.7743
No log	19.0	57	0.5621	0.5115	0.5622	0.7498
No log	20.0	60	0.5841	0.5243	0.5840	0.7642
No log	21.0	63	0.5605	0.5495	0.5605	0.7486
No log	22.0	66	0.8995	0.4494	0.8992	0.9482
No log	23.0	69	0.5892	0.6023	0.5890	0.7674
No log	24.0	72	0.8271	0.5051	0.8267	0.9092
No log	25.0	75	0.6575	0.5735	0.6571	0.8106
No log	26.0	78	0.8563	0.4343	0.8561	0.9253
No log	27.0	81	0.6136	0.5467	0.6135	0.7832
No log	28.0	84	0.7603	0.4819	0.7599	0.8717
No log	29.0	87	0.7338	0.5140	0.7334	0.8564
No log	30.0	90	0.7988	0.4700	0.7983	0.8935
No log	31.0	93	0.7243	0.4703	0.7239	0.8509
No log	32.0	96	1.2116	0.3857	1.2109	1.1004
No log	33.0	99	0.6649	0.5325	0.6646	0.8152
No log	34.0	102	1.0527	0.3841	1.0520	1.0257
No log	35.0	105	0.7187	0.4693	0.7182	0.8475
No log	36.0	108	0.9240	0.4108	0.9234	0.9609
No log	37.0	111	0.7391	0.4644	0.7386	0.8594
No log	38.0	114	1.1231	0.3587	1.1225	1.0595

genki10/BERT_AugV8_k3_task1_organization_sp040_lw040_fold2

BERT_AugV8_k3_task1_organization_sp040_lw040_fold2