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	8.1112	0.0	8.1112	2.8480
No log	2.0	6	6.7455	0.0	6.7455	2.5972
No log	3.0	9	5.5072	0.0115	5.5072	2.3467
No log	4.0	12	4.2464	0.0039	4.2464	2.0607
No log	5.0	15	3.1695	0.0	3.1695	1.7803
No log	6.0	18	2.2542	0.1276	2.2542	1.5014
No log	7.0	21	1.5896	0.0575	1.5896	1.2608
No log	8.0	24	1.1383	0.0382	1.1383	1.0669
No log	9.0	27	0.9363	0.0409	0.9363	0.9676
No log	10.0	30	1.0050	0.2236	1.0050	1.0025
No log	11.0	33	0.8552	0.0811	0.8552	0.9248
No log	12.0	36	0.6647	0.4663	0.6647	0.8153
No log	13.0	39	1.2662	0.2407	1.2662	1.1252
No log	14.0	42	0.7570	0.4754	0.7570	0.8701
No log	15.0	45	0.6731	0.3416	0.6731	0.8204
No log	16.0	48	0.7340	0.5113	0.7340	0.8568
No log	17.0	51	0.7970	0.3658	0.7970	0.8927
No log	18.0	54	0.7516	0.4134	0.7516	0.8669
No log	19.0	57	0.7412	0.4076	0.7412	0.8609
No log	20.0	60	0.6636	0.4186	0.6636	0.8146
No log	21.0	63	0.7346	0.3983	0.7346	0.8571
No log	22.0	66	0.6874	0.3456	0.6874	0.8291
No log	23.0	69	0.9615	0.2971	0.9615	0.9806
No log	24.0	72	0.7569	0.3644	0.7569	0.8700
No log	25.0	75	0.8407	0.3797	0.8407	0.9169
No log	26.0	78	0.7703	0.3978	0.7703	0.8776
No log	27.0	81	0.8311	0.3663	0.8311	0.9116
No log	28.0	84	0.8343	0.4156	0.8343	0.9134
No log	29.0	87	0.7483	0.3981	0.7483	0.8650
No log	30.0	90	0.7290	0.4506	0.7290	0.8538
No log	31.0	93	0.8826	0.3713	0.8826	0.9395

genki10/BERT_AugV8_k3_task1_organization_sp040_lw010_fold0

BERT_AugV8_k3_task1_organization_sp040_lw010_fold0