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	6	7.7251	0.0	7.7225	2.7789
No log	2.0	12	3.2036	0.0	3.2019	1.7894
No log	3.0	18	1.5826	0.0315	1.5812	1.2575
No log	4.0	24	1.0569	0.0211	1.0555	1.0274
No log	5.0	30	1.1193	0.0583	1.1178	1.0572
No log	6.0	36	0.8145	0.3397	0.8132	0.9018
No log	7.0	42	0.6764	0.4294	0.6750	0.8216
No log	8.0	48	0.8355	0.2225	0.8346	0.9136
No log	9.0	54	0.8046	0.3334	0.8030	0.8961
No log	10.0	60	0.7683	0.3700	0.7669	0.8757
No log	11.0	66	0.7523	0.3878	0.7507	0.8664
No log	12.0	72	0.9977	0.2890	0.9960	0.9980
No log	13.0	78	0.7111	0.4232	0.7096	0.8424
No log	14.0	84	0.7068	0.4189	0.7054	0.8399
No log	15.0	90	0.8852	0.4226	0.8837	0.9401
No log	16.0	96	0.8386	0.3701	0.8369	0.9148
No log	17.0	102	1.0945	0.3121	1.0925	1.0452
No log	18.0	108	0.9579	0.3049	0.9559	0.9777
No log	19.0	114	1.0193	0.2587	1.0172	1.0086
No log	20.0	120	0.8656	0.3285	0.8638	0.9294
No log	21.0	126	0.9179	0.3396	0.9159	0.9571
No log	22.0	132	0.8455	0.3766	0.8438	0.9186

genki10/BERT_AugV8_k7_task1_organization_sp040_lw040_fold1

BERT_AugV8_k7_task1_organization_sp040_lw040_fold1