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	7	6.5223	0.0018	6.5223	2.5539
No log	2.0	14	2.3005	0.1867	2.3005	1.5167
No log	3.0	21	1.1387	0.0213	1.1387	1.0671
No log	4.0	28	1.2042	0.0520	1.2042	1.0974
No log	5.0	35	0.9636	0.0818	0.9636	0.9816
No log	6.0	42	1.1526	0.2623	1.1526	1.0736
No log	7.0	49	0.8837	0.2911	0.8837	0.9401
No log	8.0	56	0.8842	0.4452	0.8842	0.9403
No log	9.0	63	0.5569	0.5008	0.5569	0.7462
No log	10.0	70	0.5437	0.5805	0.5437	0.7373
No log	11.0	77	0.7128	0.4688	0.7128	0.8443
No log	12.0	84	0.9971	0.3370	0.9971	0.9985
No log	13.0	91	1.4744	0.2456	1.4744	1.2143
No log	14.0	98	1.0108	0.3748	1.0108	1.0054
No log	15.0	105	0.7456	0.4532	0.7456	0.8635
No log	16.0	112	0.7467	0.4283	0.7467	0.8641
No log	17.0	119	1.0857	0.2527	1.0857	1.0419
No log	18.0	126	1.5208	0.1746	1.5208	1.2332
No log	19.0	133	1.2316	0.2669	1.2316	1.1098
No log	20.0	140	1.2504	0.2352	1.2504	1.1182
No log	21.0	147	1.3922	0.2345	1.3922	1.1799
No log	22.0	154	0.9394	0.3946	0.9394	0.9692
No log	23.0	161	0.9961	0.3419	0.9961	0.9980
No log	24.0	168	0.9379	0.3523	0.9379	0.9684
No log	25.0	175	0.9380	0.3322	0.9380	0.9685

genki10/BERT_AugV8_k10_task1_organization_sp010_lw040_fold4

BERT_AugV8_k10_task1_organization_sp010_lw040_fold4