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	3.5698	0.0	3.5679	1.8889
No log	2.0	14	1.6217	0.0211	1.6201	1.2728
No log	3.0	21	1.5117	0.0106	1.5102	1.2289
No log	4.0	28	1.2206	0.0106	1.2191	1.1041
No log	5.0	35	1.0685	0.0790	1.0671	1.0330
No log	6.0	42	0.7631	0.3276	0.7620	0.8729
No log	7.0	49	0.6805	0.3669	0.6795	0.8243
No log	8.0	56	0.7360	0.3675	0.7351	0.8574
No log	9.0	63	0.6515	0.5095	0.6507	0.8067
No log	10.0	70	0.8613	0.4593	0.8601	0.9274
No log	11.0	77	0.8680	0.3418	0.8667	0.9310
No log	12.0	84	0.6538	0.4941	0.6530	0.8081
No log	13.0	91	0.9270	0.3835	0.9258	0.9622
No log	14.0	98	1.0283	0.2828	1.0269	1.0134
No log	15.0	105	0.8580	0.3471	0.8568	0.9256
No log	16.0	112	0.9526	0.3877	0.9513	0.9753
No log	17.0	119	0.8170	0.3741	0.8159	0.9033
No log	18.0	126	0.8637	0.3777	0.8625	0.9287
No log	19.0	133	0.9941	0.3524	0.9927	0.9963
No log	20.0	140	0.9017	0.3955	0.9007	0.9491
No log	21.0	147	1.3681	0.1975	1.3669	1.1691
No log	22.0	154	1.0631	0.2833	1.0618	1.0304
No log	23.0	161	0.8098	0.3802	0.8087	0.8993
No log	24.0	168	0.7455	0.3946	0.7445	0.8628

genki10/BERT_AugV8_k10_task1_organization_sp030_lw040_fold1

BERT_AugV8_k10_task1_organization_sp030_lw040_fold1