learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.5734	1.0	18336	0.5731	0.6919	0.6919	0.6919	0.6919
0.5493	2.0	36672	0.5456	0.7191	0.7196	0.7189	0.7188
0.5059	3.0	55008	0.5394	0.7332	0.7335	0.7333	0.7332
0.4804	4.0	73344	0.5308	0.7399	0.7399	0.7398	0.7398
0.4360	5.0	91680	0.5421	0.7483	0.7500	0.7486	0.7480
0.4035	6.0	110016	0.5732	0.7536	0.7548	0.7533	0.7531
0.3684	7.0	128352	0.5933	0.7629	0.7640	0.7632	0.7628
0.3326	8.0	146688	0.5838	0.7678	0.7681	0.7679	0.7678
0.3045	9.0	165024	0.5788	0.7718	0.7736	0.7722	0.7716
0.2776	10.0	183360	0.6116	0.7801	0.7820	0.7805	0.7799
0.2383	11.0	201696	0.6572	0.7795	0.7819	0.7799	0.7791
0.2173	12.0	220032	0.7140	0.7860	0.7868	0.7862	0.7859
0.1882	13.0	238368	0.7037	0.7898	0.7904	0.7900	0.7897
0.1752	14.0	256704	0.7857	0.7937	0.7950	0.7940	0.7936
0.1532	15.0	275040	0.8212	0.7922	0.7959	0.7927	0.7918
0.1391	16.0	293376	0.8650	0.7984	0.7995	0.7987	0.7983
0.1290	17.0	311712	0.8996	0.7983	0.8003	0.7987	0.7981
0.1112	18.0	330048	0.9984	0.7962	0.7997	0.7966	0.7957
0.1070	19.0	348384	1.0093	0.8008	0.8027	0.8011	0.8006
0.0832	20.0	366720	1.0581	0.8014	0.8032	0.8018	0.8013

mskang1120/kobert_baseline

kobert_baseline