learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.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: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.476	1.0	375	0.4315	0.8037	0.7539
0.3951	2.0	750	0.4368	0.8143	0.7795
0.3517	3.0	1125	0.4516	0.8147	0.7685
0.3025	4.0	1500	0.4954	0.8127	0.7574
0.2675	5.0	1875	0.5354	0.8003	0.7689
0.2326	6.0	2250	0.5403	0.8143	0.7648
0.2015	7.0	2625	0.5689	0.8117	0.7740
0.1757	8.0	3000	0.6340	0.8097	0.7693
0.16	9.0	3375	0.6285	0.8033	0.7679
0.1522	10.0	3750	0.6530	0.8047	0.7676

phunganhsang/PhoBert_Lexical_CITA_15k

PhoBert_Lexical_CITA_15k