learning_rate: 1e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 64
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 10
label_smoothing_factor: 0.1

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.6996	0.5333	100	0.4548	0.8867	0.8615	0.8761	0.8503
0.6996	1.064	200	0.3524	0.9187	0.8998	0.9207	0.8844
0.6996	1.5973	300	0.3441	0.9217	0.9039	0.9223	0.8900
0.4376	2.128	400	0.3457	0.9247	0.9070	0.9296	0.8906
0.4376	2.6613	500	0.3423	0.928	0.9106	0.9366	0.8924
0.4376	3.192	600	0.3370	0.9253	0.9089	0.9245	0.8966
0.4376	3.7253	700	0.3378	0.9227	0.9074	0.9132	0.9021
0.3287	4.256	800	0.3392	0.921	0.9051	0.9126	0.8985
0.3287	4.7893	900	0.3374	0.9237	0.9078	0.9180	0.8992
0.3287	5.32	1000	0.3377	0.9223	0.9067	0.9142	0.9000
0.3287	5.8533	1100	0.3386	0.9273	0.9118	0.9248	0.9012
0.3037	6.384	1200	0.3454	0.919	0.9037	0.9064	0.9011
0.3037	6.9173	1300	0.3367	0.9233	0.9070	0.9192	0.8971
0.3037	7.448	1400	0.3373	0.9237	0.9073	0.9200	0.8970
0.291	7.9813	1500	0.3373	0.9223	0.9055	0.9196	0.8942
0.291	8.512	1600	0.3394	0.9233	0.9071	0.9189	0.8974
0.291	9.0427	1700	0.3379	0.9237	0.9075	0.9194	0.8976
0.291	9.576	1800	0.3386	0.923	0.9068	0.9180	0.8974

RonTon05/PhishLang_PhoBERTCNN_15k

PhishLang_PhoBERTCNN_15k