PhobertLexicalHostingMeta-v11_14_2024

This model is a fine-tuned version of vinai/phobert-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

Model description

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

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: 20

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.6211	100	1.9279	0.7977	0.5812
1.1694	1.2422	200	0.2518	0.9227	0.7147
1.1694	1.8634	300	0.3123	0.8991	0.6752
0.9066	2.4845	400	0.3268	0.8905	0.6802
0.7239	3.1056	500	0.2673	0.9075	0.7024
0.7239	3.7267	600	0.2586	0.9104	0.6931
0.6778	4.3478	700	0.5058	0.8618	0.6411
0.6778	4.9689	800	0.2765	0.9104	0.6989
0.8308	5.5901	900	0.2210	0.9286	0.7346
0.6671	6.2112	1000	0.2969	0.9142	0.7044
0.6671	6.8323	1100	0.2703	0.9248	0.7257
0.6693	7.4534	1200	1.1115	0.8763	0.6646
0.4595	8.0745	1300	0.3775	0.8763	0.6575
0.4595	8.6957	1400	0.3518	0.9066	0.7050
0.4777	9.3168	1500	0.3372	0.9107	0.7032
0.4777	9.9379	1600	0.3355	0.9079	0.7044
0.5556	10.5590	1700	0.3375	0.9210	0.7281
0.4535	11.1801	1800	0.4279	0.8937	0.6906
0.4535	11.8012	1900	0.3980	0.9059	0.7012
0.3419	12.4224	2000	0.3628	0.9107	0.7121
0.5153	13.0435	2100	0.3750	0.9082	0.7049
0.5153	13.6646	2200	0.4046	0.9057	0.7055
0.5357	14.2857	2300	0.3281	0.9275	0.7314
0.5357	14.9068	2400	0.4413	0.8892	0.6879
0.4949	15.5280	2500	0.4054	0.8940	0.6817
0.4613	16.1491	2600	0.3914	0.9076	0.7035
0.4613	16.7702	2700	0.3740	0.9137	0.7118
0.3909	17.3913	2800	0.4084	0.9068	0.7030
0.2968	18.0124	2900	0.3745	0.9130	0.7120
0.2968	18.6335	3000	0.4066	0.9059	0.7047
0.3972	19.2547	3100	0.3913	0.9107	0.7086
0.3972	19.8758	3200	0.3926	0.9107	0.7086