phobert-base-v2-vinli

This model is a fine-tuned version of FacebookAI/xlm-roberta-base on the None 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:

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.7633	0.9515	1000	0.7920	0.6440	0.6434	0.6504	0.6440
0.6055	1.9029	2000	0.7411	0.6943	0.6935	0.6939	0.6943
0.471	2.8544	3000	0.8055	0.7049	0.7033	0.7035	0.7049
0.3809	3.8059	4000	0.9021	0.7045	0.7014	0.7064	0.7045
0.3057	4.7574	5000	0.9746	0.7045	0.7055	0.7087	0.7045
0.2228	5.7088	6000	1.0864	0.7173	0.7160	0.7172	0.7173
0.1727	6.6603	7000	1.1915	0.7217	0.7204	0.7213	0.7217
0.1459	7.6118	8000	1.3036	0.7213	0.7206	0.7218	0.7213
0.1395	8.5633	9000	1.3762	0.7195	0.7197	0.7202	0.7195
0.0993	9.5147	10000	1.4585	0.7226	0.7224	0.7226	0.7226

Loading…