Modelpublic

pqthinh232/HCMUS-phobert-vietnamese-restaurant-sentiment-analysis

sourceHugging Facemitupdated 6mo agoView on Hugging Face

0likes29downloads

Model Card

HCMUS-phobert-vietnamese-restaurant-sentiment-analysis

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

—Loss: 0.4611
—Accuracy: 0.8863
—F1: 0.8604

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

—learning_rate: 2e-05
—trainbatchsize: 16
—evalbatchsize: 16
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.4982	0.1222	200	0.3764	0.8731	0.8424
0.3940	0.2445	400	0.3521	0.8860	0.8546
0.3724	0.3667	600	0.5267	0.8676	0.8086
0.3917	0.4890	800	0.3354	0.8676	0.8411
0.3471	0.6112	1000	0.3149	0.8670	0.8485
0.3933	0.7335	1200	0.3361	0.8951	0.8648
0.3404	0.8557	1400	0.3083	0.8826	0.8592
0.3327	0.9780	1600	0.2888	0.8869	0.8674
0.2984	1.1002	1800	0.3315	0.9016	0.8753
0.2923	1.2225	2000	0.3172	0.8692	0.8563
0.2716	1.3447	2200	0.3403	0.8936	0.8674
0.3105	1.4670	2400	0.3192	0.8921	0.8689
0.3007	1.5892	2600	0.3127	0.8899	0.8666
0.2747	1.7115	2800	0.3107	0.8967	0.8739
0.2653	1.8337	3000	0.3615	0.8997	0.8719
0.2515	1.9560	3200	0.3425	0.9025	0.8771
0.1740	2.0782	3400	0.3909	0.9022	0.8750
0.1925	2.2005	3600	0.3693	0.9019	0.8769
0.2424	2.3227	3800	0.3650	0.9000	0.8756
0.1503	2.4450	4000	0.4356	0.9034	0.8745
0.1694	2.5672	4200	0.3934	0.9031	0.8786
0.1957	2.6895	4400	0.4115	0.9034	0.8772
0.2120	2.8117	4600	0.3684	0.8988	0.8757
0.1872	2.9340	4800	0.3893	0.9019	0.8767

Framework versions

—Transformers 5.0.0
—Pytorch 2.10.0+cu128
—Datasets 4.0.0
—Tokenizers 0.22.2