ViGLUE
Collection
A collection to store all the artifacts of the paper: ViGLUE: A Vietnamese General Language Understanding Benchmark and Analysis of Vietnamese LMs.
•
145 items
•
Updated
This model is a fine-tuned version of bert-base-multilingual-cased on the tmnam20/VieGLUE/MNLI dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
0.6369 | 0.41 | 5000 | 0.6399 | 0.7401 |
0.5945 | 0.81 | 10000 | 0.5746 | 0.7680 |
0.4847 | 1.22 | 15000 | 0.5817 | 0.7773 |
0.5109 | 1.63 | 20000 | 0.5680 | 0.7790 |
0.3754 | 2.04 | 25000 | 0.5796 | 0.7890 |
0.3989 | 2.44 | 30000 | 0.5581 | 0.7892 |
0.4013 | 2.85 | 35000 | 0.5501 | 0.7955 |
Base model
google-bert/bert-base-multilingual-cased