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/SST2 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 |
---|---|---|---|---|
0.3821 | 0.24 | 500 | 0.3799 | 0.8314 |
0.3198 | 0.48 | 1000 | 0.4079 | 0.8417 |
0.272 | 0.71 | 1500 | 0.3721 | 0.8670 |
0.2847 | 0.95 | 2000 | 0.3885 | 0.8567 |
0.1893 | 1.19 | 2500 | 0.4329 | 0.8589 |
0.2124 | 1.43 | 3000 | 0.4133 | 0.8532 |
0.2208 | 1.66 | 3500 | 0.3665 | 0.8773 |
0.2219 | 1.9 | 4000 | 0.4164 | 0.8601 |
0.1562 | 2.14 | 4500 | 0.4350 | 0.8635 |
0.1399 | 2.38 | 5000 | 0.4571 | 0.8761 |
0.1399 | 2.61 | 5500 | 0.4346 | 0.8796 |
0.1403 | 2.85 | 6000 | 0.4325 | 0.8819 |
Base model
google-bert/bert-base-multilingual-cased