DS200.Q21 - Big Data Analysis - Group 2
Collection
DS200 Course Project (Group 02): Reimplementation and Improvement of ViHateT5 for Vietnamese Hate Speech Detection • 9 items • Updated
How to use NCPhat2005/focal_loss_exp with Transformers:
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("NCPhat2005/focal_loss_exp")
model = AutoModelForSeq2SeqLM.from_pretrained("NCPhat2005/focal_loss_exp")This model was trained from scratch on the None 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 | F1 Macro | Gen Len |
|---|---|---|---|---|---|
| 0.1329 | 1.0 | 2494 | 0.1170 | 33.0589 | 5.9413 |
| 0.11 | 2.0 | 4988 | 0.1038 | 32.2483 | 6.0022 |
| 0.0883 | 3.0 | 7482 | 0.1142 | 32.1053 | 6.0029 |