ShihHsuanChen/deberta-v3-emotion

Training

• Code: Training Notebook

• Criteria: Best validation loss

• Training configuration:

  {
    "seed": 567,
    "ddp": true,
    "learning_rate": 5e-05,
    "train_batch_size": 80,
    "valid_batch_size": 80,
    "lr_scheduler_type": "linear",
    "num_epochs": 20,
    "num_warmup_steps": 125,
    "max_train_steps": null,
    "max_valid_steps": null,
    "max_length": 72
  }
  

Evaluation

• Code: Evaluation Notebook
• Results

  	sadness	joy	love	anger	fear	surprise	Total (Macro)
  Accuracy	0.985420	0.965309	0.974359	0.983912	0.980392	0.985923	0.979219
  Precision	0.966102	0.936709	0.858108	0.980159	0.868526	1.000000	0.934934
  Recall	0.984456	0.965217	0.808917	0.901460	0.973214	0.569231	0.867083
  F1-Score	0.975192	0.950749	0.832787	0.939163	0.917895	0.725490	0.890213