multicfe CDA
Collection
base and CDA cross- and multilingual mbert-based models trained on XNLI and sib200
•
16 items
•
Updated
YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
SIB200 CDA Model with Qwen
This model was trained on the SIB200 dataset using Counterfactual Data Augmentation (CDA) with counterfactuals generated by Qwen.
Training Parameters
- Dataset: SIB200
- Mode: CDA
- Selection Model: Qwen
- Selection Method: Random
- Train Size: 700 examples
- Epochs: 20
- Batch Size: 8
- Effective Batch Size: 32 (batch_size * gradient_accumulation_steps)
- Learning Rate: 8e-06
- Patience: 8
- Max Length: 192
- Gradient Accumulation Steps: 4
- Warmup Ratio: 0.1
- Weight Decay: 0.01
- Optimizer: AdamW
- Scheduler: cosine_with_warmup
- Random Seed: 42
Performance
- Overall Accuracy: 77.61%
- Overall Loss: 0.0206
Language-Specific Performance
- English (EN): 85.86%
- German (DE): 84.85%
- Arabic (AR): 53.54%
- Spanish (ES): 88.89%
- Hindi (HI): 75.76%
- Swahili (SW): 76.77%
Model Information
- Base Model: bert-base-multilingual-cased
- Task: Topic Classification
- Languages: 6 languages (EN, DE, AR, ES, HI, SW)
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support