Beta
Explore
Marketplace
Neural Labs
Chat
Wallet
Docs
xnli_mbert_cda_gemma_crosslingual – AI Model by fledor | AlphaNeural AI
You can deploy this model and start earning money today!
fledor
/
xnli_mbert_cda_gemma_crosslingual
like
0
safetensors
bert
us
Views
No views yet
Model card
Files and Versions
Community
API
Deploy
XNLI CDA Model with Gemma (Cross-Lingual)
This model was trained on the XNLI dataset using Counterfactual Data Augmentation (CDA) with counterfactuals generated by Gemma.
Training Parameters
Dataset
: XNLI
Mode
: CDA
Selection Model
: Gemma
Selection Method
: Random
Cross Lingual
: true
Train Size
: 2400 examples
Epochs
: 8
Batch Size
: 16
Effective Batch Size
: 64 (batch_size * gradient_accumulation_steps)
Learning Rate
: 1e-05
Patience
: 6
Max Length
: 256
Gradient Accumulation Steps
: 4
Warmup Ratio
: 0.1
Weight Decay
: 0.01
Optimizer
: AdamW
Scheduler
: cosine_with_warmup
Random Seed
: 42
Performance
Overall Accuracy
: 58.96%
Overall Loss
: 0.0161
Language-Specific Performance
English (EN)
: 71.66%
German (DE)
: 62.53%
Arabic (AR)
: 56.01%
Spanish (ES)
: 64.35%
Hindi (HI)
: 52.38%
Swahili (SW)
: 46.81%
Model Information
Base Model
: bert-base-multilingual-cased
Task
: Natural Language Inference
Languages
: 6 languages (EN, DE, AR, ES, HI, SW)
