opus-mt-sw-en-finetuned

This model performs translation trained using MLflow and deployed on Hugging Face.

Model Details

• Model Name: opus-mt-sw-en-finetuned
• Version: 7
• Task: Translation
• Languages: sw,en
• Framework: pytorch
• License: apache-2.0

Intended Uses & Limitations

Intended Uses

• Translation tasks
• Research and development
• Child helpline services support

Limitations

• Performance may vary on out-of-distribution data
• Should be evaluated on your specific use case before production deployment
• Designed for child helpline contexts, may need adaptation for other domains

Training Data

• Dataset: synthetic.jsonl
• Size: Not specified
• Languages: sw,en

Training Configuration

Parameter	Value
Dataset Config Auto Segment Long Sequences	True
Dataset Config Max Length Ratio	2.5
Dataset Config Max Samples	None
Dataset Config Min Length	3
Dataset Config Primary Dataset	custom
Dataset Config Segment Max Tokens	400
Dataset Config Segment Overlap Tokens	100
Dataset Config Validation Split	0.1
Evaluation Config Inference Test Frequency	every_eval
Evaluation Config Run Inference Validation	True
Evaluation Config Test Size	500
Language Name	Swahili
Language Pair	sw-en
Max Length	512
Model Name	Helsinki-NLP/opus-mt-mul-en
Total Parameters	77518848
Trainable Parameters	76994560
Training Config Batch Size	16
Training Config Dataloader Num Workers	4
Training Config Early Stopping Patience	3
Training Config Early Stopping Threshold	0.001
Training Config Eval Steps	500
Training Config Eval Strategy	steps
Training Config Generation Length Penalty	0.85
Training Config Generation Max Length	128
Training Config Generation No Repeat Ngram Size	3
Training Config Generation Num Beams	4
Training Config Generation Repetition Penalty	1.0
Training Config Generation Top K	50
Training Config Gradient Accumulation Steps	2
Training Config Learning Rate	2e-05
Training Config Logging Steps	50
Training Config Lr Scheduler	cosine_with_restarts
Training Config Max Length	512
Training Config Mixed Precision	fp16
Training Config Num Epochs	10
Training Config Pin Memory	True
Training Config Save Strategy	epoch
Training Config Warmup Steps	1000
Training Config Weight Decay	0.01
Vocab Size	64172

Performance Metrics

Evaluation Results

Metric	Value
Baseline Bleu	0.0145
Baseline Chrf	16.4877
Baseline Hallucination Rate	0.0050
Baseline Keyword Preservation	0.0983
Baseline Urgency Preservation	0.3019
Bleu Improvement	0.4410
Bleu Improvement Percent	3051.3105
Chrf Improvement	42.8156
Chrf Improvement Percent	259.6828
Epoch	10.0000
Eval Bertscore F1	0.9432
Eval Bleu	0.4555
Eval Chrf	59.3032
Eval Loss	0.1448
Eval Meteor	0.5747
Eval Runtime	106.5231
Eval Samples Per Second	11.0210
Eval Steps Per Second	0.6950
Final Epoch	10.0000
Final Eval Bertscore F1	0.9432
Final Eval Bleu	0.4555
Final Eval Chrf	59.3032
Final Eval Loss	0.1448
Final Eval Meteor	0.5747
Final Eval Runtime	106.5231
Final Eval Samples Per Second	11.0210
Final Eval Steps Per Second	0.6950
Grad Norm	0.8218
Inference Test/Abuse Reporting Success	1.0000
Inference Test/Code Switching Success	1.0000
Inference Test/Emergency Success	1.0000
Inference Test/Emotional Distress Success	1.0000
Inference Test/Empty Input Success	1.0000
Inference Test/Fragmented Trauma Success	1.0000
Inference Test/Help Request Success	1.0000
Inference Test/Incomplete Success	1.0000
Inference Test/Location Info Success	1.0000
Inference Test/Numbers Preservation Success	0.0000
Inference Test/Simple Greeting Success	1.0000
Inference Test/Whitespace Only Success	1.0000
Inference Validation Pass Rate	0.9167
Learning Rate	0.0000
Loss	0.1418
Total Flos	11212302632878080.0000
Total Samples	11732.0000
Train Loss	0.3851
Train Runtime	1770.8962
Train Samples	10558.0000
Train Samples Per Second	59.6200
Train Steps Per Second	1.8630
Validation Samples	1174.0000

Usage

Installation

pip install transformers torch

Translation Example

from transformers import pipeline

translator = pipeline("translation", model="marlonbino/opus-mt-sw-en-finetuned")
result = translator("Your text here")
print(result[0]["translation_text"])

MLflow Tracking

• Experiment: translation-sw-en
• Run ID: 618fb8990ea248d18259b61c18b9017a
• Training Date: 2025-10-31 21:38:14
• Tracking URI: http://192.168.10.6:5000

Training Metrics Visualization

View detailed training metrics and TensorBoard logs in the Training metrics tab.

Citation

@misc{opus_mt_sw_en_finetuned,
  title={opus-mt-sw-en-finetuned},
  author={OpenCHS Team},
  year={2025},
  publisher={Hugging Face},
  url={https://huggingface.co/marlonbino/opus-mt-sw-en-finetuned}
}

Contact

info@bitz-itc.com

---

Model card auto-generated from MLflow