Downloads · 30 days
10
12% of all-time downloads
mayaj5/opus-mt-en-lg-finetuned-English-to-Luganda
opus-mt-en-lg-finetuned-English-to-Luganda is a machine learning model from mayaj5. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
10
12% of all-time downloads
All-time downloads
83
Public
Parameters
75.1M
2.1 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors301 MB · 99%
From the Hugging Face model README
This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-lg 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 | Bleu | Gen Len |
|---|---|---|---|---|---|
| No log | 1.0 | 64 | 0.4512 | 77.4782 | 6.0618 |
| No log | 2.0 | 128 | 0.3856 | 81.5076 | 6.1011 |
| No log | 3.0 | 192 | 0.3798 | 77.0572 | 6.1124 |
| No log | 4.0 | 256 | 0.3736 | 86.2867 | 6.0169 |
| No log | 5.0 | 320 | 0.3487 | 86.1799 | 5.9719 |
| No log | 6.0 | 384 | 0.3469 | 83.0195 | 5.9831 |
| No log | 7.0 | 448 | 0.3436 | 88.8664 | 5.8876 |
| 0.2566 | 8.0 | 512 | 0.3264 | 81.0767 | 5.927 |
| 0.2566 | 9.0 | 576 | 0.3007 | 80.781 | 6.0112 |
| 0.2566 | 10.0 | 640 | 0.3027 | 89.7888 | 5.8427 |
| 0.2566 | 11.0 | 704 | 0.3114 | 87.3083 | 5.9944 |
| 0.2566 | 12.0 | 768 | 0.2978 | 81.3439 | 5.9775 |
| 0.2566 | 13.0 | 832 | 0.2869 | 80.9199 | 6.0281 |
| 0.2566 | 14.0 | 896 | 0.2751 | 82.9235 | 6.0337 |
| 0.2566 | 15.0 | 960 | 0.2836 | 84.7659 | 5.9326 |
| 0.1005 | 16.0 | 1024 | 0.2907 | 91.5857 | 5.8146 |
| 0.1005 | 17.0 | 1088 | 0.2952 | 86.9909 | 5.927 |
| 0.1005 | 18.0 | 1152 | 0.2935 | 88.0386 | 5.8876 |
| 0.1005 | 19.0 | 1216 | 0.2919 | 92.3533 | 5.8202 |
| 0.1005 | 20.0 | 1280 | 0.2911 | 85.7675 | 5.8989 |