Downloads · 30 days
5
1% of all-time downloads
Shamus/mbart-large-50-many-to-many-mmt-finetuned-acw-to-en
mbart-large-50-many-to-many-mmt-finetuned-acw-to-en is a machine learning model from Shamus. 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.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
5
1% of all-time downloads
All-time downloads
350
Public
Repo size
7.4 GB
Likes
0
Public
Click a slice to open those files.
.bin2.4 GB · 99%
From the Hugging Face model README
This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt 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 |
|---|---|---|---|---|---|
| 1.4657 | 1.0 | 816 | 1.1739 | 30.1212 | 32.868 |
| 0.8541 | 2.0 | 1632 | 1.1190 | 33.0098 | 32.808 |
| 0.6176 | 3.0 | 2448 | 1.1681 | 33.3634 | 32.756 |
| 0.3397 | 4.0 | 3264 | 1.3327 | 33.2941 | 33.6 |
| 0.2227 | 5.0 | 4080 | 1.4211 | 33.9298 | 33.128 |
| 0.1597 | 6.0 | 4896 | 1.5157 | 34.7405 | 33.496 |
| 0.1426 | 6.13 | 5000 | 1.5204 | 34.8213 | 33.544 |