Downloads · 30 days
95
52% of all-time downloads
nadzma/finetuned-mbart-v1-french-financial-summarization
finetuned-mbart-v1-french-financial-summarization is a machine learning model from nadzma. 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 mit.
should probably proofread and complete it, then remove this comment. --
Downloads · 30 days
95
52% of all-time downloads
All-time downloads
182
Public
Repo size
24.5 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 on an unknown 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 | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Bertscore | Bartscore | Bleurt | Meteor | Frugal Score (mover-score) | Frugal Score (bert-score) | Cider | Infolm Kl Divergence | Infolm Beta Divergence | Infolm L1 Distance | Infolm Fisher Rao Distance | Baryscore | Depthscore |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1.3489 | 1.0 | 388 | 0.9959 | 45.6453 | 31.2339 | 36.5437 | 41.7876 | 159.3691 | 0.7311 | 0.5831 | -0.3653 | 0.3326 | 0.4541 | 0.4541 | 0.2323 | -2.0989 | 1.5257 | 1.2389 | 1.7286 | 0.8118 | 0.1227 |
| 0.836 | 2.0 | 776 | 0.9509 | 46.9348 | 33.3226 | 38.5367 | 43.0864 | 152.2215 | 0.7421 | 0.5972 | -0.2906 | 0.3501 | 0.4802 | 0.4802 | 0.4472 | -1.5779 | 1.1603 | 0.9542 | 1.329 | 0.8362 | 0.1166 |
| 0.6153 | 3.0 | 1164 | 0.9510 | 49.7629 | 36.0455 | 40.8611 | 46.0195 | 170.0604 | 0.7504 | 0.6153 | -0.2210 | 0.3748 | 0.5093 | 0.5093 | 0.3703 | -1.5389 | 1.1195 | 0.9292 | 1.2921 | 0.8161 | 0.1334 |
| 6.1788 | 4.0 | 1552 | 1.1890 | 40.9179 | 24.4059 | 30.1535 | 36.3914 | 167.7852 | 0.7071 | 0.5444 | -0.7406 | 0.2957 | 0.2925 | 0.2925 | 0.0460 | -2.2465 | 1.6575 | 1.33 | 1.8533 | 0.9048 | 0.1179 |
| 6.6481 | 5.0 | 1940 | 5.9645 | 11.6342 | 0.7536 | 10.1766 | 11.3151 | 200.0 | 0.5049 | 0.2574 | -1.1882 | 0.0749 | -0.0087 | -0.0087 | 0.0000 | -6.942 | 5.347 | 1.8469 | 2.7717 | 0.9615 | 0.1543 |
| 4.6219 | 6.0 | 2328 | 2.9868 | 12.4714 | 1.2543 | 8.486 | 10.1856 | 200.0 | 0.5724 | 0.3489 | -0.7434 | 0.0698 | 0.2279 | 0.2279 | 0.0003 | -3.565 | 2.4692 | 1.5029 | 2.102 | 0.867 | 0.1409 |
| 2.5282 | 7.0 | 2716 | 2.5885 | 16.7393 | 1.6982 | 10.6036 | 13.5492 | 200.0 | 0.5744 | 0.3796 | -0.8090 | 0.0944 | 0.2607 | 0.2607 | 0.0026 | -2.3701 | 1.6686 | 1.2963 | 1.8184 | 0.8225 | 0.1326 |
| 1.9088 | 8.0 | 3104 | 2.4646 | 23.4552 | 4.1879 | 14.2485 | 18.816 | 200.0 | 0.6232 | 0.4313 | -0.8844 | 0.1323 | 0.2590 | 0.2590 | 0.0024 | -2.5352 | 1.6674 | 1.3219 | 1.8474 | 0.7277 | 0.1317 |
| 1.7004 | 9.0 | 3492 | 2.5055 | 15.6022 | 1.3846 | 11.6503 | 13.5318 | 200.0 | 0.5677 | 0.3800 | -0.9227 | 0.0914 | 0.2617 | 0.2617 | 0.0014 | -2.7313 | 1.8038 | 1.3798 | 1.9433 | 0.8246 | 0.1477 |
| 1.5903 | 10.0 | 3880 | 2.5509 | 23.4083 | 2.7691 | 12.3471 | 19.1882 | 200.0 | 0.6309 | 0.4214 | -0.8686 | 0.1407 | 0.2754 | 0.2754 | 0.0041 | -2.5552 | 1.6615 | 1.3249 | 1.863 | 0.8097 | 0.1062 |