Downloads · 30 days
18
3% of all-time downloads
chrommium/xlm-roberta-large-finetuned-sent_in_news
xlm-roberta-large-finetuned-sent_in_news is a text classification model from chrommium. Use it when you need a label for a piece of text. 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
18
3% of all-time downloads
All-time downloads
703
Public
Repo size
6.7 GB
Likes
0
Public
Click a slice to open those files.
.bin2.2 GB · 100%
From the Hugging Face model README
This model is a fine-tuned version of xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:
Модель ассиметрична, реагирует на метку X в тексте новости. Попробуйте следующие примеры:
a) Агентство X понизило рейтинг банка Fitch.
b) Агентство Fitch понизило рейтинг банка X.
a) Компания Финам показала рекордную прибыль, говорят аналитики компании X. b) Компания X показала рекордную прибыль, говорят аналитики компании Финам.
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|---|---|---|---|---|---|
| No log | 1.0 | 106 | 1.2526 | 0.6108 | 0.1508 |
| No log | 2.0 | 212 | 1.1553 | 0.6648 | 0.1141 |
| No log | 3.0 | 318 | 1.1150 | 0.6591 | 0.1247 |
| No log | 4.0 | 424 | 1.0007 | 0.6705 | 0.1383 |
| 1.1323 | 5.0 | 530 | 0.9267 | 0.6733 | 0.2027 |
| 1.1323 | 6.0 | 636 | 1.0869 | 0.6335 | 0.4084 |
| 1.1323 | 7.0 | 742 | 1.1224 | 0.6932 | 0.4586 |
| 1.1323 | 8.0 | 848 | 1.2535 | 0.6307 | 0.3424 |
| 1.1323 | 9.0 | 954 | 1.4288 | 0.6932 | 0.4881 |
| 0.5252 | 10.0 | 1060 | 1.5856 | 0.6932 | 0.4739 |
| 0.5252 | 11.0 | 1166 | 1.7101 | 0.6733 | 0.4530 |
| 0.5252 | 12.0 | 1272 | 1.7330 | 0.6903 | 0.4750 |
| 0.5252 | 13.0 | 1378 | 1.8872 | 0.7273 | 0.5125 |
| 0.5252 | 14.0 | 1484 | 1.8797 | 0.7301 | 0.5033 |
| 0.1252 | 15.0 | 1590 | 1.9339 | 0.7330 | 0.5024 |
| 0.1252 | 16.0 | 1696 | 1.9632 | 0.7301 | 0.4967 |