Commit
•
44106bc
1
Parent(s):
30aa00b
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,14 +12,18 @@ model-index:
|
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
-
# iva_mt_wslot-m2m100_418M-0.1.0
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
- Loss: 0.0176
|
| 20 |
- Bleu: 61.6249
|
| 21 |
- Gen Len: 21.157
|
| 22 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 23 |
## Model description
|
| 24 |
|
| 25 |
More information needed
|
|
@@ -30,7 +34,17 @@ More information needed
|
|
| 30 |
|
| 31 |
## Training and evaluation data
|
| 32 |
|
| 33 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
|
| 35 |
## Training procedure
|
| 36 |
|
|
|
|
| 12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
|
| 15 |
+
# iva_mt_wslot-m2m100_418M-0.1.0 en-pl
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [facebook/m2m100_418M](https://huggingface.co/facebook/m2m100_418M) on the [iva_mt_wslot](https://huggingface.co/datasets/cartesinus/iva_mt_wslot) dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
- Loss: 0.0176
|
| 20 |
- Bleu: 61.6249
|
| 21 |
- Gen Len: 21.157
|
| 22 |
|
| 23 |
+
On training set:
|
| 24 |
+
- translated train witout slots in input: 93.8200 Bleu
|
| 25 |
+
- translated train with slots in input: 70.5597 Bleu
|
| 26 |
+
|
| 27 |
## Model description
|
| 28 |
|
| 29 |
More information needed
|
|
|
|
| 34 |
|
| 35 |
## Training and evaluation data
|
| 36 |
|
| 37 |
+
## Dataset Composition (en-pl)
|
| 38 |
+
| Corpus | Train | Dev | Test |
|
| 39 |
+
|----------------------------------------------------------------------|--------|-------|-------|
|
| 40 |
+
| [Massive 1.1](https://huggingface.co/datasets/AmazonScience/massive) | 11514 | 2033 | 2974 |
|
| 41 |
+
| [Leyzer 0.2.0](https://github.com/cartesinus/leyzer/tree/0.2.0) | 3974 | 701 | 1380 |
|
| 42 |
+
| [OpenSubtitles from OPUS](https://opus.nlpl.eu/OpenSubtitles-v1.php) | 2329 | 411 | 500 |
|
| 43 |
+
| [KDE from OPUS](https://opus.nlpl.eu/KDE4.php) | 1154 | 241 | 241 |
|
| 44 |
+
| [CCMatrix from Opus](https://opus.nlpl.eu/CCMatrix.php) | 1096 | 232 | 237 |
|
| 45 |
+
| [Ubuntu from OPUS](https://opus.nlpl.eu/Ubuntu.php) | 281 | 60 | 59 |
|
| 46 |
+
| [Gnome from OPUS](https://opus.nlpl.eu/GNOME.php) | 14 | 3 | 3 |
|
| 47 |
+
| *total* | 20362 | 3681 | 5394 |
|
| 48 |
|
| 49 |
## Training procedure
|
| 50 |
|