Ebtihal
/

AraBertMo_base_V8

Inference Endpoints

Model card Files Files and versions Community

Ebtihal commited on Mar 21, 2022

Commit

cba1665

·

1 Parent(s): 048413f

Update README.md

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -16,6 +16,7 @@ widget:
 `AraBertMo_base_V8' model was pre-trained on ~3 million words: [OSCAR](https://traces1.inria.fr/oscar/) - Arabic version "unshuffled_deduplicated_ar".
 ## Training results
 this model achieves the following results:
 | Task | Num examples | Num Epochs  | Batch Size | steps | Wall time  | training loss|
 |:----:|:----:|:----:|:----:|:-----:|:----:|:-----:|
 | Fill-Mask| 40032|  8  | 64 | 5008  | 10h 5m 57s | 7.2367  |

 `AraBertMo_base_V8' model was pre-trained on ~3 million words: [OSCAR](https://traces1.inria.fr/oscar/) - Arabic version "unshuffled_deduplicated_ar".
 ## Training results
 this model achieves the following results:
 | Task | Num examples | Num Epochs  | Batch Size | steps | Wall time  | training loss|
 |:----:|:----:|:----:|:----:|:-----:|:----:|:-----:|
 | Fill-Mask| 40032|  8  | 64 | 5008  | 10h 5m 57s | 7.2367  |