Commit ·
a5afd99
1
Parent(s): a2ba7f8
Update Readme.md
Browse files
README.md
CHANGED
|
@@ -19,6 +19,7 @@ metrics:
|
|
| 19 |
This model was created by finetuning the mBERT model for the downstream task of Hate speech detection for the Amharic language.
|
| 20 |
The initial mBERT model used for finetuning is Davlan/bert-base-multilingual-cased-finetuned-amharic which was provided by Davlan on Huggingface.
|
| 21 |
The model was fine-tuned using HuggingFace's Trainer API. The final result of the finetuning has an F1-score of 0.9172 and an accuracy of 91.59%.
|
|
|
|
| 22 |
|
| 23 |
**Dataset description**
|
| 24 |
The finetuning was done on an Amharic Dataset that was made available by Mendeley Data (https://data.mendeley.com/datasets/ymtmxx385m). It has a size of 30,000 rows.
|
|
|
|
| 19 |
This model was created by finetuning the mBERT model for the downstream task of Hate speech detection for the Amharic language.
|
| 20 |
The initial mBERT model used for finetuning is Davlan/bert-base-multilingual-cased-finetuned-amharic which was provided by Davlan on Huggingface.
|
| 21 |
The model was fine-tuned using HuggingFace's Trainer API. The final result of the finetuning has an F1-score of 0.9172 and an accuracy of 91.59%.
|
| 22 |
+
The model was finetuned with 15 epochs and a learning rate of 0.00005.
|
| 23 |
|
| 24 |
**Dataset description**
|
| 25 |
The finetuning was done on an Amharic Dataset that was made available by Mendeley Data (https://data.mendeley.com/datasets/ymtmxx385m). It has a size of 30,000 rows.
|