pm
commited on
Commit
•
be4057b
1
Parent(s):
5ec3b79
Update README.md
Browse files
README.md
CHANGED
|
@@ -23,8 +23,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 23 |
|
| 24 |
# go-emotions-fine-tuned-distilroberta
|
| 25 |
|
| 26 |
-
This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on
|
| 27 |
-
It achieves the following results on the evaluation set:
|
| 28 |
- Loss: 0.0841
|
| 29 |
- Micro Precision: 0.6789
|
| 30 |
- Micro Recall: 0.5047
|
|
@@ -37,20 +37,6 @@ It achieves the following results on the evaluation set:
|
|
| 37 |
- Weighted F1: 0.5577
|
| 38 |
- Hamming Loss: 0.0308
|
| 39 |
|
| 40 |
-
## Model description
|
| 41 |
-
|
| 42 |
-
More information needed
|
| 43 |
-
|
| 44 |
-
## Intended uses & limitations
|
| 45 |
-
|
| 46 |
-
More information needed
|
| 47 |
-
|
| 48 |
-
## Training and evaluation data
|
| 49 |
-
|
| 50 |
-
More information needed
|
| 51 |
-
|
| 52 |
-
## Training procedure
|
| 53 |
-
|
| 54 |
### Training hyperparameters
|
| 55 |
|
| 56 |
The following hyperparameters were used during training:
|
|
|
|
| 23 |
|
| 24 |
# go-emotions-fine-tuned-distilroberta
|
| 25 |
|
| 26 |
+
This model is a fine-tuned version of [distilbert/distilroberta-base](https://huggingface.co/distilbert/distilroberta-base) on GoEmotions dataset.
|
| 27 |
+
It achieves the following results on the evaluation set (threshold = 0.5):
|
| 28 |
- Loss: 0.0841
|
| 29 |
- Micro Precision: 0.6789
|
| 30 |
- Micro Recall: 0.5047
|
|
|
|
| 37 |
- Weighted F1: 0.5577
|
| 38 |
- Hamming Loss: 0.0308
|
| 39 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
### Training hyperparameters
|
| 41 |
|
| 42 |
The following hyperparameters were used during training:
|