Update README.md
Browse files
README.md
CHANGED
@@ -7,4 +7,35 @@ pipeline_tag: token-classification
|
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
- f1
|
10 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
- f1
|
10 |
+
---
|
11 |
+
# AraBERT_Arabic_NER
|
12 |
+
|
13 |
+
|
14 |
+
This is fine tuned AraBERT model for Arabic NER
|
15 |
+
|
16 |
+
|
17 |
+
## Model description
|
18 |
+
|
19 |
+
More information needed
|
20 |
+
|
21 |
+
## Intended uses & limitations
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Training and evaluation results
|
26 |
+
Train Loss Val Loss Accuracy Precision Recall F1
|
27 |
+
No log 0.168362 0.960146 0.781193 0.756899 0.768854
|
28 |
+
No log 0.142247 0.967788 0.823397 0.798511 0.810763
|
29 |
+
No log 0.144166 0.969069 0.830401 0.806395 0.818222
|
30 |
+
No log 0.144989 0.970229 0.827586 0.819974 0.823762
|
31 |
+
0.211600 0.151844 0.970950 0.836991 0.818660 0.827724
|
32 |
+
0.211600 0.152624 0.970990 0.835268 0.819536 0.827327
|
33 |
+
0.211600 0.154714 0.971110 0.833037 0.821726 0.827343
|
34 |
+
0.211600 0.157353 0.970629 0.834449 0.819098 0.826702
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- optimizer: None
|
41 |
+
- training_precision: float32
|