update model card README.md
Browse files
README.md
CHANGED
|
@@ -2,6 +2,9 @@
|
|
| 2 |
base_model: aubmindlab/bert-large-arabertv02-twitter
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: Araberv2_large
|
| 7 |
results: []
|
|
@@ -12,7 +15,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# Araberv2_large
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [aubmindlab/bert-large-arabertv02-twitter](https://huggingface.co/aubmindlab/bert-large-arabertv02-twitter) on
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
@@ -39,6 +48,20 @@ The following hyperparameters were used during training:
|
|
| 39 |
- lr_scheduler_type: linear
|
| 40 |
- num_epochs: 15
|
| 41 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
### Framework versions
|
| 43 |
|
| 44 |
- Transformers 4.31.0
|
|
|
|
| 2 |
base_model: aubmindlab/bert-large-arabertv02-twitter
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- f1
|
| 7 |
+
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: Araberv2_large
|
| 10 |
results: []
|
|
|
|
| 15 |
|
| 16 |
# Araberv2_large
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [aubmindlab/bert-large-arabertv02-twitter](https://huggingface.co/aubmindlab/bert-large-arabertv02-twitter) on the None dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.3745
|
| 21 |
+
- F1: 0.5436
|
| 22 |
+
- F1 Macro: 0.1187
|
| 23 |
+
- Roc Auc: 0.7222
|
| 24 |
+
- Accuracy: 0.5531
|
| 25 |
|
| 26 |
## Model description
|
| 27 |
|
|
|
|
| 48 |
- lr_scheduler_type: linear
|
| 49 |
- num_epochs: 15
|
| 50 |
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | F1 Macro | Roc Auc | Accuracy |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:--------:|:-------:|:--------:|
|
| 55 |
+
| 0.3412 | 1.0 | 507 | 0.3815 | 0.5436 | 0.1187 | 0.7222 | 0.5531 |
|
| 56 |
+
| 0.3775 | 2.0 | 1014 | 0.3745 | 0.5436 | 0.1187 | 0.7222 | 0.5531 |
|
| 57 |
+
| 0.3768 | 3.0 | 1521 | 0.3914 | 0.5436 | 0.1187 | 0.7222 | 0.5531 |
|
| 58 |
+
| 0.3764 | 4.0 | 2028 | 0.3745 | 0.5436 | 0.1187 | 0.7222 | 0.5531 |
|
| 59 |
+
| 0.3714 | 5.0 | 2535 | 0.3870 | 0.5436 | 0.1187 | 0.7222 | 0.5531 |
|
| 60 |
+
| 0.3697 | 6.0 | 3042 | 0.3835 | 0.5436 | 0.1187 | 0.7222 | 0.5531 |
|
| 61 |
+
| 0.3688 | 7.0 | 3549 | 0.4026 | 0.5436 | 0.1187 | 0.7222 | 0.5531 |
|
| 62 |
+
| 0.3654 | 8.0 | 4056 | 0.4771 | 0.5436 | 0.1187 | 0.7222 | 0.5531 |
|
| 63 |
+
|
| 64 |
+
|
| 65 |
### Framework versions
|
| 66 |
|
| 67 |
- Transformers 4.31.0
|