lamaabdulaziz
commited on
Commit
•
260341e
1
Parent(s):
f075d07
update model card README.md
Browse files
README.md
CHANGED
@@ -17,11 +17,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [aubmindlab/araelectra-base-discriminator](https://huggingface.co/aubmindlab/araelectra-base-discriminator) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Macro F1: 0.
|
22 |
-
- Accuracy: 0.
|
23 |
-
- Precision: 0.
|
24 |
-
- Recall: 0.
|
25 |
|
26 |
## Model description
|
27 |
|
@@ -40,23 +40,24 @@ More information needed
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
-
- learning_rate:
|
44 |
- train_batch_size: 16
|
45 |
-
- eval_batch_size:
|
46 |
- seed: 123
|
47 |
- gradient_accumulation_steps: 2
|
48 |
- total_train_batch_size: 32
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
-
- num_epochs:
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | Precision | Recall |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
|
|
60 |
|
61 |
|
62 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [aubmindlab/araelectra-base-discriminator](https://huggingface.co/aubmindlab/araelectra-base-discriminator) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.2410
|
21 |
+
- Macro F1: 0.9174
|
22 |
+
- Accuracy: 0.9197
|
23 |
+
- Precision: 0.9159
|
24 |
+
- Recall: 0.9191
|
25 |
|
26 |
## Model description
|
27 |
|
|
|
40 |
### Training hyperparameters
|
41 |
|
42 |
The following hyperparameters were used during training:
|
43 |
+
- learning_rate: 3e-05
|
44 |
- train_batch_size: 16
|
45 |
+
- eval_batch_size: 16
|
46 |
- seed: 123
|
47 |
- gradient_accumulation_steps: 2
|
48 |
- total_train_batch_size: 32
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: linear
|
51 |
+
- num_epochs: 4
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Accuracy | Precision | Recall |
|
56 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:---------:|:------:|
|
57 |
+
| 0.1488 | 1.0 | 798 | 0.2533 | 0.9109 | 0.9125 | 0.9078 | 0.9179 |
|
58 |
+
| 0.1264 | 2.0 | 1596 | 0.2410 | 0.9174 | 0.9197 | 0.9159 | 0.9191 |
|
59 |
+
| 0.145 | 3.0 | 2394 | 0.2779 | 0.9083 | 0.9117 | 0.9107 | 0.9064 |
|
60 |
+
| 0.0934 | 4.0 | 3192 | 0.2858 | 0.9171 | 0.9199 | 0.9179 | 0.9163 |
|
61 |
|
62 |
|
63 |
### Framework versions
|