Instructions to use SMG0/Model4_arabertv2_base_T2_WS_A100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SMG0/Model4_arabertv2_base_T2_WS_A100 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="SMG0/Model4_arabertv2_base_T2_WS_A100")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("SMG0/Model4_arabertv2_base_T2_WS_A100") model = AutoModelForSequenceClassification.from_pretrained("SMG0/Model4_arabertv2_base_T2_WS_A100", device_map="auto") - Notebooks
- Google Colab
- Kaggle
update model card README.md
Browse files
README.md
CHANGED
|
@@ -17,10 +17,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02-twitter](https://huggingface.co/aubmindlab/bert-base-arabertv02-twitter) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- F1: 0.
|
| 22 |
-
- Roc Auc: 0.
|
| 23 |
-
- Accuracy: 0.
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
@@ -51,15 +51,11 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
|
| 54 |
-
| No log | 1.0 | 193 | 0.
|
| 55 |
-
| No log | 2.0 | 386 | 0.
|
| 56 |
-
| 0.
|
| 57 |
-
| 0.
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.0318 | 6.0 | 1158 | 0.0669 | 0.8467 | 0.9197 | 0.7579 |
|
| 60 |
-
| 0.0318 | 7.0 | 1351 | 0.0686 | 0.8471 | 0.9190 | 0.7672 |
|
| 61 |
-
| 0.0141 | 8.0 | 1544 | 0.0705 | 0.8493 | 0.9259 | 0.7561 |
|
| 62 |
-
| 0.0141 | 9.0 | 1737 | 0.0732 | 0.8450 | 0.9248 | 0.7486 |
|
| 63 |
|
| 64 |
|
| 65 |
### Framework versions
|
|
|
|
| 17 |
|
| 18 |
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02-twitter](https://huggingface.co/aubmindlab/bert-base-arabertv02-twitter) on the None dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.0694
|
| 21 |
+
- F1: 0.8430
|
| 22 |
+
- Roc Auc: 0.9128
|
| 23 |
+
- Accuracy: 0.7523
|
| 24 |
|
| 25 |
## Model description
|
| 26 |
|
|
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:-------:|:--------:|
|
| 54 |
+
| No log | 1.0 | 193 | 0.0694 | 0.8430 | 0.9128 | 0.7523 |
|
| 55 |
+
| No log | 2.0 | 386 | 0.0713 | 0.8489 | 0.9184 | 0.7598 |
|
| 56 |
+
| 0.0183 | 3.0 | 579 | 0.0779 | 0.8377 | 0.9226 | 0.7412 |
|
| 57 |
+
| 0.0183 | 4.0 | 772 | 0.0727 | 0.8455 | 0.9181 | 0.7523 |
|
| 58 |
+
| 0.0183 | 5.0 | 965 | 0.0749 | 0.8555 | 0.9264 | 0.7672 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 59 |
|
| 60 |
|
| 61 |
### Framework versions
|