Commit
·
5c3cdd2
1
Parent(s):
6dbf5bb
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
metrics:
|
| 5 |
+
- precision
|
| 6 |
+
- recall
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: train
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# train
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [aubmindlab/bert-base-arabertv02](https://huggingface.co/aubmindlab/bert-base-arabertv02) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.8776
|
| 21 |
+
- Macro F1: 0.8019
|
| 22 |
+
- Precision: 0.8062
|
| 23 |
+
- Recall: 0.8128
|
| 24 |
+
- Kappa: 0.7158
|
| 25 |
+
- Accuracy: 0.8128
|
| 26 |
+
|
| 27 |
+
## Model description
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Intended uses & limitations
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training and evaluation data
|
| 36 |
+
|
| 37 |
+
More information needed
|
| 38 |
+
|
| 39 |
+
## Training procedure
|
| 40 |
+
|
| 41 |
+
### Training hyperparameters
|
| 42 |
+
|
| 43 |
+
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 2e-05
|
| 45 |
+
- train_batch_size: 16
|
| 46 |
+
- eval_batch_size: 128
|
| 47 |
+
- seed: 25
|
| 48 |
+
- gradient_accumulation_steps: 2
|
| 49 |
+
- total_train_batch_size: 32
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 15
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Macro F1 | Precision | Recall | Kappa | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
+
| No log | 1.0 | 101 | 1.1216 | 0.6286 | 0.5851 | 0.7094 | 0.5110 | 0.7094 |
|
| 59 |
+
| No log | 2.0 | 203 | 0.9280 | 0.6797 | 0.6829 | 0.7438 | 0.5734 | 0.7438 |
|
| 60 |
+
| No log | 3.0 | 304 | 0.8106 | 0.7296 | 0.7227 | 0.7759 | 0.6335 | 0.7759 |
|
| 61 |
+
| No log | 4.0 | 406 | 0.7705 | 0.7814 | 0.7822 | 0.8030 | 0.6985 | 0.8030 |
|
| 62 |
+
| 0.9926 | 5.0 | 507 | 0.7413 | 0.7792 | 0.7719 | 0.8005 | 0.6899 | 0.8005 |
|
| 63 |
+
| 0.9926 | 6.0 | 609 | 0.7339 | 0.7930 | 0.7858 | 0.8128 | 0.7099 | 0.8128 |
|
| 64 |
+
| 0.9926 | 7.0 | 710 | 0.7714 | 0.7789 | 0.7768 | 0.7906 | 0.6863 | 0.7906 |
|
| 65 |
+
| 0.9926 | 8.0 | 812 | 0.7817 | 0.7938 | 0.7861 | 0.8128 | 0.7108 | 0.8128 |
|
| 66 |
+
| 0.9926 | 9.0 | 913 | 0.8029 | 0.7905 | 0.7885 | 0.8067 | 0.7046 | 0.8067 |
|
| 67 |
+
| 0.3377 | 10.0 | 1015 | 0.8392 | 0.7953 | 0.7922 | 0.8091 | 0.7090 | 0.8091 |
|
| 68 |
+
| 0.3377 | 11.0 | 1116 | 0.8399 | 0.7984 | 0.7981 | 0.8116 | 0.7139 | 0.8116 |
|
| 69 |
+
| 0.3377 | 12.0 | 1218 | 0.8519 | 0.8036 | 0.8099 | 0.8153 | 0.7184 | 0.8153 |
|
| 70 |
+
| 0.3377 | 13.0 | 1319 | 0.8683 | 0.8058 | 0.8167 | 0.8165 | 0.7206 | 0.8165 |
|
| 71 |
+
| 0.3377 | 14.0 | 1421 | 0.8745 | 0.8022 | 0.8068 | 0.8128 | 0.7160 | 0.8128 |
|
| 72 |
+
| 0.1504 | 14.93 | 1515 | 0.8776 | 0.8019 | 0.8062 | 0.8128 | 0.7158 | 0.8128 |
|
| 73 |
+
|
| 74 |
+
|
| 75 |
+
### Framework versions
|
| 76 |
+
|
| 77 |
+
- Transformers 4.29.2
|
| 78 |
+
- Pytorch 2.0.1+cu118
|
| 79 |
+
- Tokenizers 0.13.3
|