Commit
•
28dfd33
1
Parent(s):
14ba75a
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- accuracy
|
| 7 |
+
model-index:
|
| 8 |
+
- name: malaysia-news-classification-bert-english-skewness-fixed
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# malaysia-news-classification-bert-english-skewness-fixed
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.2051
|
| 20 |
+
- Accuracy: 0.8436
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 5e-05
|
| 40 |
+
- train_batch_size: 8
|
| 41 |
+
- eval_batch_size: 64
|
| 42 |
+
- seed: 42
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: linear
|
| 45 |
+
- num_epochs: 16
|
| 46 |
+
- mixed_precision_training: Native AMP
|
| 47 |
+
|
| 48 |
+
### Training results
|
| 49 |
+
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------:|
|
| 52 |
+
| No log | 1.0 | 358 | 0.9357 | 0.7486 |
|
| 53 |
+
| 1.3554 | 2.0 | 716 | 0.9041 | 0.7807 |
|
| 54 |
+
| 0.4851 | 3.0 | 1074 | 0.7842 | 0.8282 |
|
| 55 |
+
| 0.4851 | 4.0 | 1432 | 0.9478 | 0.8226 |
|
| 56 |
+
| 0.2558 | 5.0 | 1790 | 1.0765 | 0.8282 |
|
| 57 |
+
| 0.1084 | 6.0 | 2148 | 1.1310 | 0.8380 |
|
| 58 |
+
| 0.0625 | 7.0 | 2506 | 1.0999 | 0.8464 |
|
| 59 |
+
| 0.0625 | 8.0 | 2864 | 1.1391 | 0.8408 |
|
| 60 |
+
| 0.0301 | 9.0 | 3222 | 1.1036 | 0.8506 |
|
| 61 |
+
| 0.0171 | 10.0 | 3580 | 1.0765 | 0.8534 |
|
| 62 |
+
| 0.0171 | 11.0 | 3938 | 1.1291 | 0.8506 |
|
| 63 |
+
| 0.0129 | 12.0 | 4296 | 1.1360 | 0.8520 |
|
| 64 |
+
| 0.0035 | 13.0 | 4654 | 1.1619 | 0.8450 |
|
| 65 |
+
| 0.0039 | 14.0 | 5012 | 1.1727 | 0.8534 |
|
| 66 |
+
| 0.0039 | 15.0 | 5370 | 1.2079 | 0.8408 |
|
| 67 |
+
| 0.0031 | 16.0 | 5728 | 1.2051 | 0.8436 |
|
| 68 |
+
|
| 69 |
+
|
| 70 |
+
### Framework versions
|
| 71 |
+
|
| 72 |
+
- Transformers 4.18.0
|
| 73 |
+
- Pytorch 2.2.1+cu121
|
| 74 |
+
- Datasets 2.19.0
|
| 75 |
+
- Tokenizers 0.12.1
|