Commit
•
df20887
1
Parent(s):
2ad0a98
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
metrics:
|
| 6 |
+
- f1
|
| 7 |
+
- accuracy
|
| 8 |
+
model-index:
|
| 9 |
+
- name: bert-finetuned-gender_classification
|
| 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 |
+
# bert-finetuned-gender_classification
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.1484
|
| 21 |
+
- F1: 0.9645
|
| 22 |
+
- Roc Auc: 0.9732
|
| 23 |
+
- Accuracy: 0.964
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 2e-05
|
| 43 |
+
- train_batch_size: 8
|
| 44 |
+
- eval_batch_size: 8
|
| 45 |
+
- seed: 42
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- num_epochs: 10
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Roc Auc | Accuracy |
|
| 53 |
+
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:|:--------:|
|
| 54 |
+
| 0.1679 | 1.0 | 1125 | 0.1781 | 0.928 | 0.946 | 0.927 |
|
| 55 |
+
| 0.1238 | 2.0 | 2250 | 0.1252 | 0.9516 | 0.9640 | 0.95 |
|
| 56 |
+
| 0.0863 | 3.0 | 3375 | 0.1283 | 0.9515 | 0.9637 | 0.95 |
|
| 57 |
+
| 0.0476 | 4.0 | 4500 | 0.1419 | 0.9565 | 0.9672 | 0.956 |
|
| 58 |
+
| 0.0286 | 5.0 | 5625 | 0.1428 | 0.9555 | 0.9667 | 0.954 |
|
| 59 |
+
| 0.0091 | 6.0 | 6750 | 0.1515 | 0.9604 | 0.9700 | 0.959 |
|
| 60 |
+
| 0.0157 | 7.0 | 7875 | 0.1535 | 0.9580 | 0.9682 | 0.957 |
|
| 61 |
+
| 0.0048 | 8.0 | 9000 | 0.1484 | 0.9645 | 0.9732 | 0.964 |
|
| 62 |
+
| 0.0045 | 9.0 | 10125 | 0.1769 | 0.9605 | 0.9703 | 0.96 |
|
| 63 |
+
| 0.0037 | 10.0 | 11250 | 0.2007 | 0.9565 | 0.9672 | 0.956 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.19.2
|
| 69 |
+
- Pytorch 1.11.0+cu113
|
| 70 |
+
- Datasets 2.2.2
|
| 71 |
+
- Tokenizers 0.12.1
|