Update README.md
Browse files
README.md
CHANGED
|
@@ -5,11 +5,12 @@ tags:
|
|
| 5 |
model-index:
|
| 6 |
- name: bert-base-uncased-Masked_Language_Modeling-AG_News
|
| 7 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
-
|
| 13 |
# bert-base-uncased-Masked_Language_Modeling-AG_News
|
| 14 |
|
| 15 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
|
|
@@ -18,15 +19,17 @@ It achieves the following results on the evaluation set:
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
| 21 |
-
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Intended uses & limitations
|
| 24 |
|
| 25 |
-
|
| 26 |
|
| 27 |
## Training and evaluation data
|
| 28 |
|
| 29 |
-
|
| 30 |
|
| 31 |
## Training procedure
|
| 32 |
|
|
@@ -49,10 +52,11 @@ The following hyperparameters were used during training:
|
|
| 49 |
| 1.9626 | 2.0 | 12446 | 1.7879 |
|
| 50 |
| 1.8663 | 3.0 | 18669 | 1.7443 |
|
| 51 |
|
|
|
|
| 52 |
|
| 53 |
### Framework versions
|
| 54 |
|
| 55 |
- Transformers 4.26.1
|
| 56 |
- Pytorch 1.13.1+cu116
|
| 57 |
- Datasets 2.10.1
|
| 58 |
-
- Tokenizers 0.13.2
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: bert-base-uncased-Masked_Language_Modeling-AG_News
|
| 7 |
results: []
|
| 8 |
+
language:
|
| 9 |
+
- en
|
| 10 |
+
metrics:
|
| 11 |
+
- perplexity
|
| 12 |
---
|
| 13 |
|
|
|
|
|
|
|
|
|
|
| 14 |
# bert-base-uncased-Masked_Language_Modeling-AG_News
|
| 15 |
|
| 16 |
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
|
|
|
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
| 22 |
+
This is a masked language modeling project.
|
| 23 |
+
|
| 24 |
+
For more information on how it was created, check out the following link: https://github.com/DunnBC22/NLP_Projects/blob/main/Masked%20Language%20Model/AG%20News/AG_News_MLM.ipynb
|
| 25 |
|
| 26 |
## Intended uses & limitations
|
| 27 |
|
| 28 |
+
This model is intended to demonstrate my ability to solve a complex problem using technology.
|
| 29 |
|
| 30 |
## Training and evaluation data
|
| 31 |
|
| 32 |
+
Dataset Source: https://www.kaggle.com/datasets/thedevastator/new-dataset-for-text-classification-ag-news
|
| 33 |
|
| 34 |
## Training procedure
|
| 35 |
|
|
|
|
| 52 |
| 1.9626 | 2.0 | 12446 | 1.7879 |
|
| 53 |
| 1.8663 | 3.0 | 18669 | 1.7443 |
|
| 54 |
|
| 55 |
+
Perplexity: 5.95
|
| 56 |
|
| 57 |
### Framework versions
|
| 58 |
|
| 59 |
- Transformers 4.26.1
|
| 60 |
- Pytorch 1.13.1+cu116
|
| 61 |
- Datasets 2.10.1
|
| 62 |
+
- Tokenizers 0.13.2
|