Text Classification
Transformers
PyTorch
English
distilbert
distilbert-base-uncased-finetuned-sst-2-english
Instructions to use rosherd/job_classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use rosherd/job_classification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="rosherd/job_classification")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("rosherd/job_classification") model = AutoModelForSequenceClassification.from_pretrained("rosherd/job_classification", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from rosherd/job_classification: direct link, hf CLI and curl.
- Browser
- Download file 1.86 kB
-
https://huggingface.co/rosherd/job_classification/resolve/main/README.md
- Command line
-
hf download hf://rosherd/job_classification/README.md
-
curl -L -o README.md https://huggingface.co/rosherd/job_classification/resolve/main/README.md
1.86 kB
| language: en | |
| tags: | |
| - "distilbert-base-uncased-finetuned-sst-2-english" | |
| license: apache-2.0 | |
| widget: | |
| - text: "Sales Account Manager" | |
| example_title: "sales,management,account_management" | |
| - text: "Registered Nurse – Medical Surgical l" | |
| example_title: "healthcare" | |
| - text: "$24/hr | Oil & Gas Accounting Specialist" | |
| example_title: "oil_and_gas,accounting,human_resources" | |
| # Job Classification | |
| This model will predict job leaf class(es) | |
| ## Model description | |
| As above, pre-trained on ```"distilbert-base-uncased-finetuned-sst-2-english"``` | |
| ## Training data | |
| pretrained on RL job data | |
| ## Evaluation results | |
| When fine-tuned on downstream tasks, this model achieves the following results: | |
| | **Epoch** | **Training Loss** | **Validation Loss** | **F1** | **Roc Auc** | **Accuracy** | | |
| |-----------|-------------------|---------------------|----------|-------------|--------------| | |
| | 1 | 0.001700 | 0.001172 | 0.889403 | 0.918269 | 0.676408 | | |
| | 2 | 0.000800 | 0.000575 | 0.945118 | 0.959073 | 0.827609 | | |
| | 3 | 0.000500 | 0.000371 | 0.965682 | 0.975373 | 0.889090 | | |
| | 4 | 0.000300 | 0.000265 | 0.975741 | 0.984176 | 0.920520 | | |
| | 5 | 0.000200 | 0.000217 | 0.980912 | 0.987641 | 0.938598 | | |
| | 6 | 0.000100 | 0.000188 | 0.984096 | 0.989826 | 0.948720 | | |
| | 7 | 0.000100 | 0.000174 | 0.986366 | 0.990944 | 0.956243 | | |
| | 8 | 0.000100 | 0.000159 | 0.987374 | 0.992371 | 0.960260 | | |
| | 9 | 0.000100 | 0.000153 | 0.987939 | 0.992148 | 0.961954 | | |
| | 10 | 0.000100 | 0.000152 | 0.988216 | 0.992329 | 0.963293 | | |