update model card README.md

README.md

@@ -1,44 +1,63 @@
 ---
-license: mit
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: soft-search
+  results: []
 ---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
 # soft-search
 
-[![Build Status](https://github.com/PugetSoundClinic-PIT/soft-search/workflows/CI/badge.svg)](https://github.com/PugetSoundClinic-PIT/soft-search/actions)
-[![Documentation](https://github.com/PugetSoundClinic-PIT/soft-search/workflows/Documentation/badge.svg)](https://PugetSoundClinic-PIT.github.io/soft-search)
+This model is a fine-tuned version of [distilbert-base-uncased-finetuned-sst-2-english](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2866
+- Accuracy: 0.8333
 
-searching for software promises in grant applications
+## Model description
 
----
+More information needed
+
+## Intended uses & limitations
+
+More information needed
 
-## Installation
+## Training and evaluation data
 
-**Stable Release:** `pip install soft-search`<br>
-**Development Head:** `pip install git+https://github.com/PugetSoundClinic-PIT/soft-search.git`
+More information needed
 
-## Quickstart
+## Training procedure
 
-### Apply our Pre-trained Transformer
+### Training hyperparameters
 
-```python
-from soft_search import constants, nsf
-from soft_search.label import transformer
-df = nsf.get_nsf_dataset(
-    "2016-01-01",
-    "2017-01-01",
-    dataset_fields=[constants.NSFFields.abstractText],
-)
-predicted = transformer.label(
-    df,
-    apply_column=constants.NSFFields.abstractText,
-)
-```
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
 
-## Documentation
+### Training results
 
-For full package documentation please visit [PugetSoundClinic-PIT.github.io/soft-search](https://PugetSoundClinic-PIT.github.io/soft-search).
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 3    | 0.7179          | 0.75     |
+| No log        | 2.0   | 6    | 0.2900          | 0.8333   |
+| No log        | 3.0   | 9    | 0.2498          | 0.8333   |
+| 0.6351        | 4.0   | 12   | 0.2538          | 0.9167   |
+| 0.6351        | 5.0   | 15   | 0.2866          | 0.8333   |
 
-## Development
 
-See [CONTRIBUTING.md](CONTRIBUTING.md) for information related to developing the code.
+### Framework versions
 
-**MIT License**
+- Transformers 4.21.0
+- Pytorch 1.12.0+cu102
+- Datasets 2.4.0
+- Tokenizers 0.12.1