Update README.md
Browse files
README.md
CHANGED
|
@@ -3,6 +3,9 @@ license: mit
|
|
| 3 |
tags:
|
| 4 |
- chemistry
|
| 5 |
- smarts
|
|
|
|
|
|
|
|
|
|
| 6 |
---
|
| 7 |
|
| 8 |
# Model Card for Model hogru/MolReactGen-USPTO50K-Reaction-Templates
|
|
@@ -63,11 +66,11 @@ The model generates reaction templates that are similar to the USPTO-50K trainin
|
|
| 63 |
|
| 64 |
The default Hugging Face `Trainer()` has been used, with an `EarlyStoppingCallback()`.
|
| 65 |
|
| 66 |
-
|
| 67 |
|
| 68 |
The training data was pre-processed with a `PreTrainedTokenizerFast()` trained on the training data with a bespoke `RegEx` pre-tokenizer which "understands" the SMARTS syntax.
|
| 69 |
|
| 70 |
-
|
| 71 |
|
| 72 |
- **Batch size:** 8
|
| 73 |
- **Gradient accumulation steps:** 4
|
|
@@ -86,7 +89,7 @@ More configuration (options) can be found in the [`conf`](https://github.com/hog
|
|
| 86 |
|
| 87 |
Please see the slides / the poster mentioned above.
|
| 88 |
|
| 89 |
-
|
| 90 |
|
| 91 |
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 92 |
|
|
|
|
| 3 |
tags:
|
| 4 |
- chemistry
|
| 5 |
- smarts
|
| 6 |
+
widget:
|
| 7 |
+
- text: "^"
|
| 8 |
+
example_title: "Sample reaction template | SMARTS"
|
| 9 |
---
|
| 10 |
|
| 11 |
# Model Card for Model hogru/MolReactGen-USPTO50K-Reaction-Templates
|
|
|
|
| 66 |
|
| 67 |
The default Hugging Face `Trainer()` has been used, with an `EarlyStoppingCallback()`.
|
| 68 |
|
| 69 |
+
### Preprocessing
|
| 70 |
|
| 71 |
The training data was pre-processed with a `PreTrainedTokenizerFast()` trained on the training data with a bespoke `RegEx` pre-tokenizer which "understands" the SMARTS syntax.
|
| 72 |
|
| 73 |
+
### Training Hyperparameters
|
| 74 |
|
| 75 |
- **Batch size:** 8
|
| 76 |
- **Gradient accumulation steps:** 4
|
|
|
|
| 89 |
|
| 90 |
Please see the slides / the poster mentioned above.
|
| 91 |
|
| 92 |
+
### Metrics
|
| 93 |
|
| 94 |
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 95 |
|