Update README.md

README.md

@@ -29,9 +29,9 @@ model-index:
 | **Default Pipeline** | `transformer`, `ner` |
 | **Components** | `transformer`, `ner` |
 | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
-| **Sources** | n/a |
-| **License** | n/a |
-| **Author** | [n/a]() |
+| **Sources** | [longformer](https://huggingface.co/allenai/longformer-base-4096) |
+| **License** | Something permissive |
+| **Author** | [Langdon Holmes]() |
 
 ### Label Scheme
 
@@ -53,4 +53,9 @@ model-index:
 | `ENTS_P` | 83.12 |
 | `ENTS_R` | 84.21 |
 | `TRANSFORMER_LOSS` | 56255026.35 |
-| `NER_LOSS` | 31154.89 |
+| `NER_LOSS` | 31154.89 |
+
+
+### Training Data
+
+6,293 student writing assignments were submitted as PDF files and student names were labeled by human raters (one rater per document). A preliminary model was trained and all disagreements between this model and the human annotations were adjudicated by two additional reviewers. The final labeled dataset has 1,155 student name annotations across 845 documents.