Upload evaluation/gold_results.json with huggingface_hub

evaluation/gold_results.json

@@ -0,0 +1,11 @@
+{
+  "entity_f1": 0.4735,
+  "entity_precision": 0.4394,
+  "entity_recall": 0.5133,
+  "ci_95_low": 0.2711,
+  "ci_95_high": 0.6437,
+  "n_examples": 496,
+  "model_path": "models/checkpoints/dictabert_crf/P10_crf_thread_aware_io",
+  "test_file": "data/gold_validation/gold_tokenized_dictabert_io_corrected.jsonl",
+  "classification_report": "              precision    recall  f1-score   support\n\n    QUANTITY       0.53      0.55      0.54        62\nSUBSTITUTION       0.35      0.47      0.40        51\n\n   micro avg       0.44      0.51      0.47       113\n   macro avg       0.44      0.51      0.47       113\nweighted avg       0.45      0.51      0.48       113\n"
+}