| { |
| "created_at": "2026-05-10T08:02:13.433720+00:00", |
| "method": "temperature_scaling", |
| "temperature": 1.779860258102417, |
| "fit_split": "artifacts/dataset/splits/val.csv", |
| "forbidden_splits": [ |
| "internal_test", |
| "instructor_final_test" |
| ], |
| "num_samples": 3157, |
| "before": { |
| "nll": 0.2979576885700226, |
| "ece": 0.03823123127222061, |
| "accuracy": 0.9239784479141235, |
| "mean_confidence": 0.9612730741500854 |
| }, |
| "after": { |
| "nll": 0.24159657955169678, |
| "ece": 0.01043415255844593, |
| "accuracy": 0.9239784479141235, |
| "mean_confidence": 0.9190037250518799 |
| }, |
| "test_eval": { |
| "split": "artifacts/dataset/splits/internal_test.csv", |
| "num_samples": 3170, |
| "before": { |
| "nll": 0.2744634747505188, |
| "ece": 0.03928366303443909, |
| "accuracy": 0.9201892614364624, |
| "mean_confidence": 0.9594728946685791 |
| }, |
| "after": { |
| "nll": 0.23008054494857788, |
| "ece": 0.010715372860431671, |
| "accuracy": 0.9201892614364624, |
| "mean_confidence": 0.9168013334274292 |
| } |
| } |
| } |
|
|