training_provenance.json

{
  "base_model": "jhu-clsp/mmBERT-base",
  "task": "code-language-identification",
  "problem_type": "multi_label_classification",
  "labels": [
    "Python",
    "JavaScript",
    "Java",
    "C",
    "C++",
    "C#",
    "Go",
    "Rust",
    "Kotlin",
    "Swift",
    "Ruby",
    "R",
    "Scala",
    "Perl",
    "Lua",
    "Bash",
    "PowerShell",
    "Batch",
    "SQL",
    "Dockerfile",
    "YAML",
    "Makefile",
    "Terraform",
    "AWK",
    "jq"
  ],
  "max_seq_length": 3072,
  "epochs": 2,
  "learning_rate": 2e-05,
  "threshold": 0.5,
  "trained_at": "2026-06-02T09:22:34+00:00"
}