{
  "schema_version": 1,
  "variant": "seq2seq",
  "encoder": "openai",
  "seed": 42,
  "compression": null,
  "tokenizer": "bpe",
  "model": {
    "input_dim": 1536,
    "vocab_size": 5000,
    "embed_dim": 512,
    "num_heads": 8,
    "num_layers": 6,
    "dropout": 0.1,
    "max_slug_tokens": 24
  },
  "training": {
    "lr": 0.0003,
    "weight_decay": 0.0001,
    "batch_size": 1024,
    "patience": 10,
    "epochs": 50,
    "eval_every": 2000,
    "val_max_samples": 5000,
    "checkpoint_every": 5000,
    "keep_last_checkpoints": 5,
    "f1_n_samples": 2000
  },
  "results": {
    "best_val_loss": 2.937381767654419,
    "best_step": 64000,
    "total_steps": 64000,
    "n_params": 24840072
  },
  "artifacts": [
    "best.pt",
    "tokenizer.json",
    "history.jsonl",
    "step_040000.pt",
    "step_045000.pt",
    "step_050000.pt",
    "step_055000.pt",
    "step_060000.pt"
  ]
}