{
  "model": "Supernova Transformer V2",
  "organization": "Supernova11c",
  "framework": "PyTorch",
  "architecture": "Decoder-only causal Transformer",
  "vocab_size": 131,
  "hidden_size": 256,
  "attention_heads": 8,
  "layers": 4,
  "feed_forward_size": 1024,
  "max_sequence_length": 512,
  "state_dict_tensors": 53,
  "state_dict_elements": 3357696,
  "unique_trainable_parameters": 3357696,
  "embedding_lm_head": "separate_parameters",
  "best_validation_loss": 0.14225323487189598,
  "training_examples": 2601,
  "validation_examples": 289,
  "training_type": "Supervised causal language modeling",
  "loss_scope": "Assistant-only loss",
  "checkpoint_source": "supernova_transformer_v2_best.pt",
  "export_verification": "Exact tensor-by-tensor verification"
}