{
  "model_name": "distilgpt2",
  "version": "maximum-accuracy",
  "lora_r": 32,
  "lora_alpha": 64,
  "target_modules": [
    "c_attn",
    "c_proj",
    "c_fc"
  ],
  "lora_dropout": 0.05,
  "murlis_used": 500,
  "total_examples": 344,
  "epochs": 15,
  "max_length": 512,
  "batch_size": 2,
  "gradient_accumulation": 8,
  "effective_batch_size": 16,
  "learning_rate": 5e-05,
  "warmup_steps": 200,
  "scheduler": "cosine",
  "weight_decay": 0.02,
  "completed_at": "2025-10-03T12:25:52.051354",
  "improvements": [
    "LoRA Rank: 32 (8x from standard, 2x from enhanced)",
    "LoRA Alpha: 64 (8x from standard, 2x from enhanced)",
    "Target Modules: c_attn + c_proj + c_fc (ALL layers)",
    "Epochs: 15 (5x from standard, 1.5x from enhanced)",
    "Murlis: 500 (3.3x from standard, 1.67x from enhanced)",
    "Context: 512 tokens (2x from standard, 1.33x from enhanced)",
    "15 detailed spiritual concepts with full explanations",
    "7 different formats per murli for comprehensive learning",
    "Ultra-careful learning rate (5e-5)",
    "Maximum warmup (200 steps)",
    "Larger effective batch (16)",
    "Stronger regularization (0.02 weight decay)"
  ]
}