{
  "model_name": "SmolLM2-135M-Reasoning-5K",
  "base_model": "HuggingFaceTB/SmolLM2-135M-Instruct",
  "dataset": "SupraLabs/reasoning-corpus-4K-5M-v1",
  "training_method": "full-parameter supervised fine-tuning",
  "training_rows": 5000,
  "evaluation_rows": 128,
  "epochs": 2,
  "learning_rate": 3e-05,
  "maximum_sequence_length": 4096,
  "loss_masking": "assistant tokens only",
  "reasoning_format": "<think>reasoning</think> followed by the final answer",
  "system_prompt": "You are a helpful AI assistant. For difficult problems, reason carefully inside <think> and </think> tags, then provide a clear final answer.",
  "architecture": [
    "LlamaForCausalLM"
  ],
  "model_type": "llama",
  "hidden_size": 576,
  "num_hidden_layers": 30,
  "vocab_size": 49152,
  "weight_size_bytes": 269060552,
  "weight_sha256": {
    "model.safetensors": "5d4e7b05c25b575e1519ea785a69792f0cff31843fbaf3e1f05e213cfb3315ce"
  },
  "recorded_training_metrics": {
    "train_results.json": {
      "epoch": 1.0,
      "total_flos": 1.2703418486728704e+16,
      "train_loss": 1.257179560470581,
      "train_runtime": 2169.844,
      "train_samples_per_second": 4.609,
      "train_steps_per_second": 0.288
    },
    "eval_results.json": {
      "epoch": 1.0,
      "eval_loss": 1.272692322731018,
      "eval_runtime": 7.2216,
      "eval_samples_per_second": 17.725,
      "eval_steps_per_second": 8.862
    },
    "all_results.json": {
      "epoch": 1.0,
      "eval_loss": 1.272692322731018,
      "eval_runtime": 7.2216,
      "eval_samples_per_second": 17.725,
      "eval_steps_per_second": 8.862,
      "total_flos": 1.2703418486728704e+16,
      "train_loss": 1.257179560470581,
      "train_runtime": 2169.844,
      "train_samples_per_second": 4.609,
      "train_steps_per_second": 0.288
    },
    "trainer_state_summary": {
      "best_metric": 1.2715508937835693,
      "best_model_checkpoint": "/content/SmolLM2-135M-Reasoning-5K/checkpoint-624",
      "epoch": 1.0,
      "global_step": 625
    }
  }
}