{
  "args": {
    "model_id": "Qwen/Qwen3-4B",
    "load_in_4bit": true,
    "torch_dtype": "bf16",
    "device_map": "auto",
    "use_lora": true,
    "lora_r": 8,
    "lora_alpha": 16,
    "lora_dropout": 0.05,
    "lora_target_modules": "all-linear",
    "gradient_checkpointing": true,
    "optimizer": "paged_adamw_8bit",
    "modulus": 97,
    "max_steps": 24,
    "train_min_len": 1,
    "train_max_len": 12,
    "curriculum_stages": "answer:1:24:300",
    "answer_train_min_len": 1,
    "answer_train_max_len": 24,
    "eval_lengths": "4,8,12,24",
    "train_template_mode": "mixed",
    "paired_train": true,
    "paired_batches": true,
    "paired_template_modes": "standard,paraphrase",
    "pair_size": 2,
    "answer_train_template_mode": "mixed",
    "eval_template_modes": "standard,paraphrase",
    "paired_eval": true,
    "paired_eval_template_modes": "standard,paraphrase",
    "train_size": 128,
    "answer_train_size": 512,
    "eval_size": 64,
    "train_batch_size": 4,
    "eval_batch_size": 8,
    "bootstrap_steps": 0,
    "answer_steps": 0,
    "eval_every": 100,
    "stage_eval_every": 100,
    "lr": 0.0002,
    "answer_lr_scale": 0.1,
    "weight_decay": 0.0,
    "grad_clip": 1.0,
    "head_width": 512,
    "register_width": 512,
    "register_layers": 1,
    "register_heads": 4,
    "register_dropout": 0.05,
    "register_style": "bare",
    "trace_loss_weight": 1.0,
    "init_trace_loss_weight": 4.0,
    "op_trace_loss_weight": 1.0,
    "arg_trace_loss_weight": 4.0,
    "executor_loss_weight": 1.0,
    "state_loss_weight": 0.25,
    "variants": "direct",
    "max_length": 768,
    "seed": 7,
    "train_seed": -1,
    "output_dir": "experiments/qwen_register_token_latent_compiler/runs/control_direct_answer_s300",
    "checkpoint_dir": "large_artifacts/qwen_register_token_latent_compiler/checkpoints/control_direct_answer_s300"
  },
  "metadata": {
    "python": "3.12.3",
    "platform": "Linux-6.8.0-62-generic-x86_64-with-glibc2.39",
    "torch": "2.8.0+cu128",
    "cuda_available": true,
    "transformers_loader": "AutoModelForCausalLM",
    "peft_installed": true,
    "use_lora": true,
    "lora_r": 8,
    "gpu_name": "NVIDIA RTX 6000 Ada Generation",
    "gpu_vram_gb": 47.383
  },
  "hidden_dim": 2560,
  "register_count": 49,
  "dataset": {
    "train_size": 128,
    "train_examples": 256,
    "curriculum_stages": [
      {
        "name": "answer",
        "min_len": 1,
        "max_len": 24,
        "steps": 300
      }
    ],
    "answer_train_size": 512,
    "eval_size": 64,
    "eval_lengths": [
      4,
      8,
      12,
      24
    ],
    "train_template_mode": "mixed",
    "paired_train": true,
    "paired_template_modes": [
      "standard",
      "paraphrase"
    ],
    "answer_train_template_mode": "mixed",
    "eval_template_modes": [
      "standard",
      "paraphrase"
    ],
    "paired_eval": true,
    "paired_eval_template_modes": [
      "standard",
      "paraphrase"
    ],
    "register_style": "bare"
  },
  "variants": {
    "direct": {
      "variant": "direct",
      "train_seconds": 845.8741309642792,
      "checkpoints": [
        "large_artifacts/qwen_register_token_latent_compiler/checkpoints/control_direct_answer_s300/direct/adapter",
        "large_artifacts/qwen_register_token_latent_compiler/checkpoints/control_direct_answer_s300/direct/heads.pt"
      ],
      "train_log": [
        {
          "variant": "direct",
          "stage": "answer_only",
          "local_step": 1,
          "step": 1,
          "loss": 4.548712730407715,
          "trace_loss_active": false,
          "executor_loss_active": false,
          "state_loss_active": false,
          "lr_scale": 1.0,
          "direct_loss": 4.548712730407715,
          "standard_len4_direct_accuracy": 0.0,
          "standard_len4_direct_target_mass": 0.009991438477300107,
          "standard_len4_executor_accuracy": NaN,
          "standard_len4_executor_target_mass": NaN,
          "standard_len4_init_accuracy": NaN,
          "standard_len4_op_accuracy": NaN,
          "standard_len4_arg_accuracy": NaN,
          "standard_len4_program_exact": NaN,
          "standard_len4_state_accuracy": NaN,
          "standard_len4_state_all_exact": NaN,
          "standard_len4_state_prefix_fraction": NaN,
          "standard_len8_direct_accuracy": 0.015625,
          "standard_len8_direct_target_mass": 0.010375249199569225,
          "standard_len8_executor_accuracy": NaN,
          "standard_len8_executor_target_mass": NaN,
          "standard_len8_init_accuracy": NaN,
          "standard_len8_op_accuracy": NaN,
          "standard_len8_arg_accuracy": NaN,
          "standard_len8_program_exact": NaN,
          "standard_len8_state_accuracy": NaN,
          "standard_len8_state_all_exact": NaN,
          "standard_len8_state_prefix_fraction": NaN,
          "standard_len12_direct_accuracy": 0.0,
          "standard_len12_direct_target_mass": 0.00990655121859163,
          "standard_len12_executor_accuracy": NaN,
          "standard_len12_executor_target_mass": NaN,
          "standard_len12_init_accuracy": NaN,
          "standard_len12_op_accuracy": NaN,
          "standard_len12_arg_accuracy": NaN,
          "standard_len12_program_exact": NaN,
          "standard_len12_state_accuracy": NaN,
          "standard_len12_state_all_exact": NaN,
          "standard_len12_state_prefix_fraction": NaN,
          "standard_len24_direct_accuracy": 0.015625,
          "standard_len24_direct_target_mass": 0.010577832232229412,
          "standard_len24_executor_accuracy": NaN,
          "standard_len24_executor_target_mass": NaN,
          "standard_len24_init_accuracy": NaN,
          "standard_len24_op_accuracy": NaN,
          "standard_len24_arg_accuracy": NaN,
          "standard_len24_program_exact": NaN,
          "standard_len24_state_accuracy": NaN,
          "standard_len24_state_all_exact": NaN,
          "standard_len24_state_prefix_fraction": NaN,
          "paraphrase_len4_direct_accuracy": 0.0,
          "paraphrase_len4_direct_target_mass": 0.010066985269077122,
          "paraphrase_len4_executor_accuracy": NaN,
          "paraphrase_len4_executor_target_mass": NaN,
          "paraphrase_len4_init_accuracy": NaN,
          "paraphrase_len4_op_accuracy": NaN,
          "paraphrase_len4_arg_accuracy": NaN,
          "paraphrase_len4_program_exact": NaN,
          "paraphrase_len4_state_accuracy": NaN,
          "paraphrase_len4_state_all_exact": NaN,
          "paraphrase_len4_state_prefix_fraction": NaN,
          "paraphrase_len8_direct_accuracy": 0.0,
          "paraphrase_len8_direct_target_mass": 0.01072024879977107,
          "paraphrase_len8_executor_accuracy": NaN,
          "paraphrase_len8_executor_target_mass": NaN,
          "paraphrase_len8_init_accuracy": NaN,
          "paraphrase_len8_op_accuracy": NaN,
          "paraphrase_len8_arg_accuracy": NaN,
          "paraphrase_len8_program_exact": NaN,
          "paraphrase_len8_state_accuracy": NaN,
          "paraphrase_len8_state_all_exact": NaN,
          "paraphrase_len8_state_prefix_fraction": NaN,
          "paraphrase_len12_direct_accuracy": 0.0,
          "paraphrase_len12_direct_target_mass": 0.010127400164492428,
          "paraphrase_len12_executor_accuracy": NaN,
          "paraphrase_len12_executor_target_mass": NaN,
          "paraphrase_len12_init_accuracy": NaN,
          "paraphrase_len12_op_accuracy": NaN,
          "paraphrase_len12_arg_accuracy": NaN,
          "paraphrase_len12_program_exact": NaN,
          "paraphrase_len12_state_accuracy": NaN,
          "paraphrase_len12_state_all_exact": NaN,
          "paraphrase_len12_state_prefix_fraction": NaN,
          "paraphrase_len24_direct_accuracy": 0.015625,
          "paraphrase_len24_direct_target_mass": 0.010251763858832419,
          "paraphrase_len24_executor_accuracy": NaN,
          "paraphrase_len24_executor_target_mass": NaN,
          "paraphrase_len24_init_accuracy": NaN,
          "paraphrase_len24_op_accuracy": NaN,
          "paraphrase_len24_arg_accuracy": NaN,
          "paraphrase_len24_program_exact": NaN,
          "paraphrase_len24_state_accuracy": NaN,
          "paraphrase_len24_state_all_exact": NaN,
          "paraphrase_len24_state_prefix_fraction": NaN,
          "paired_len4_direct_accuracy": 0.0,
          "paired_len4_direct_target_mass": 0.010528439248446375,
          "paired_len4_executor_accuracy": NaN,
          "paired_len4_executor_target_mass": NaN,
          "paired_len4_init_accuracy": NaN,
          "paired_len4_op_accuracy": NaN,
          "paired_len4_arg_accuracy": NaN,
          "paired_len4_program_exact": NaN,
          "paired_len4_state_accuracy": NaN,
          "paired_len4_state_all_exact": NaN,
          "paired_len4_state_prefix_fraction": NaN,
          "paired_len4_pair_true_answer_consistency": 1.0,
          "paired_len4_direct_pair_answer_consistency": 0.75,
          "paired_len4_direct_pair_both_correct": 0.0,
          "paired_len8_direct_accuracy": 0.0234375,
          "paired_len8_direct_target_mass": 0.010385037050582469,
          "paired_len8_executor_accuracy": NaN,
          "paired_len8_executor_target_mass": NaN,
          "paired_len8_init_accuracy": NaN,
          "paired_len8_op_accuracy": NaN,
          "paired_len8_arg_accuracy": NaN,
          "paired_len8_program_exact": NaN,
          "paired_len8_state_accuracy": NaN,
          "paired_len8_state_all_exact": NaN,
          "paired_len8_state_prefix_fraction": NaN,
          "paired_len8_pair_true_answer_consistency": 1.0,
          "paired_len8_direct_pair_answer_consistency": 0.734375,
          "paired_len8_direct_pair_both_correct": 0.015625,
          "paired_len12_direct_accuracy": 0.0078125,
          "paired_len12_direct_target_mass": 0.010441710939630866,
          "paired_len12_executor_accuracy": NaN,
          "paired_len12_executor_target_mass": NaN,
          "paired_len12_init_accuracy": NaN,
          "paired_len12_op_accuracy": NaN,
          "paired_len12_arg_accuracy": NaN,
          "paired_len12_program_exact": NaN,
          "paired_len12_state_accuracy": NaN,
          "paired_len12_state_all_exact": NaN,
          "paired_len12_state_prefix_fraction": NaN,
          "paired_len12_pair_true_answer_consistency": 1.0,
          "paired_len12_direct_pair_answer_consistency": 0.609375,
          "paired_len12_direct_pair_both_correct": 0.0,
          "paired_len24_direct_accuracy": 0.0234375,
          "paired_len24_direct_target_mass": 0.010658582847099751,
          "paired_len24_executor_accuracy": NaN,
          "paired_len24_executor_target_mass": NaN,
          "paired_len24_init_accuracy": NaN,
          "paired_len24_op_accuracy": NaN,
          "paired_len24_arg_accuracy": NaN,
          "paired_len24_program_exact": NaN,
          "paired_len24_state_accuracy": NaN,
          "paired_len24_state_all_exact": NaN,
          "paired_len24_state_prefix_fraction": NaN,
          "paired_len24_pair_true_answer_consistency": 1.0,
          "paired_len24_direct_pair_answer_consistency": 0.6875,
          "paired_len24_direct_pair_both_correct": 0.015625
        },
        {
          "variant": "direct",
          "stage": "answer_only",
          "local_step": 100,
          "step": 100,
          "loss": 5.15815544128418,
          "trace_loss_active": false,
          "executor_loss_active": false,
          "state_loss_active": false,
          "lr_scale": 1.0,
          "direct_loss": 5.15815544128418,
          "standard_len4_direct_accuracy": 0.015625,
          "standard_len4_direct_target_mass": 0.010356259299442172,
          "standard_len4_executor_accuracy": NaN,
          "standard_len4_executor_target_mass": NaN,
          "standard_len4_init_accuracy": NaN,
          "standard_len4_op_accuracy": NaN,
          "standard_len4_arg_accuracy": NaN,
          "standard_len4_program_exact": NaN,
          "standard_len4_state_accuracy": NaN,
          "standard_len4_state_all_exact": NaN,
          "standard_len4_state_prefix_fraction": NaN,
          "standard_len8_direct_accuracy": 0.046875,
          "standard_len8_direct_target_mass": 0.011637821095064282,
          "standard_len8_executor_accuracy": NaN,
          "standard_len8_executor_target_mass": NaN,
          "standard_len8_init_accuracy": NaN,
          "standard_len8_op_accuracy": NaN,
          "standard_len8_arg_accuracy": NaN,
          "standard_len8_program_exact": NaN,
          "standard_len8_state_accuracy": NaN,
          "standard_len8_state_all_exact": NaN,
          "standard_len8_state_prefix_fraction": NaN,
          "standard_len12_direct_accuracy": 0.0,
          "standard_len12_direct_target_mass": 0.009690985432825983,
          "standard_len12_executor_accuracy": NaN,
          "standard_len12_executor_target_mass": NaN,
          "standard_len12_init_accuracy": NaN,
          "standard_len12_op_accuracy": NaN,
          "standard_len12_arg_accuracy": NaN,
          "standard_len12_program_exact": NaN,
          "standard_len12_state_accuracy": NaN,
          "standard_len12_state_all_exact": NaN,
          "standard_len12_state_prefix_fraction": NaN,
          "standard_len24_direct_accuracy": 0.015625,
          "standard_len24_direct_target_mass": 0.011303443112410605,
          "standard_len24_executor_accuracy": NaN,
          "standard_len24_executor_target_mass": NaN,
          "standard_len24_init_accuracy": NaN,
          "standard_len24_op_accuracy": NaN,
          "standard_len24_arg_accuracy": NaN,
          "standard_len24_program_exact": NaN,
          "standard_len24_state_accuracy": NaN,
          "standard_len24_state_all_exact": NaN,
          "standard_len24_state_prefix_fraction": NaN,
          "paraphrase_len4_direct_accuracy": 0.0,
          "paraphrase_len4_direct_target_mass": 0.009024781233165413,
          "paraphrase_len4_executor_accuracy": NaN,
          "paraphrase_len4_executor_target_mass": NaN,
          "paraphrase_len4_init_accuracy": NaN,
          "paraphrase_len4_op_accuracy": NaN,
          "paraphrase_len4_arg_accuracy": NaN,
          "paraphrase_len4_program_exact": NaN,
          "paraphrase_len4_state_accuracy": NaN,
          "paraphrase_len4_state_all_exact": NaN,
          "paraphrase_len4_state_prefix_fraction": NaN,
          "paraphrase_len8_direct_accuracy": 0.0,
          "paraphrase_len8_direct_target_mass": 0.00999791722279042,
          "paraphrase_len8_executor_accuracy": NaN,
          "paraphrase_len8_executor_target_mass": NaN,
          "paraphrase_len8_init_accuracy": NaN,
          "paraphrase_len8_op_accuracy": NaN,
          "paraphrase_len8_arg_accuracy": NaN,
          "paraphrase_len8_program_exact": NaN,
          "paraphrase_len8_state_accuracy": NaN,
          "paraphrase_len8_state_all_exact": NaN,
          "paraphrase_len8_state_prefix_fraction": NaN,
          "paraphrase_len12_direct_accuracy": 0.015625,
          "paraphrase_len12_direct_target_mass": 0.010176196752581745,
          "paraphrase_len12_executor_accuracy": NaN,
          "paraphrase_len12_executor_target_mass": NaN,
          "paraphrase_len12_init_accuracy": NaN,
          "paraphrase_len12_op_accuracy": NaN,
          "paraphrase_len12_arg_accuracy": NaN,
          "paraphrase_len12_program_exact": NaN,
          "paraphrase_len12_state_accuracy": NaN,
          "paraphrase_len12_state_all_exact": NaN,
          "paraphrase_len12_state_prefix_fraction": NaN,
          "paraphrase_len24_direct_accuracy": 0.015625,
          "paraphrase_len24_direct_target_mass": 0.010937099403236061,
          "paraphrase_len24_executor_accuracy": NaN,
          "paraphrase_len24_executor_target_mass": NaN,
          "paraphrase_len24_init_accuracy": NaN,
          "paraphrase_len24_op_accuracy": NaN,
          "paraphrase_len24_arg_accuracy": NaN,
          "paraphrase_len24_program_exact": NaN,
          "paraphrase_len24_state_accuracy": NaN,
          "paraphrase_len24_state_all_exact": NaN,
          "paraphrase_len24_state_prefix_fraction": NaN,
          "paired_len4_direct_accuracy": 0.015625,
          "paired_len4_direct_target_mass": 0.012035822961479425,
          "paired_len4_executor_accuracy": NaN,
          "paired_len4_executor_target_mass": NaN,
          "paired_len4_init_accuracy": NaN,
          "paired_len4_op_accuracy": NaN,
          "paired_len4_arg_accuracy": NaN,
          "paired_len4_program_exact": NaN,
          "paired_len4_state_accuracy": NaN,
          "paired_len4_state_all_exact": NaN,
          "paired_len4_state_prefix_fraction": NaN,
          "paired_len4_pair_true_answer_consistency": 1.0,
          "paired_len4_direct_pair_answer_consistency": 0.21875,
          "paired_len4_direct_pair_both_correct": 0.0,
          "paired_len8_direct_accuracy": 0.0234375,
          "paired_len8_direct_target_mass": 0.011016997508704662,
          "paired_len8_executor_accuracy": NaN,
          "paired_len8_executor_target_mass": NaN,
          "paired_len8_init_accuracy": NaN,
          "paired_len8_op_accuracy": NaN,
          "paired_len8_arg_accuracy": NaN,
          "paired_len8_program_exact": NaN,
          "paired_len8_state_accuracy": NaN,
          "paired_len8_state_all_exact": NaN,
          "paired_len8_state_prefix_fraction": NaN,
          "paired_len8_pair_true_answer_consistency": 1.0,
          "paired_len8_direct_pair_answer_consistency": 0.21875,
          "paired_len8_direct_pair_both_correct": 0.0,
          "paired_len12_direct_accuracy": 0.0,
          "paired_len12_direct_target_mass": 0.010981235624058172,
          "paired_len12_executor_accuracy": NaN,
          "paired_len12_executor_target_mass": NaN,
          "paired_len12_init_accuracy": NaN,
          "paired_len12_op_accuracy": NaN,
          "paired_len12_arg_accuracy": NaN,
          "paired_len12_program_exact": NaN,
          "paired_len12_state_accuracy": NaN,
          "paired_len12_state_all_exact": NaN,
          "paired_len12_state_prefix_fraction": NaN,
          "paired_len12_pair_true_answer_consistency": 1.0,
          "paired_len12_direct_pair_answer_consistency": 0.328125,
          "paired_len12_direct_pair_both_correct": 0.0,
          "paired_len24_direct_accuracy": 0.0078125,
          "paired_len24_direct_target_mass": 0.009453960112296045,
          "paired_len24_executor_accuracy": NaN,
          "paired_len24_executor_target_mass": NaN,
          "paired_len24_init_accuracy": NaN,
          "paired_len24_op_accuracy": NaN,
          "paired_len24_arg_accuracy": NaN,
          "paired_len24_program_exact": NaN,
          "paired_len24_state_accuracy": NaN,
          "paired_len24_state_all_exact": NaN,
          "paired_len24_state_prefix_fraction": NaN,
          "paired_len24_pair_true_answer_consistency": 1.0,
          "paired_len24_direct_pair_answer_consistency": 0.1875,
          "paired_len24_direct_pair_both_correct": 0.0
        },
        {
          "variant": "direct",
          "stage": "answer_only",
          "local_step": 200,
          "step": 200,
          "loss": 4.489184379577637,
          "trace_loss_active": false,
          "executor_loss_active": false,
          "state_loss_active": false,
          "lr_scale": 1.0,
          "direct_loss": 4.489184379577637,
          "standard_len4_direct_accuracy": 0.0,
          "standard_len4_direct_target_mass": 0.011436699714977294,
          "standard_len4_executor_accuracy": NaN,
          "standard_len4_executor_target_mass": NaN,
          "standard_len4_init_accuracy": NaN,
          "standard_len4_op_accuracy": NaN,
          "standard_len4_arg_accuracy": NaN,
          "standard_len4_program_exact": NaN,
          "standard_len4_state_accuracy": NaN,
          "standard_len4_state_all_exact": NaN,
          "standard_len4_state_prefix_fraction": NaN,
          "standard_len8_direct_accuracy": 0.0,
          "standard_len8_direct_target_mass": 0.010816301917657256,
          "standard_len8_executor_accuracy": NaN,
          "standard_len8_executor_target_mass": NaN,
          "standard_len8_init_accuracy": NaN,
          "standard_len8_op_accuracy": NaN,
          "standard_len8_arg_accuracy": NaN,
          "standard_len8_program_exact": NaN,
          "standard_len8_state_accuracy": NaN,
          "standard_len8_state_all_exact": NaN,
          "standard_len8_state_prefix_fraction": NaN,
          "standard_len12_direct_accuracy": 0.015625,
          "standard_len12_direct_target_mass": 0.008875600178726017,
          "standard_len12_executor_accuracy": NaN,
          "standard_len12_executor_target_mass": NaN,
          "standard_len12_init_accuracy": NaN,
          "standard_len12_op_accuracy": NaN,
          "standard_len12_arg_accuracy": NaN,
          "standard_len12_program_exact": NaN,
          "standard_len12_state_accuracy": NaN,
          "standard_len12_state_all_exact": NaN,
          "standard_len12_state_prefix_fraction": NaN,
          "standard_len24_direct_accuracy": 0.03125,
          "standard_len24_direct_target_mass": 0.012563865166157484,
          "standard_len24_executor_accuracy": NaN,
          "standard_len24_executor_target_mass": NaN,
          "standard_len24_init_accuracy": NaN,
          "standard_len24_op_accuracy": NaN,
          "standard_len24_arg_accuracy": NaN,
          "standard_len24_program_exact": NaN,
          "standard_len24_state_accuracy": NaN,
          "standard_len24_state_all_exact": NaN,
          "standard_len24_state_prefix_fraction": NaN,
          "paraphrase_len4_direct_accuracy": 0.03125,
          "paraphrase_len4_direct_target_mass": 0.0094730380224064,
          "paraphrase_len4_executor_accuracy": NaN,
          "paraphrase_len4_executor_target_mass": NaN,
          "paraphrase_len4_init_accuracy": NaN,
          "paraphrase_len4_op_accuracy": NaN,
          "paraphrase_len4_arg_accuracy": NaN,
          "paraphrase_len4_program_exact": NaN,
          "paraphrase_len4_state_accuracy": NaN,
          "paraphrase_len4_state_all_exact": NaN,
          "paraphrase_len4_state_prefix_fraction": NaN,
          "paraphrase_len8_direct_accuracy": 0.0,
          "paraphrase_len8_direct_target_mass": 0.009604912949725986,
          "paraphrase_len8_executor_accuracy": NaN,
          "paraphrase_len8_executor_target_mass": NaN,
          "paraphrase_len8_init_accuracy": NaN,
          "paraphrase_len8_op_accuracy": NaN,
          "paraphrase_len8_arg_accuracy": NaN,
          "paraphrase_len8_program_exact": NaN,
          "paraphrase_len8_state_accuracy": NaN,
          "paraphrase_len8_state_all_exact": NaN,
          "paraphrase_len8_state_prefix_fraction": NaN,
          "paraphrase_len12_direct_accuracy": 0.015625,
          "paraphrase_len12_direct_target_mass": 0.010256750218104571,
          "paraphrase_len12_executor_accuracy": NaN,
          "paraphrase_len12_executor_target_mass": NaN,
          "paraphrase_len12_init_accuracy": NaN,
          "paraphrase_len12_op_accuracy": NaN,
          "paraphrase_len12_arg_accuracy": NaN,
          "paraphrase_len12_program_exact": NaN,
          "paraphrase_len12_state_accuracy": NaN,
          "paraphrase_len12_state_all_exact": NaN,
          "paraphrase_len12_state_prefix_fraction": NaN,
          "paraphrase_len24_direct_accuracy": 0.0,
          "paraphrase_len24_direct_target_mass": 0.010861504706554115,
          "paraphrase_len24_executor_accuracy": NaN,
          "paraphrase_len24_executor_target_mass": NaN,
          "paraphrase_len24_init_accuracy": NaN,
          "paraphrase_len24_op_accuracy": NaN,
          "paraphrase_len24_arg_accuracy": NaN,
          "paraphrase_len24_program_exact": NaN,
          "paraphrase_len24_state_accuracy": NaN,
          "paraphrase_len24_state_all_exact": NaN,
          "paraphrase_len24_state_prefix_fraction": NaN,
          "paired_len4_direct_accuracy": 0.0078125,
          "paired_len4_direct_target_mass": 0.011512628785567358,
          "paired_len4_executor_accuracy": NaN,
          "paired_len4_executor_target_mass": NaN,
          "paired_len4_init_accuracy": NaN,
          "paired_len4_op_accuracy": NaN,
          "paired_len4_arg_accuracy": NaN,
          "paired_len4_program_exact": NaN,
          "paired_len4_state_accuracy": NaN,
          "paired_len4_state_all_exact": NaN,
          "paired_len4_state_prefix_fraction": NaN,
          "paired_len4_pair_true_answer_consistency": 1.0,
          "paired_len4_direct_pair_answer_consistency": 0.0,
          "paired_len4_direct_pair_both_correct": 0.0,
          "paired_len8_direct_accuracy": 0.015625,
          "paired_len8_direct_target_mass": 0.01012100515072234,
          "paired_len8_executor_accuracy": NaN,
          "paired_len8_executor_target_mass": NaN,
          "paired_len8_init_accuracy": NaN,
          "paired_len8_op_accuracy": NaN,
          "paired_len8_arg_accuracy": NaN,
          "paired_len8_program_exact": NaN,
          "paired_len8_state_accuracy": NaN,
          "paired_len8_state_all_exact": NaN,
          "paired_len8_state_prefix_fraction": NaN,
          "paired_len8_pair_true_answer_consistency": 1.0,
          "paired_len8_direct_pair_answer_consistency": 0.0,
          "paired_len8_direct_pair_both_correct": 0.0,
          "paired_len12_direct_accuracy": 0.015625,
          "paired_len12_direct_target_mass": 0.011790893171564676,
          "paired_len12_executor_accuracy": NaN,
          "paired_len12_executor_target_mass": NaN,
          "paired_len12_init_accuracy": NaN,
          "paired_len12_op_accuracy": NaN,
          "paired_len12_arg_accuracy": NaN,
          "paired_len12_program_exact": NaN,
          "paired_len12_state_accuracy": NaN,
          "paired_len12_state_all_exact": NaN,
          "paired_len12_state_prefix_fraction": NaN,
          "paired_len12_pair_true_answer_consistency": 1.0,
          "paired_len12_direct_pair_answer_consistency": 0.0,
          "paired_len12_direct_pair_both_correct": 0.0,
          "paired_len24_direct_accuracy": 0.0078125,
          "paired_len24_direct_target_mass": 0.009576360636856407,
          "paired_len24_executor_accuracy": NaN,
          "paired_len24_executor_target_mass": NaN,
          "paired_len24_init_accuracy": NaN,
          "paired_len24_op_accuracy": NaN,
          "paired_len24_arg_accuracy": NaN,
          "paired_len24_program_exact": NaN,
          "paired_len24_state_accuracy": NaN,
          "paired_len24_state_all_exact": NaN,
          "paired_len24_state_prefix_fraction": NaN,
          "paired_len24_pair_true_answer_consistency": 1.0,
          "paired_len24_direct_pair_answer_consistency": 0.0,
          "paired_len24_direct_pair_both_correct": 0.0
        },
        {
          "variant": "direct",
          "stage": "answer_only",
          "local_step": 300,
          "step": 300,
          "loss": 3.871479034423828,
          "trace_loss_active": false,
          "executor_loss_active": false,
          "state_loss_active": false,
          "lr_scale": 1.0,
          "direct_loss": 3.871479034423828,
          "standard_len4_direct_accuracy": 0.015625,
          "standard_len4_direct_target_mass": 0.009979097987525165,
          "standard_len4_executor_accuracy": NaN,
          "standard_len4_executor_target_mass": NaN,
          "standard_len4_init_accuracy": NaN,
          "standard_len4_op_accuracy": NaN,
          "standard_len4_arg_accuracy": NaN,
          "standard_len4_program_exact": NaN,
          "standard_len4_state_accuracy": NaN,
          "standard_len4_state_all_exact": NaN,
          "standard_len4_state_prefix_fraction": NaN,
          "standard_len8_direct_accuracy": 0.015625,
          "standard_len8_direct_target_mass": 0.010282560833729804,
          "standard_len8_executor_accuracy": NaN,
          "standard_len8_executor_target_mass": NaN,
          "standard_len8_init_accuracy": NaN,
          "standard_len8_op_accuracy": NaN,
          "standard_len8_arg_accuracy": NaN,
          "standard_len8_program_exact": NaN,
          "standard_len8_state_accuracy": NaN,
          "standard_len8_state_all_exact": NaN,
          "standard_len8_state_prefix_fraction": NaN,
          "standard_len12_direct_accuracy": 0.015625,
          "standard_len12_direct_target_mass": 0.01085659972159192,
          "standard_len12_executor_accuracy": NaN,
          "standard_len12_executor_target_mass": NaN,
          "standard_len12_init_accuracy": NaN,
          "standard_len12_op_accuracy": NaN,
          "standard_len12_arg_accuracy": NaN,
          "standard_len12_program_exact": NaN,
          "standard_len12_state_accuracy": NaN,
          "standard_len12_state_all_exact": NaN,
          "standard_len12_state_prefix_fraction": NaN,
          "standard_len24_direct_accuracy": 0.03125,
          "standard_len24_direct_target_mass": 0.012475729861762375,
          "standard_len24_executor_accuracy": NaN,
          "standard_len24_executor_target_mass": NaN,
          "standard_len24_init_accuracy": NaN,
          "standard_len24_op_accuracy": NaN,
          "standard_len24_arg_accuracy": NaN,
          "standard_len24_program_exact": NaN,
          "standard_len24_state_accuracy": NaN,
          "standard_len24_state_all_exact": NaN,
          "standard_len24_state_prefix_fraction": NaN,
          "paraphrase_len4_direct_accuracy": 0.0,
          "paraphrase_len4_direct_target_mass": 0.009030730987433344,
          "paraphrase_len4_executor_accuracy": NaN,
          "paraphrase_len4_executor_target_mass": NaN,
          "paraphrase_len4_init_accuracy": NaN,
          "paraphrase_len4_op_accuracy": NaN,
          "paraphrase_len4_arg_accuracy": NaN,
          "paraphrase_len4_program_exact": NaN,
          "paraphrase_len4_state_accuracy": NaN,
          "paraphrase_len4_state_all_exact": NaN,
          "paraphrase_len4_state_prefix_fraction": NaN,
          "paraphrase_len8_direct_accuracy": 0.0,
          "paraphrase_len8_direct_target_mass": 0.009098326787352562,
          "paraphrase_len8_executor_accuracy": NaN,
          "paraphrase_len8_executor_target_mass": NaN,
          "paraphrase_len8_init_accuracy": NaN,
          "paraphrase_len8_op_accuracy": NaN,
          "paraphrase_len8_arg_accuracy": NaN,
          "paraphrase_len8_program_exact": NaN,
          "paraphrase_len8_state_accuracy": NaN,
          "paraphrase_len8_state_all_exact": NaN,
          "paraphrase_len8_state_prefix_fraction": NaN,
          "paraphrase_len12_direct_accuracy": 0.0,
          "paraphrase_len12_direct_target_mass": 0.009421012888196856,
          "paraphrase_len12_executor_accuracy": NaN,
          "paraphrase_len12_executor_target_mass": NaN,
          "paraphrase_len12_init_accuracy": NaN,
          "paraphrase_len12_op_accuracy": NaN,
          "paraphrase_len12_arg_accuracy": NaN,
          "paraphrase_len12_program_exact": NaN,
          "paraphrase_len12_state_accuracy": NaN,
          "paraphrase_len12_state_all_exact": NaN,
          "paraphrase_len12_state_prefix_fraction": NaN,
          "paraphrase_len24_direct_accuracy": 0.0,
          "paraphrase_len24_direct_target_mass": 0.009803309803828597,
          "paraphrase_len24_executor_accuracy": NaN,
          "paraphrase_len24_executor_target_mass": NaN,
          "paraphrase_len24_init_accuracy": NaN,
          "paraphrase_len24_op_accuracy": NaN,
          "paraphrase_len24_arg_accuracy": NaN,
          "paraphrase_len24_program_exact": NaN,
          "paraphrase_len24_state_accuracy": NaN,
          "paraphrase_len24_state_all_exact": NaN,
          "paraphrase_len24_state_prefix_fraction": NaN,
          "paired_len4_direct_accuracy": 0.0078125,
          "paired_len4_direct_target_mass": 0.011186226387508214,
          "paired_len4_executor_accuracy": NaN,
          "paired_len4_executor_target_mass": NaN,
          "paired_len4_init_accuracy": NaN,
          "paired_len4_op_accuracy": NaN,
          "paired_len4_arg_accuracy": NaN,
          "paired_len4_program_exact": NaN,
          "paired_len4_state_accuracy": NaN,
          "paired_len4_state_all_exact": NaN,
          "paired_len4_state_prefix_fraction": NaN,
          "paired_len4_pair_true_answer_consistency": 1.0,
          "paired_len4_direct_pair_answer_consistency": 0.0,
          "paired_len4_direct_pair_both_correct": 0.0,
          "paired_len8_direct_accuracy": 0.0,
          "paired_len8_direct_target_mass": 0.0106004418048542,
          "paired_len8_executor_accuracy": NaN,
          "paired_len8_executor_target_mass": NaN,
          "paired_len8_init_accuracy": NaN,
          "paired_len8_op_accuracy": NaN,
          "paired_len8_arg_accuracy": NaN,
          "paired_len8_program_exact": NaN,
          "paired_len8_state_accuracy": NaN,
          "paired_len8_state_all_exact": NaN,
          "paired_len8_state_prefix_fraction": NaN,
          "paired_len8_pair_true_answer_consistency": 1.0,
          "paired_len8_direct_pair_answer_consistency": 0.0,
          "paired_len8_direct_pair_both_correct": 0.0,
          "paired_len12_direct_accuracy": 0.015625,
          "paired_len12_direct_target_mass": 0.0123308481706772,
          "paired_len12_executor_accuracy": NaN,
          "paired_len12_executor_target_mass": NaN,
          "paired_len12_init_accuracy": NaN,
          "paired_len12_op_accuracy": NaN,
          "paired_len12_arg_accuracy": NaN,
          "paired_len12_program_exact": NaN,
          "paired_len12_state_accuracy": NaN,
          "paired_len12_state_all_exact": NaN,
          "paired_len12_state_prefix_fraction": NaN,
          "paired_len12_pair_true_answer_consistency": 1.0,
          "paired_len12_direct_pair_answer_consistency": 0.0,
          "paired_len12_direct_pair_both_correct": 0.0,
          "paired_len24_direct_accuracy": 0.015625,
          "paired_len24_direct_target_mass": 0.00973344044177793,
          "paired_len24_executor_accuracy": NaN,
          "paired_len24_executor_target_mass": NaN,
          "paired_len24_init_accuracy": NaN,
          "paired_len24_op_accuracy": NaN,
          "paired_len24_arg_accuracy": NaN,
          "paired_len24_program_exact": NaN,
          "paired_len24_state_accuracy": NaN,
          "paired_len24_state_all_exact": NaN,
          "paired_len24_state_prefix_fraction": NaN,
          "paired_len24_pair_true_answer_consistency": 1.0,
          "paired_len24_direct_pair_answer_consistency": 0.0,
          "paired_len24_direct_pair_both_correct": 0.0
        }
      ],
      "final_metrics": {
        "standard_len4": {
          "variant": "direct",
          "n": 64.0,
          "direct_accuracy": 0.015625,
          "direct_target_mass": 0.009979097987525165,
          "executor_accuracy": NaN,
          "executor_target_mass": NaN,
          "init_accuracy": NaN,
          "op_accuracy": NaN,
          "arg_accuracy": NaN,
          "program_exact": NaN,
          "state_accuracy": NaN,
          "state_all_exact": NaN,
          "state_prefix_fraction": NaN
        },
        "standard_len8": {
          "variant": "direct",
          "n": 64.0,
          "direct_accuracy": 0.015625,
          "direct_target_mass": 0.010282560833729804,
          "executor_accuracy": NaN,
          "executor_target_mass": NaN,
          "init_accuracy": NaN,
          "op_accuracy": NaN,
          "arg_accuracy": NaN,
          "program_exact": NaN,
          "state_accuracy": NaN,
          "state_all_exact": NaN,
          "state_prefix_fraction": NaN
        },
        "standard_len12": {
          "variant": "direct",
          "n": 64.0,
          "direct_accuracy": 0.015625,
          "direct_target_mass": 0.01085659972159192,
          "executor_accuracy": NaN,
          "executor_target_mass": NaN,
          "init_accuracy": NaN,
          "op_accuracy": NaN,
          "arg_accuracy": NaN,
          "program_exact": NaN,
          "state_accuracy": NaN,
          "state_all_exact": NaN,
          "state_prefix_fraction": NaN
        },
        "standard_len24": {
          "variant": "direct",
          "n": 64.0,
          "direct_accuracy": 0.03125,
          "direct_target_mass": 0.012475729861762375,
          "executor_accuracy": NaN,
          "executor_target_mass": NaN,
          "init_accuracy": NaN,
          "op_accuracy": NaN,
          "arg_accuracy": NaN,
          "program_exact": NaN,
          "state_accuracy": NaN,
          "state_all_exact": NaN,
          "state_prefix_fraction": NaN
        },
        "paraphrase_len4": {
          "variant": "direct",
          "n": 64.0,
          "direct_accuracy": 0.0,
          "direct_target_mass": 0.009030730987433344,
          "executor_accuracy": NaN,
          "executor_target_mass": NaN,
          "init_accuracy": NaN,
          "op_accuracy": NaN,
          "arg_accuracy": NaN,
          "program_exact": NaN,
          "state_accuracy": NaN,
          "state_all_exact": NaN,
          "state_prefix_fraction": NaN
        },
        "paraphrase_len8": {
          "variant": "direct",
          "n": 64.0,
          "direct_accuracy": 0.0,
          "direct_target_mass": 0.009098326787352562,
          "executor_accuracy": NaN,
          "executor_target_mass": NaN,
          "init_accuracy": NaN,
          "op_accuracy": NaN,
          "arg_accuracy": NaN,
          "program_exact": NaN,
          "state_accuracy": NaN,
          "state_all_exact": NaN,
          "state_prefix_fraction": NaN
        },
        "paraphrase_len12": {
          "variant": "direct",
          "n": 64.0,
          "direct_accuracy": 0.0,
          "direct_target_mass": 0.009421012888196856,
          "executor_accuracy": NaN,
          "executor_target_mass": NaN,
          "init_accuracy": NaN,
          "op_accuracy": NaN,
          "arg_accuracy": NaN,
          "program_exact": NaN,
          "state_accuracy": NaN,
          "state_all_exact": NaN,
          "state_prefix_fraction": NaN
        },
        "paraphrase_len24": {
          "variant": "direct",
          "n": 64.0,
          "direct_accuracy": 0.0,
          "direct_target_mass": 0.009803309803828597,
          "executor_accuracy": NaN,
          "executor_target_mass": NaN,
          "init_accuracy": NaN,
          "op_accuracy": NaN,
          "arg_accuracy": NaN,
          "program_exact": NaN,
          "state_accuracy": NaN,
          "state_all_exact": NaN,
          "state_prefix_fraction": NaN
        },
        "paired_len4": {
          "variant": "direct",
          "n": 128.0,
          "direct_accuracy": 0.0078125,
          "direct_target_mass": 0.011186226387508214,
          "executor_accuracy": NaN,
          "executor_target_mass": NaN,
          "init_accuracy": NaN,
          "op_accuracy": NaN,
          "arg_accuracy": NaN,
          "program_exact": NaN,
          "state_accuracy": NaN,
          "state_all_exact": NaN,
          "state_prefix_fraction": NaN,
          "pair_true_answer_consistency": 1.0,
          "direct_pair_answer_consistency": 0.0,
          "direct_pair_both_correct": 0.0
        },
        "paired_len8": {
          "variant": "direct",
          "n": 128.0,
          "direct_accuracy": 0.0,
          "direct_target_mass": 0.0106004418048542,
          "executor_accuracy": NaN,
          "executor_target_mass": NaN,
          "init_accuracy": NaN,
          "op_accuracy": NaN,
          "arg_accuracy": NaN,
          "program_exact": NaN,
          "state_accuracy": NaN,
          "state_all_exact": NaN,
          "state_prefix_fraction": NaN,
          "pair_true_answer_consistency": 1.0,
          "direct_pair_answer_consistency": 0.0,
          "direct_pair_both_correct": 0.0
        },
        "paired_len12": {
          "variant": "direct",
          "n": 128.0,
          "direct_accuracy": 0.015625,
          "direct_target_mass": 0.0123308481706772,
          "executor_accuracy": NaN,
          "executor_target_mass": NaN,
          "init_accuracy": NaN,
          "op_accuracy": NaN,
          "arg_accuracy": NaN,
          "program_exact": NaN,
          "state_accuracy": NaN,
          "state_all_exact": NaN,
          "state_prefix_fraction": NaN,
          "pair_true_answer_consistency": 1.0,
          "direct_pair_answer_consistency": 0.0,
          "direct_pair_both_correct": 0.0
        },
        "paired_len24": {
          "variant": "direct",
          "n": 128.0,
          "direct_accuracy": 0.015625,
          "direct_target_mass": 0.00973344044177793,
          "executor_accuracy": NaN,
          "executor_target_mass": NaN,
          "init_accuracy": NaN,
          "op_accuracy": NaN,
          "arg_accuracy": NaN,
          "program_exact": NaN,
          "state_accuracy": NaN,
          "state_all_exact": NaN,
          "state_prefix_fraction": NaN,
          "pair_true_answer_consistency": 1.0,
          "direct_pair_answer_consistency": 0.0,
          "direct_pair_both_correct": 0.0
        }
      }
    }
  }
}