{
  "args": {
    "model_id": "Qwen/Qwen3-4B",
    "load_in_4bit": true,
    "torch_dtype": "bf16",
    "device_map": "auto",
    "use_lora": true,
    "lora_r": 4,
    "lora_alpha": 8,
    "lora_dropout": 0.05,
    "lora_target_modules": "all-linear",
    "gradient_checkpointing": true,
    "optimizer": "paged_adamw_8bit",
    "modulus": 97,
    "max_steps": 4,
    "train_min_len": 1,
    "train_max_len": 12,
    "curriculum_stages": "short:1:2:2,long:2:4:2",
    "answer_train_min_len": 1,
    "answer_train_max_len": 24,
    "eval_lengths": "2,4",
    "train_template_mode": "mixed",
    "paired_train": false,
    "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": 32,
    "answer_train_size": 32,
    "eval_size": 4,
    "train_batch_size": 2,
    "eval_batch_size": 2,
    "bootstrap_steps": 0,
    "answer_steps": 0,
    "eval_every": 2,
    "stage_eval_every": 2,
    "lr": 0.0002,
    "answer_lr_scale": 0.1,
    "weight_decay": 0.0,
    "grad_clip": 1.0,
    "head_width": 128,
    "rank_temperature": 1.0,
    "arg_reader_mode": "after_op",
    "arg_window": 8,
    "arg_distance_temperature": 2.0,
    "trace_loss_weight": 1.0,
    "init_trace_loss_weight": 4.0,
    "op_trace_loss_weight": 1.0,
    "arg_trace_loss_weight": 4.0,
    "selection_loss_weight": 1.0,
    "role_pos_weight": 20.0,
    "init_selection_loss_weight": 1.0,
    "op_selection_loss_weight": 1.0,
    "arg_selection_loss_weight": 4.0,
    "executor_loss_weight": 1.0,
    "state_loss_weight": 0.25,
    "state_loss_schedule": "constant",
    "teacher_position_loss_weight": 0.1,
    "teacher_rep_loss_weight": 0.05,
    "teacher_position_sigma": 1.0,
    "teacher_rep_temperature": 1.0,
    "teacher_init_window": 6,
    "teacher_op_window": 2,
    "teacher_arg_window": 3,
    "teacher_init_loss_weight": 1.0,
    "teacher_op_loss_weight": 1.0,
    "teacher_arg_loss_weight": 4.0,
    "save_eval_checkpoints": true,
    "selection_metric": "paired_len4_executor_accuracy",
    "variants": "copy_trace_state_teacher",
    "max_length": 192,
    "seed": 7,
    "train_seed": -1,
    "output_dir": "experiments/qwen_teacher_distilled_slot_compiler/runs/smoke_qwen3_4b_teacher",
    "checkpoint_dir": "",
    "state_loss_weight_by_stage": {
      "short": 0.25,
      "long": 0.25
    }
  },
  "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": 4,
    "gpu_name": "NVIDIA RTX 6000 Ada Generation",
    "gpu_vram_gb": 47.383
  },
  "hidden_dim": 2560,
  "dataset": {
    "train_size": 32,
    "train_examples": 64,
    "curriculum_stages": [
      {
        "name": "short",
        "min_len": 1,
        "max_len": 2,
        "steps": 2
      },
      {
        "name": "long",
        "min_len": 2,
        "max_len": 4,
        "steps": 2
      }
    ],
    "state_loss_weight_by_stage": {
      "short": 0.25,
      "long": 0.25
    },
    "answer_train_size": 32,
    "eval_size": 4,
    "train_lengths": [
      1,
      12
    ],
    "answer_train_lengths": [
      1,
      24
    ],
    "eval_lengths": [
      2,
      4
    ],
    "train_template_mode": "mixed",
    "paired_train": false,
    "paired_batches": 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"
    ]
  },
  "variants": {
    "copy_trace_state_teacher": {
      "variant": "copy_trace_state_teacher",
      "train_seconds": 13.629915952682495,
      "checkpoints": [
        {
          "variant": "copy_trace_state_teacher",
          "tag": "eval_trace_state_teacher_short",
          "step": 1,
          "checkpoint_dir": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00001",
          "model_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00001/adapter",
          "heads_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00001/heads.pt",
          "selection_metric": "paired_len4_executor_accuracy",
          "selection_value": 0.0
        },
        {
          "variant": "copy_trace_state_teacher",
          "tag": "eval_trace_state_teacher_short",
          "step": 2,
          "checkpoint_dir": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00002",
          "model_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00002/adapter",
          "heads_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00002/heads.pt",
          "selection_metric": "paired_len4_executor_accuracy",
          "selection_value": 0.0
        },
        {
          "variant": "copy_trace_state_teacher",
          "tag": "eval_trace_state_teacher_long",
          "step": 3,
          "checkpoint_dir": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_long_step00003",
          "model_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_long_step00003/adapter",
          "heads_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_long_step00003/heads.pt",
          "selection_metric": "paired_len4_executor_accuracy",
          "selection_value": 0.0
        },
        {
          "variant": "copy_trace_state_teacher",
          "tag": "eval_trace_state_teacher_long",
          "step": 4,
          "checkpoint_dir": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_long_step00004",
          "model_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_long_step00004/adapter",
          "heads_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_long_step00004/heads.pt",
          "selection_metric": "paired_len4_executor_accuracy",
          "selection_value": 0.0
        },
        {
          "variant": "copy_trace_state_teacher",
          "tag": "final",
          "step": 4,
          "checkpoint_dir": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/final_step00004",
          "model_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/final_step00004/adapter",
          "heads_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/final_step00004/heads.pt",
          "selection_metric": "paired_len4_executor_accuracy",
          "selection_value": 0.0
        }
      ],
      "selected_checkpoint": {
        "variant": "copy_trace_state_teacher",
        "tag": "eval_trace_state_teacher_short",
        "step": 1,
        "checkpoint_dir": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00001",
        "model_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00001/adapter",
        "heads_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_qwen3_4b_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00001/heads.pt",
        "selection_metric": "paired_len4_executor_accuracy",
        "selection_value": 0.0
      },
      "train_log": [
        {
          "variant": "copy_trace_state_teacher",
          "stage": "trace_state_teacher_short",
          "local_step": 1,
          "step": 1,
          "loss": 32.92429733276367,
          "trace_loss_active": true,
          "executor_loss_active": true,
          "state_loss_active": true,
          "state_loss_weight": 0.25,
          "teacher_position_loss_weight": 0.1,
          "teacher_rep_loss_weight": 0.05,
          "lr_scale": 1.0,
          "executor_loss": 0.8875846862792969,
          "state_loss": 0.8875846862792969,
          "state_train_accuracy": 0.0,
          "init_loss": 0.3979347050189972,
          "op_loss": 0.0,
          "arg_loss": 1.420189619064331,
          "init_attn_loss": 3.5250463485717773,
          "op_attn_loss": 3.3406333923339844,
          "arg_attn_loss": 3.4968509674072266,
          "role_loss": 1.5635699033737183,
          "teacher_init_pos_loss": 3.531594753265381,
          "teacher_op_pos_loss": 3.3406333923339844,
          "teacher_arg_pos_loss": 3.4968509674072266,
          "teacher_init_rep_loss": 0.13303864002227783,
          "teacher_op_rep_loss": 0.13942590355873108,
          "teacher_arg_rep_loss": 0.1303812861442566,
          "standard_len2_direct_accuracy": NaN,
          "standard_len2_direct_target_mass": NaN,
          "standard_len2_executor_accuracy": 0.0,
          "standard_len2_executor_target_mass": 0.08753952011466026,
          "standard_len2_init_accuracy": 0.5,
          "standard_len2_init_pos_accuracy": 0.0,
          "standard_len2_op_accuracy": 1.0,
          "standard_len2_arg_accuracy": 0.5,
          "standard_len2_op_pos_accuracy": 0.0,
          "standard_len2_arg_pos_accuracy": 0.25,
          "standard_len2_program_exact": 0.0,
          "standard_len2_state_accuracy": 0.0,
          "standard_len2_state_all_exact": 0.0,
          "standard_len2_state_prefix_fraction": 0.0,
          "standard_len2_state_mean_correct_prefix": 0.0,
          "standard_len4_direct_accuracy": NaN,
          "standard_len4_direct_target_mass": NaN,
          "standard_len4_executor_accuracy": 0.0,
          "standard_len4_executor_target_mass": 0.010950693394988775,
          "standard_len4_init_accuracy": 0.75,
          "standard_len4_init_pos_accuracy": 0.0,
          "standard_len4_op_accuracy": 0.75,
          "standard_len4_arg_accuracy": 0.4375,
          "standard_len4_op_pos_accuracy": 0.0,
          "standard_len4_arg_pos_accuracy": 0.125,
          "standard_len4_program_exact": 0.0,
          "standard_len4_state_accuracy": 0.0,
          "standard_len4_state_all_exact": 0.0,
          "standard_len4_state_prefix_fraction": 0.0,
          "standard_len4_state_mean_correct_prefix": 0.0,
          "paraphrase_len2_direct_accuracy": NaN,
          "paraphrase_len2_direct_target_mass": NaN,
          "paraphrase_len2_executor_accuracy": 0.25,
          "paraphrase_len2_executor_target_mass": 0.08470536395907402,
          "paraphrase_len2_init_accuracy": 0.5,
          "paraphrase_len2_init_pos_accuracy": 0.0,
          "paraphrase_len2_op_accuracy": 1.0,
          "paraphrase_len2_arg_accuracy": 0.5,
          "paraphrase_len2_op_pos_accuracy": 0.0,
          "paraphrase_len2_arg_pos_accuracy": 0.0,
          "paraphrase_len2_program_exact": 0.0,
          "paraphrase_len2_state_accuracy": 0.25,
          "paraphrase_len2_state_all_exact": 0.25,
          "paraphrase_len2_state_prefix_fraction": 0.25,
          "paraphrase_len2_state_mean_correct_prefix": 0.5,
          "paraphrase_len4_direct_accuracy": NaN,
          "paraphrase_len4_direct_target_mass": NaN,
          "paraphrase_len4_executor_accuracy": 0.0,
          "paraphrase_len4_executor_target_mass": 0.012598395347595215,
          "paraphrase_len4_init_accuracy": 1.0,
          "paraphrase_len4_init_pos_accuracy": 0.25,
          "paraphrase_len4_op_accuracy": 0.6875,
          "paraphrase_len4_arg_accuracy": 0.5625,
          "paraphrase_len4_op_pos_accuracy": 0.0,
          "paraphrase_len4_arg_pos_accuracy": 0.125,
          "paraphrase_len4_program_exact": 0.0,
          "paraphrase_len4_state_accuracy": 0.0,
          "paraphrase_len4_state_all_exact": 0.0,
          "paraphrase_len4_state_prefix_fraction": 0.0,
          "paraphrase_len4_state_mean_correct_prefix": 0.0,
          "paired_len2_direct_accuracy": NaN,
          "paired_len2_direct_target_mass": NaN,
          "paired_len2_executor_accuracy": 0.0,
          "paired_len2_executor_target_mass": 0.060381281189620495,
          "paired_len2_init_accuracy": 0.75,
          "paired_len2_init_pos_accuracy": 0.0,
          "paired_len2_op_accuracy": 1.0,
          "paired_len2_arg_accuracy": 0.25,
          "paired_len2_op_pos_accuracy": 0.0625,
          "paired_len2_arg_pos_accuracy": 0.125,
          "paired_len2_program_exact": 0.0,
          "paired_len2_state_accuracy": 0.0,
          "paired_len2_state_all_exact": 0.0,
          "paired_len2_state_prefix_fraction": 0.0,
          "paired_len2_state_mean_correct_prefix": 0.0,
          "paired_len2_pair_true_answer_consistency": 1.0,
          "paired_len2_pair_true_length_consistency": 1.0,
          "paired_len2_executor_pair_answer_consistency": 1.0,
          "paired_len2_executor_pair_both_correct": 0.0,
          "paired_len2_compiler_pair_program_consistency": 1.0,
          "paired_len2_compiler_pair_state_consistency": 1.0,
          "paired_len4_direct_accuracy": NaN,
          "paired_len4_direct_target_mass": NaN,
          "paired_len4_executor_accuracy": 0.0,
          "paired_len4_executor_target_mass": 0.03735468024387956,
          "paired_len4_init_accuracy": 0.75,
          "paired_len4_init_pos_accuracy": 0.0,
          "paired_len4_op_accuracy": 0.8125,
          "paired_len4_arg_accuracy": 0.53125,
          "paired_len4_op_pos_accuracy": 0.0625,
          "paired_len4_arg_pos_accuracy": 0.0625,
          "paired_len4_program_exact": 0.0,
          "paired_len4_state_accuracy": 0.03125,
          "paired_len4_state_all_exact": 0.0,
          "paired_len4_state_prefix_fraction": 0.03125,
          "paired_len4_state_mean_correct_prefix": 0.125,
          "paired_len4_pair_true_answer_consistency": 1.0,
          "paired_len4_pair_true_length_consistency": 1.0,
          "paired_len4_executor_pair_answer_consistency": 0.25,
          "paired_len4_executor_pair_both_correct": 0.0,
          "paired_len4_compiler_pair_program_consistency": 0.25,
          "paired_len4_compiler_pair_state_consistency": 0.25
        },
        {
          "variant": "copy_trace_state_teacher",
          "stage": "trace_state_teacher_short",
          "local_step": 2,
          "step": 2,
          "loss": 34.24158477783203,
          "trace_loss_active": true,
          "executor_loss_active": true,
          "state_loss_active": true,
          "state_loss_weight": 0.25,
          "teacher_position_loss_weight": 0.1,
          "teacher_rep_loss_weight": 0.05,
          "lr_scale": 1.0,
          "executor_loss": 1.6281940937042236,
          "state_loss": 1.6037944555282593,
          "state_train_accuracy": 0.3333333432674408,
          "init_loss": 0.792438805103302,
          "op_loss": 0.31490322947502136,
          "arg_loss": 0.9967775940895081,
          "init_attn_loss": 3.6857335567474365,
          "op_attn_loss": 3.3528378009796143,
          "arg_attn_loss": 3.4681804180145264,
          "role_loss": 1.7107874155044556,
          "teacher_init_pos_loss": 3.696739435195923,
          "teacher_op_pos_loss": 3.3528380393981934,
          "teacher_arg_pos_loss": 3.448183536529541,
          "teacher_init_rep_loss": 0.1385774314403534,
          "teacher_op_rep_loss": 0.17065715789794922,
          "teacher_arg_rep_loss": 0.09447803348302841,
          "standard_len2_direct_accuracy": NaN,
          "standard_len2_direct_target_mass": NaN,
          "standard_len2_executor_accuracy": 0.0,
          "standard_len2_executor_target_mass": 0.09048301912844181,
          "standard_len2_init_accuracy": 0.5,
          "standard_len2_init_pos_accuracy": 0.0,
          "standard_len2_op_accuracy": 1.0,
          "standard_len2_arg_accuracy": 0.625,
          "standard_len2_op_pos_accuracy": 0.125,
          "standard_len2_arg_pos_accuracy": 0.375,
          "standard_len2_program_exact": 0.0,
          "standard_len2_state_accuracy": 0.0,
          "standard_len2_state_all_exact": 0.0,
          "standard_len2_state_prefix_fraction": 0.0,
          "standard_len2_state_mean_correct_prefix": 0.0,
          "standard_len4_direct_accuracy": NaN,
          "standard_len4_direct_target_mass": NaN,
          "standard_len4_executor_accuracy": 0.0,
          "standard_len4_executor_target_mass": 0.008873460348695517,
          "standard_len4_init_accuracy": 0.75,
          "standard_len4_init_pos_accuracy": 0.0,
          "standard_len4_op_accuracy": 0.75,
          "standard_len4_arg_accuracy": 0.5,
          "standard_len4_op_pos_accuracy": 0.0,
          "standard_len4_arg_pos_accuracy": 0.125,
          "standard_len4_program_exact": 0.0,
          "standard_len4_state_accuracy": 0.0625,
          "standard_len4_state_all_exact": 0.0,
          "standard_len4_state_prefix_fraction": 0.0625,
          "standard_len4_state_mean_correct_prefix": 0.25,
          "paraphrase_len2_direct_accuracy": NaN,
          "paraphrase_len2_direct_target_mass": NaN,
          "paraphrase_len2_executor_accuracy": 0.5,
          "paraphrase_len2_executor_target_mass": 0.08712909370660782,
          "paraphrase_len2_init_accuracy": 0.75,
          "paraphrase_len2_init_pos_accuracy": 0.25,
          "paraphrase_len2_op_accuracy": 1.0,
          "paraphrase_len2_arg_accuracy": 0.625,
          "paraphrase_len2_op_pos_accuracy": 0.25,
          "paraphrase_len2_arg_pos_accuracy": 0.0,
          "paraphrase_len2_program_exact": 0.25,
          "paraphrase_len2_state_accuracy": 0.5,
          "paraphrase_len2_state_all_exact": 0.5,
          "paraphrase_len2_state_prefix_fraction": 0.5,
          "paraphrase_len2_state_mean_correct_prefix": 1.0,
          "paraphrase_len4_direct_accuracy": NaN,
          "paraphrase_len4_direct_target_mass": NaN,
          "paraphrase_len4_executor_accuracy": 0.0,
          "paraphrase_len4_executor_target_mass": 0.010890090838074684,
          "paraphrase_len4_init_accuracy": 1.0,
          "paraphrase_len4_init_pos_accuracy": 0.75,
          "paraphrase_len4_op_accuracy": 0.625,
          "paraphrase_len4_arg_accuracy": 0.4375,
          "paraphrase_len4_op_pos_accuracy": 0.0,
          "paraphrase_len4_arg_pos_accuracy": 0.0,
          "paraphrase_len4_program_exact": 0.0,
          "paraphrase_len4_state_accuracy": 0.0625,
          "paraphrase_len4_state_all_exact": 0.0,
          "paraphrase_len4_state_prefix_fraction": 0.0625,
          "paraphrase_len4_state_mean_correct_prefix": 0.25,
          "paired_len2_direct_accuracy": NaN,
          "paired_len2_direct_target_mass": NaN,
          "paired_len2_executor_accuracy": 0.25,
          "paired_len2_executor_target_mass": 0.05921641085296869,
          "paired_len2_init_accuracy": 0.75,
          "paired_len2_init_pos_accuracy": 0.125,
          "paired_len2_op_accuracy": 1.0,
          "paired_len2_arg_accuracy": 0.5,
          "paired_len2_op_pos_accuracy": 0.1875,
          "paired_len2_arg_pos_accuracy": 0.1875,
          "paired_len2_program_exact": 0.25,
          "paired_len2_state_accuracy": 0.375,
          "paired_len2_state_all_exact": 0.25,
          "paired_len2_state_prefix_fraction": 0.375,
          "paired_len2_state_mean_correct_prefix": 0.75,
          "paired_len2_pair_true_answer_consistency": 1.0,
          "paired_len2_pair_true_length_consistency": 1.0,
          "paired_len2_executor_pair_answer_consistency": 0.25,
          "paired_len2_executor_pair_both_correct": 0.25,
          "paired_len2_compiler_pair_program_consistency": 0.25,
          "paired_len2_compiler_pair_state_consistency": 0.25,
          "paired_len4_direct_accuracy": NaN,
          "paired_len4_direct_target_mass": NaN,
          "paired_len4_executor_accuracy": 0.0,
          "paired_len4_executor_target_mass": 0.03026254056021571,
          "paired_len4_init_accuracy": 0.75,
          "paired_len4_init_pos_accuracy": 0.25,
          "paired_len4_op_accuracy": 0.71875,
          "paired_len4_arg_accuracy": 0.4375,
          "paired_len4_op_pos_accuracy": 0.03125,
          "paired_len4_arg_pos_accuracy": 0.09375,
          "paired_len4_program_exact": 0.0,
          "paired_len4_state_accuracy": 0.03125,
          "paired_len4_state_all_exact": 0.0,
          "paired_len4_state_prefix_fraction": 0.03125,
          "paired_len4_state_mean_correct_prefix": 0.125,
          "paired_len4_pair_true_answer_consistency": 1.0,
          "paired_len4_pair_true_length_consistency": 1.0,
          "paired_len4_executor_pair_answer_consistency": 0.0,
          "paired_len4_executor_pair_both_correct": 0.0,
          "paired_len4_compiler_pair_program_consistency": 0.0,
          "paired_len4_compiler_pair_state_consistency": 0.0
        },
        {
          "variant": "copy_trace_state_teacher",
          "stage": "trace_state_teacher_long",
          "local_step": 1,
          "step": 3,
          "loss": 39.811859130859375,
          "trace_loss_active": true,
          "executor_loss_active": true,
          "state_loss_active": true,
          "state_loss_weight": 0.25,
          "teacher_position_loss_weight": 0.1,
          "teacher_rep_loss_weight": 0.05,
          "lr_scale": 1.0,
          "executor_loss": 3.824293851852417,
          "state_loss": 3.3277552127838135,
          "state_train_accuracy": 0.0,
          "init_loss": 1.2670648097991943,
          "op_loss": 0.3869956433773041,
          "arg_loss": 0.9856767058372498,
          "init_attn_loss": 3.9790871143341064,
          "op_attn_loss": 3.557871103286743,
          "arg_attn_loss": 3.3832931518554688,
          "role_loss": 2.5448429584503174,
          "teacher_init_pos_loss": 3.977065324783325,
          "teacher_op_pos_loss": 3.5456552505493164,
          "teacher_arg_pos_loss": 3.3969264030456543,
          "teacher_init_rep_loss": 0.1097283661365509,
          "teacher_op_rep_loss": 0.10742470622062683,
          "teacher_arg_rep_loss": 0.10394173115491867,
          "standard_len2_direct_accuracy": NaN,
          "standard_len2_direct_target_mass": NaN,
          "standard_len2_executor_accuracy": 0.0,
          "standard_len2_executor_target_mass": 0.0922438707202673,
          "standard_len2_init_accuracy": 0.5,
          "standard_len2_init_pos_accuracy": 0.0,
          "standard_len2_op_accuracy": 1.0,
          "standard_len2_arg_accuracy": 0.625,
          "standard_len2_op_pos_accuracy": 0.25,
          "standard_len2_arg_pos_accuracy": 0.5,
          "standard_len2_program_exact": 0.0,
          "standard_len2_state_accuracy": 0.0,
          "standard_len2_state_all_exact": 0.0,
          "standard_len2_state_prefix_fraction": 0.0,
          "standard_len2_state_mean_correct_prefix": 0.0,
          "standard_len4_direct_accuracy": NaN,
          "standard_len4_direct_target_mass": NaN,
          "standard_len4_executor_accuracy": 0.0,
          "standard_len4_executor_target_mass": 0.008676710072904825,
          "standard_len4_init_accuracy": 0.75,
          "standard_len4_init_pos_accuracy": 0.0,
          "standard_len4_op_accuracy": 0.75,
          "standard_len4_arg_accuracy": 0.5,
          "standard_len4_op_pos_accuracy": 0.1875,
          "standard_len4_arg_pos_accuracy": 0.125,
          "standard_len4_program_exact": 0.0,
          "standard_len4_state_accuracy": 0.0625,
          "standard_len4_state_all_exact": 0.0,
          "standard_len4_state_prefix_fraction": 0.0625,
          "standard_len4_state_mean_correct_prefix": 0.25,
          "paraphrase_len2_direct_accuracy": NaN,
          "paraphrase_len2_direct_target_mass": NaN,
          "paraphrase_len2_executor_accuracy": 0.25,
          "paraphrase_len2_executor_target_mass": 0.08785099536180496,
          "paraphrase_len2_init_accuracy": 0.75,
          "paraphrase_len2_init_pos_accuracy": 0.25,
          "paraphrase_len2_op_accuracy": 1.0,
          "paraphrase_len2_arg_accuracy": 0.75,
          "paraphrase_len2_op_pos_accuracy": 0.25,
          "paraphrase_len2_arg_pos_accuracy": 0.25,
          "paraphrase_len2_program_exact": 0.25,
          "paraphrase_len2_state_accuracy": 0.25,
          "paraphrase_len2_state_all_exact": 0.25,
          "paraphrase_len2_state_prefix_fraction": 0.25,
          "paraphrase_len2_state_mean_correct_prefix": 0.5,
          "paraphrase_len4_direct_accuracy": NaN,
          "paraphrase_len4_direct_target_mass": NaN,
          "paraphrase_len4_executor_accuracy": 0.0,
          "paraphrase_len4_executor_target_mass": 0.010831320658326149,
          "paraphrase_len4_init_accuracy": 1.0,
          "paraphrase_len4_init_pos_accuracy": 0.75,
          "paraphrase_len4_op_accuracy": 0.625,
          "paraphrase_len4_arg_accuracy": 0.4375,
          "paraphrase_len4_op_pos_accuracy": 0.0625,
          "paraphrase_len4_arg_pos_accuracy": 0.125,
          "paraphrase_len4_program_exact": 0.0,
          "paraphrase_len4_state_accuracy": 0.0625,
          "paraphrase_len4_state_all_exact": 0.0,
          "paraphrase_len4_state_prefix_fraction": 0.0625,
          "paraphrase_len4_state_mean_correct_prefix": 0.25,
          "paired_len2_direct_accuracy": NaN,
          "paired_len2_direct_target_mass": NaN,
          "paired_len2_executor_accuracy": 0.25,
          "paired_len2_executor_target_mass": 0.059613652527332306,
          "paired_len2_init_accuracy": 0.75,
          "paired_len2_init_pos_accuracy": 0.125,
          "paired_len2_op_accuracy": 1.0,
          "paired_len2_arg_accuracy": 0.5,
          "paired_len2_op_pos_accuracy": 0.25,
          "paired_len2_arg_pos_accuracy": 0.1875,
          "paired_len2_program_exact": 0.25,
          "paired_len2_state_accuracy": 0.375,
          "paired_len2_state_all_exact": 0.25,
          "paired_len2_state_prefix_fraction": 0.375,
          "paired_len2_state_mean_correct_prefix": 0.75,
          "paired_len2_pair_true_answer_consistency": 1.0,
          "paired_len2_pair_true_length_consistency": 1.0,
          "paired_len2_executor_pair_answer_consistency": 0.5,
          "paired_len2_executor_pair_both_correct": 0.25,
          "paired_len2_compiler_pair_program_consistency": 0.5,
          "paired_len2_compiler_pair_state_consistency": 0.5,
          "paired_len4_direct_accuracy": NaN,
          "paired_len4_direct_target_mass": NaN,
          "paired_len4_executor_accuracy": 0.0,
          "paired_len4_executor_target_mass": 0.02942522056400776,
          "paired_len4_init_accuracy": 0.75,
          "paired_len4_init_pos_accuracy": 0.125,
          "paired_len4_op_accuracy": 0.75,
          "paired_len4_arg_accuracy": 0.4375,
          "paired_len4_op_pos_accuracy": 0.125,
          "paired_len4_arg_pos_accuracy": 0.125,
          "paired_len4_program_exact": 0.0,
          "paired_len4_state_accuracy": 0.03125,
          "paired_len4_state_all_exact": 0.0,
          "paired_len4_state_prefix_fraction": 0.03125,
          "paired_len4_state_mean_correct_prefix": 0.125,
          "paired_len4_pair_true_answer_consistency": 1.0,
          "paired_len4_pair_true_length_consistency": 1.0,
          "paired_len4_executor_pair_answer_consistency": 0.0,
          "paired_len4_executor_pair_both_correct": 0.0,
          "paired_len4_compiler_pair_program_consistency": 0.0,
          "paired_len4_compiler_pair_state_consistency": 0.0
        },
        {
          "variant": "copy_trace_state_teacher",
          "stage": "trace_state_teacher_long",
          "local_step": 2,
          "step": 4,
          "loss": 38.09269714355469,
          "trace_loss_active": true,
          "executor_loss_active": true,
          "state_loss_active": true,
          "state_loss_weight": 0.25,
          "teacher_position_loss_weight": 0.1,
          "teacher_rep_loss_weight": 0.05,
          "lr_scale": 1.0,
          "executor_loss": 3.5780935287475586,
          "state_loss": 2.8695685863494873,
          "state_train_accuracy": 0.3333333432674408,
          "init_loss": 1.3414998054504395,
          "op_loss": 0.35180774331092834,
          "arg_loss": 0.7991903424263,
          "init_attn_loss": 3.84987735748291,
          "op_attn_loss": 3.4726722240448,
          "arg_attn_loss": 3.2561004161834717,
          "role_loss": 2.4729976654052734,
          "teacher_init_pos_loss": 3.8486156463623047,
          "teacher_op_pos_loss": 3.4726722240448,
          "teacher_arg_pos_loss": 3.257807731628418,
          "teacher_init_rep_loss": 0.09340691566467285,
          "teacher_op_rep_loss": 0.10451185703277588,
          "teacher_arg_rep_loss": 0.0877295434474945,
          "standard_len2_direct_accuracy": NaN,
          "standard_len2_direct_target_mass": NaN,
          "standard_len2_executor_accuracy": 0.0,
          "standard_len2_executor_target_mass": 0.09424769505858421,
          "standard_len2_init_accuracy": 0.5,
          "standard_len2_init_pos_accuracy": 0.0,
          "standard_len2_op_accuracy": 1.0,
          "standard_len2_arg_accuracy": 0.625,
          "standard_len2_op_pos_accuracy": 0.25,
          "standard_len2_arg_pos_accuracy": 0.75,
          "standard_len2_program_exact": 0.0,
          "standard_len2_state_accuracy": 0.0,
          "standard_len2_state_all_exact": 0.0,
          "standard_len2_state_prefix_fraction": 0.0,
          "standard_len2_state_mean_correct_prefix": 0.0,
          "standard_len4_direct_accuracy": NaN,
          "standard_len4_direct_target_mass": NaN,
          "standard_len4_executor_accuracy": 0.0,
          "standard_len4_executor_target_mass": 0.009107958525419235,
          "standard_len4_init_accuracy": 0.75,
          "standard_len4_init_pos_accuracy": 0.0,
          "standard_len4_op_accuracy": 0.75,
          "standard_len4_arg_accuracy": 0.5,
          "standard_len4_op_pos_accuracy": 0.125,
          "standard_len4_arg_pos_accuracy": 0.1875,
          "standard_len4_program_exact": 0.0,
          "standard_len4_state_accuracy": 0.0625,
          "standard_len4_state_all_exact": 0.0,
          "standard_len4_state_prefix_fraction": 0.0625,
          "standard_len4_state_mean_correct_prefix": 0.25,
          "paraphrase_len2_direct_accuracy": NaN,
          "paraphrase_len2_direct_target_mass": NaN,
          "paraphrase_len2_executor_accuracy": 0.25,
          "paraphrase_len2_executor_target_mass": 0.08972702920436859,
          "paraphrase_len2_init_accuracy": 0.75,
          "paraphrase_len2_init_pos_accuracy": 0.25,
          "paraphrase_len2_op_accuracy": 1.0,
          "paraphrase_len2_arg_accuracy": 0.75,
          "paraphrase_len2_op_pos_accuracy": 0.375,
          "paraphrase_len2_arg_pos_accuracy": 0.375,
          "paraphrase_len2_program_exact": 0.25,
          "paraphrase_len2_state_accuracy": 0.25,
          "paraphrase_len2_state_all_exact": 0.25,
          "paraphrase_len2_state_prefix_fraction": 0.25,
          "paraphrase_len2_state_mean_correct_prefix": 0.5,
          "paraphrase_len4_direct_accuracy": NaN,
          "paraphrase_len4_direct_target_mass": NaN,
          "paraphrase_len4_executor_accuracy": 0.0,
          "paraphrase_len4_executor_target_mass": 0.011130061000585556,
          "paraphrase_len4_init_accuracy": 1.0,
          "paraphrase_len4_init_pos_accuracy": 0.75,
          "paraphrase_len4_op_accuracy": 0.625,
          "paraphrase_len4_arg_accuracy": 0.4375,
          "paraphrase_len4_op_pos_accuracy": 0.0625,
          "paraphrase_len4_arg_pos_accuracy": 0.1875,
          "paraphrase_len4_program_exact": 0.0,
          "paraphrase_len4_state_accuracy": 0.0625,
          "paraphrase_len4_state_all_exact": 0.0,
          "paraphrase_len4_state_prefix_fraction": 0.0625,
          "paraphrase_len4_state_mean_correct_prefix": 0.25,
          "paired_len2_direct_accuracy": NaN,
          "paired_len2_direct_target_mass": NaN,
          "paired_len2_executor_accuracy": 0.25,
          "paired_len2_executor_target_mass": 0.061364601366221905,
          "paired_len2_init_accuracy": 0.75,
          "paired_len2_init_pos_accuracy": 0.125,
          "paired_len2_op_accuracy": 1.0,
          "paired_len2_arg_accuracy": 0.5,
          "paired_len2_op_pos_accuracy": 0.1875,
          "paired_len2_arg_pos_accuracy": 0.3125,
          "paired_len2_program_exact": 0.25,
          "paired_len2_state_accuracy": 0.375,
          "paired_len2_state_all_exact": 0.25,
          "paired_len2_state_prefix_fraction": 0.375,
          "paired_len2_state_mean_correct_prefix": 0.75,
          "paired_len2_pair_true_answer_consistency": 1.0,
          "paired_len2_pair_true_length_consistency": 1.0,
          "paired_len2_executor_pair_answer_consistency": 0.5,
          "paired_len2_executor_pair_both_correct": 0.25,
          "paired_len2_compiler_pair_program_consistency": 0.5,
          "paired_len2_compiler_pair_state_consistency": 0.5,
          "paired_len4_direct_accuracy": NaN,
          "paired_len4_direct_target_mass": NaN,
          "paired_len4_executor_accuracy": 0.0,
          "paired_len4_executor_target_mass": 0.031201052479445934,
          "paired_len4_init_accuracy": 0.75,
          "paired_len4_init_pos_accuracy": 0.25,
          "paired_len4_op_accuracy": 0.71875,
          "paired_len4_arg_accuracy": 0.46875,
          "paired_len4_op_pos_accuracy": 0.15625,
          "paired_len4_arg_pos_accuracy": 0.15625,
          "paired_len4_program_exact": 0.0,
          "paired_len4_state_accuracy": 0.03125,
          "paired_len4_state_all_exact": 0.0,
          "paired_len4_state_prefix_fraction": 0.03125,
          "paired_len4_state_mean_correct_prefix": 0.125,
          "paired_len4_pair_true_answer_consistency": 1.0,
          "paired_len4_pair_true_length_consistency": 1.0,
          "paired_len4_executor_pair_answer_consistency": 0.0,
          "paired_len4_executor_pair_both_correct": 0.0,
          "paired_len4_compiler_pair_program_consistency": 0.0,
          "paired_len4_compiler_pair_state_consistency": 0.0
        }
      ],
      "final_metrics": {
        "standard_len2": {
          "variant": "copy_trace_state_teacher",
          "n": 4.0,
          "direct_accuracy": NaN,
          "direct_target_mass": NaN,
          "executor_accuracy": 0.0,
          "executor_target_mass": 0.09424769505858421,
          "init_accuracy": 0.5,
          "init_pos_accuracy": 0.0,
          "op_accuracy": 1.0,
          "arg_accuracy": 0.625,
          "op_pos_accuracy": 0.25,
          "arg_pos_accuracy": 0.75,
          "program_exact": 0.0,
          "state_accuracy": 0.0,
          "state_all_exact": 0.0,
          "state_prefix_fraction": 0.0,
          "state_mean_correct_prefix": 0.0
        },
        "standard_len4": {
          "variant": "copy_trace_state_teacher",
          "n": 4.0,
          "direct_accuracy": NaN,
          "direct_target_mass": NaN,
          "executor_accuracy": 0.0,
          "executor_target_mass": 0.009107958525419235,
          "init_accuracy": 0.75,
          "init_pos_accuracy": 0.0,
          "op_accuracy": 0.75,
          "arg_accuracy": 0.5,
          "op_pos_accuracy": 0.125,
          "arg_pos_accuracy": 0.1875,
          "program_exact": 0.0,
          "state_accuracy": 0.0625,
          "state_all_exact": 0.0,
          "state_prefix_fraction": 0.0625,
          "state_mean_correct_prefix": 0.25
        },
        "paraphrase_len2": {
          "variant": "copy_trace_state_teacher",
          "n": 4.0,
          "direct_accuracy": NaN,
          "direct_target_mass": NaN,
          "executor_accuracy": 0.25,
          "executor_target_mass": 0.08972702920436859,
          "init_accuracy": 0.75,
          "init_pos_accuracy": 0.25,
          "op_accuracy": 1.0,
          "arg_accuracy": 0.75,
          "op_pos_accuracy": 0.375,
          "arg_pos_accuracy": 0.375,
          "program_exact": 0.25,
          "state_accuracy": 0.25,
          "state_all_exact": 0.25,
          "state_prefix_fraction": 0.25,
          "state_mean_correct_prefix": 0.5
        },
        "paraphrase_len4": {
          "variant": "copy_trace_state_teacher",
          "n": 4.0,
          "direct_accuracy": NaN,
          "direct_target_mass": NaN,
          "executor_accuracy": 0.0,
          "executor_target_mass": 0.011130061000585556,
          "init_accuracy": 1.0,
          "init_pos_accuracy": 0.75,
          "op_accuracy": 0.625,
          "arg_accuracy": 0.4375,
          "op_pos_accuracy": 0.0625,
          "arg_pos_accuracy": 0.1875,
          "program_exact": 0.0,
          "state_accuracy": 0.0625,
          "state_all_exact": 0.0,
          "state_prefix_fraction": 0.0625,
          "state_mean_correct_prefix": 0.25
        },
        "paired_len2": {
          "variant": "copy_trace_state_teacher",
          "n": 8.0,
          "direct_accuracy": NaN,
          "direct_target_mass": NaN,
          "executor_accuracy": 0.25,
          "executor_target_mass": 0.061364601366221905,
          "init_accuracy": 0.75,
          "init_pos_accuracy": 0.125,
          "op_accuracy": 1.0,
          "arg_accuracy": 0.5,
          "op_pos_accuracy": 0.1875,
          "arg_pos_accuracy": 0.3125,
          "program_exact": 0.25,
          "state_accuracy": 0.375,
          "state_all_exact": 0.25,
          "state_prefix_fraction": 0.375,
          "state_mean_correct_prefix": 0.75,
          "pair_true_answer_consistency": 1.0,
          "pair_true_length_consistency": 1.0,
          "executor_pair_answer_consistency": 0.5,
          "executor_pair_both_correct": 0.25,
          "compiler_pair_program_consistency": 0.5,
          "compiler_pair_state_consistency": 0.5
        },
        "paired_len4": {
          "variant": "copy_trace_state_teacher",
          "n": 8.0,
          "direct_accuracy": NaN,
          "direct_target_mass": NaN,
          "executor_accuracy": 0.0,
          "executor_target_mass": 0.031201052479445934,
          "init_accuracy": 0.75,
          "init_pos_accuracy": 0.25,
          "op_accuracy": 0.71875,
          "arg_accuracy": 0.46875,
          "op_pos_accuracy": 0.15625,
          "arg_pos_accuracy": 0.15625,
          "program_exact": 0.0,
          "state_accuracy": 0.03125,
          "state_all_exact": 0.0,
          "state_prefix_fraction": 0.03125,
          "state_mean_correct_prefix": 0.125,
          "pair_true_answer_consistency": 1.0,
          "pair_true_length_consistency": 1.0,
          "executor_pair_answer_consistency": 0.0,
          "executor_pair_both_correct": 0.0,
          "compiler_pair_program_consistency": 0.0,
          "compiler_pair_state_consistency": 0.0
        }
      }
    }
  }
}