{
  "args": {
    "model_id": "hf-internal-testing/tiny-random-GPT2LMHeadModel",
    "load_in_4bit": false,
    "torch_dtype": "fp32",
    "device_map": "auto",
    "use_lora": false,
    "lora_r": 8,
    "lora_alpha": 16,
    "lora_dropout": 0.05,
    "lora_target_modules": "all-linear",
    "gradient_checkpointing": false,
    "optimizer": "adamw",
    "modulus": 97,
    "max_steps": 3,
    "train_min_len": 1,
    "train_max_len": 12,
    "curriculum_stages": "short:1:2:2,long:2:3:2",
    "answer_train_min_len": 1,
    "answer_train_max_len": 24,
    "eval_lengths": "2,3",
    "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": 16,
    "answer_train_size": 16,
    "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": 64,
    "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": 0.5,
    "teacher_rep_loss_weight": 0.1,
    "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_len3_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_tiny_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": false,
    "lora_r": 8,
    "gpu_name": "NVIDIA RTX 6000 Ada Generation",
    "gpu_vram_gb": 47.383
  },
  "hidden_dim": 32,
  "dataset": {
    "train_size": 16,
    "train_examples": 32,
    "curriculum_stages": [
      {
        "name": "short",
        "min_len": 1,
        "max_len": 2,
        "steps": 2
      },
      {
        "name": "long",
        "min_len": 2,
        "max_len": 3,
        "steps": 2
      }
    ],
    "state_loss_weight_by_stage": {
      "short": 0.25,
      "long": 0.25
    },
    "answer_train_size": 16,
    "eval_size": 4,
    "train_lengths": [
      1,
      12
    ],
    "answer_train_lengths": [
      1,
      24
    ],
    "eval_lengths": [
      2,
      3
    ],
    "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": 0.9985122680664062,
      "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_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00001",
          "model_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00001/frozen_backbone.txt",
          "heads_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00001/heads.pt",
          "selection_metric": "paired_len3_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_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00002",
          "model_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00002/frozen_backbone.txt",
          "heads_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00002/heads.pt",
          "selection_metric": "paired_len3_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_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_long_step00003",
          "model_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_long_step00003/frozen_backbone.txt",
          "heads_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_long_step00003/heads.pt",
          "selection_metric": "paired_len3_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_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_long_step00004",
          "model_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_long_step00004/frozen_backbone.txt",
          "heads_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_long_step00004/heads.pt",
          "selection_metric": "paired_len3_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_tiny_teacher/copy_trace_state_teacher/final_step00004",
          "model_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_tiny_teacher/copy_trace_state_teacher/final_step00004/frozen_backbone.txt",
          "heads_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_tiny_teacher/copy_trace_state_teacher/final_step00004/heads.pt",
          "selection_metric": "paired_len3_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_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00001",
        "model_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00001/frozen_backbone.txt",
        "heads_checkpoint": "large_artifacts/qwen_teacher_distilled_slot_compiler/checkpoints/smoke_tiny_teacher/copy_trace_state_teacher/eval_trace_state_teacher_short_step00001/heads.pt",
        "selection_metric": "paired_len3_executor_accuracy",
        "selection_value": 0.0
      },
      "train_log": [
        {
          "variant": "copy_trace_state_teacher",
          "stage": "trace_state_teacher_short",
          "local_step": 1,
          "step": 1,
          "loss": 140.39108276367188,
          "trace_loss_active": true,
          "executor_loss_active": true,
          "state_loss_active": true,
          "state_loss_weight": 0.25,
          "teacher_position_loss_weight": 0.5,
          "teacher_rep_loss_weight": 0.1,
          "lr_scale": 1.0,
          "executor_loss": 12.681648254394531,
          "state_loss": 8.074002265930176,
          "state_train_accuracy": 0.25,
          "init_loss": 1.0088272094726562,
          "op_loss": 2.2981951236724854,
          "arg_loss": 7.046309947967529,
          "init_attn_loss": 4.498265266418457,
          "op_attn_loss": 10.334752082824707,
          "arg_attn_loss": 11.274528503417969,
          "role_loss": 1.0708221197128296,
          "teacher_init_pos_loss": 4.48123836517334,
          "teacher_op_pos_loss": 10.148841857910156,
          "teacher_arg_pos_loss": 11.152288436889648,
          "teacher_init_rep_loss": 0.818649411201477,
          "teacher_op_rep_loss": 0.9718263745307922,
          "teacher_arg_rep_loss": 0.9289243221282959,
          "standard_len2_direct_accuracy": NaN,
          "standard_len2_direct_target_mass": NaN,
          "standard_len2_executor_accuracy": 0.0,
          "standard_len2_executor_target_mass": 0.006589910442926339,
          "standard_len2_init_accuracy": 0.5,
          "standard_len2_init_pos_accuracy": 0.0,
          "standard_len2_op_accuracy": 0.625,
          "standard_len2_arg_accuracy": 0.0,
          "standard_len2_op_pos_accuracy": 0.0,
          "standard_len2_arg_pos_accuracy": 0.0,
          "standard_len2_program_exact": 0.0,
          "standard_len2_state_accuracy": 0.125,
          "standard_len2_state_all_exact": 0.0,
          "standard_len2_state_prefix_fraction": 0.125,
          "standard_len2_state_mean_correct_prefix": 0.25,
          "standard_len3_direct_accuracy": NaN,
          "standard_len3_direct_target_mass": NaN,
          "standard_len3_executor_accuracy": 0.0,
          "standard_len3_executor_target_mass": 0.04526264511514455,
          "standard_len3_init_accuracy": 0.25,
          "standard_len3_init_pos_accuracy": 0.0,
          "standard_len3_op_accuracy": 0.75,
          "standard_len3_arg_accuracy": 0.0,
          "standard_len3_op_pos_accuracy": 0.0,
          "standard_len3_arg_pos_accuracy": 0.0,
          "standard_len3_program_exact": 0.0,
          "standard_len3_state_accuracy": 0.16666666666666666,
          "standard_len3_state_all_exact": 0.0,
          "standard_len3_state_prefix_fraction": 0.16666666666666666,
          "standard_len3_state_mean_correct_prefix": 0.5,
          "paraphrase_len2_direct_accuracy": NaN,
          "paraphrase_len2_direct_target_mass": NaN,
          "paraphrase_len2_executor_accuracy": 0.0,
          "paraphrase_len2_executor_target_mass": 0.0006274834886426106,
          "paraphrase_len2_init_accuracy": 0.5,
          "paraphrase_len2_init_pos_accuracy": 0.0,
          "paraphrase_len2_op_accuracy": 0.625,
          "paraphrase_len2_arg_accuracy": 0.0,
          "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": 0.0,
          "paraphrase_len2_state_prefix_fraction": 0.25,
          "paraphrase_len2_state_mean_correct_prefix": 0.5,
          "paraphrase_len3_direct_accuracy": NaN,
          "paraphrase_len3_direct_target_mass": NaN,
          "paraphrase_len3_executor_accuracy": 0.0,
          "paraphrase_len3_executor_target_mass": 0.00179225520696491,
          "paraphrase_len3_init_accuracy": 0.25,
          "paraphrase_len3_init_pos_accuracy": 0.0,
          "paraphrase_len3_op_accuracy": 0.5,
          "paraphrase_len3_arg_accuracy": 0.0,
          "paraphrase_len3_op_pos_accuracy": 0.0,
          "paraphrase_len3_arg_pos_accuracy": 0.0,
          "paraphrase_len3_program_exact": 0.0,
          "paraphrase_len3_state_accuracy": 0.0,
          "paraphrase_len3_state_all_exact": 0.0,
          "paraphrase_len3_state_prefix_fraction": 0.0,
          "paraphrase_len3_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": 0.12892758126326953,
          "paired_len2_init_accuracy": 0.375,
          "paired_len2_init_pos_accuracy": 0.0,
          "paired_len2_op_accuracy": 0.5,
          "paired_len2_arg_accuracy": 0.0,
          "paired_len2_op_pos_accuracy": 0.0,
          "paired_len2_arg_pos_accuracy": 0.0,
          "paired_len2_program_exact": 0.0,
          "paired_len2_state_accuracy": 0.0625,
          "paired_len2_state_all_exact": 0.0,
          "paired_len2_state_prefix_fraction": 0.0625,
          "paired_len2_state_mean_correct_prefix": 0.125,
          "paired_len2_pair_true_answer_consistency": 1.0,
          "paired_len2_pair_true_length_consistency": 1.0,
          "paired_len2_executor_pair_answer_consistency": 0.75,
          "paired_len2_executor_pair_both_correct": 0.0,
          "paired_len2_compiler_pair_program_consistency": 0.75,
          "paired_len2_compiler_pair_state_consistency": 0.75,
          "paired_len3_direct_accuracy": NaN,
          "paired_len3_direct_target_mass": NaN,
          "paired_len3_executor_accuracy": 0.0,
          "paired_len3_executor_target_mass": 0.0002354143368847872,
          "paired_len3_init_accuracy": 0.625,
          "paired_len3_init_pos_accuracy": 0.0,
          "paired_len3_op_accuracy": 0.5,
          "paired_len3_arg_accuracy": 0.0,
          "paired_len3_op_pos_accuracy": 0.0,
          "paired_len3_arg_pos_accuracy": 0.0,
          "paired_len3_program_exact": 0.0,
          "paired_len3_state_accuracy": 0.0,
          "paired_len3_state_all_exact": 0.0,
          "paired_len3_state_prefix_fraction": 0.0,
          "paired_len3_state_mean_correct_prefix": 0.0,
          "paired_len3_pair_true_answer_consistency": 1.0,
          "paired_len3_pair_true_length_consistency": 1.0,
          "paired_len3_executor_pair_answer_consistency": 0.5,
          "paired_len3_executor_pair_both_correct": 0.0,
          "paired_len3_compiler_pair_program_consistency": 0.5,
          "paired_len3_compiler_pair_state_consistency": 0.5
        },
        {
          "variant": "copy_trace_state_teacher",
          "stage": "trace_state_teacher_short",
          "local_step": 2,
          "step": 2,
          "loss": 141.79306030273438,
          "trace_loss_active": true,
          "executor_loss_active": true,
          "state_loss_active": true,
          "state_loss_weight": 0.25,
          "teacher_position_loss_weight": 0.5,
          "teacher_rep_loss_weight": 0.1,
          "lr_scale": 1.0,
          "executor_loss": 10.43677806854248,
          "state_loss": 5.850147247314453,
          "state_train_accuracy": 0.25,
          "init_loss": 0.8887213468551636,
          "op_loss": 1.375008225440979,
          "arg_loss": 7.870684623718262,
          "init_attn_loss": 4.4855852127075195,
          "op_attn_loss": 10.397517204284668,
          "arg_attn_loss": 11.642929077148438,
          "role_loss": 1.0472444295883179,
          "teacher_init_pos_loss": 4.486107349395752,
          "teacher_op_pos_loss": 10.19534969329834,
          "teacher_arg_pos_loss": 11.554154396057129,
          "teacher_init_rep_loss": 0.7869647741317749,
          "teacher_op_rep_loss": 1.036637783050537,
          "teacher_arg_rep_loss": 0.8691259622573853,
          "standard_len2_direct_accuracy": NaN,
          "standard_len2_direct_target_mass": NaN,
          "standard_len2_executor_accuracy": 0.0,
          "standard_len2_executor_target_mass": 0.00677182287654432,
          "standard_len2_init_accuracy": 0.5,
          "standard_len2_init_pos_accuracy": 0.0,
          "standard_len2_op_accuracy": 0.625,
          "standard_len2_arg_accuracy": 0.0,
          "standard_len2_op_pos_accuracy": 0.0,
          "standard_len2_arg_pos_accuracy": 0.0,
          "standard_len2_program_exact": 0.0,
          "standard_len2_state_accuracy": 0.125,
          "standard_len2_state_all_exact": 0.0,
          "standard_len2_state_prefix_fraction": 0.125,
          "standard_len2_state_mean_correct_prefix": 0.25,
          "standard_len3_direct_accuracy": NaN,
          "standard_len3_direct_target_mass": NaN,
          "standard_len3_executor_accuracy": 0.0,
          "standard_len3_executor_target_mass": 0.044718467397615314,
          "standard_len3_init_accuracy": 0.25,
          "standard_len3_init_pos_accuracy": 0.0,
          "standard_len3_op_accuracy": 0.6666666666666666,
          "standard_len3_arg_accuracy": 0.0,
          "standard_len3_op_pos_accuracy": 0.0,
          "standard_len3_arg_pos_accuracy": 0.0,
          "standard_len3_program_exact": 0.0,
          "standard_len3_state_accuracy": 0.16666666666666666,
          "standard_len3_state_all_exact": 0.0,
          "standard_len3_state_prefix_fraction": 0.16666666666666666,
          "standard_len3_state_mean_correct_prefix": 0.5,
          "paraphrase_len2_direct_accuracy": NaN,
          "paraphrase_len2_direct_target_mass": NaN,
          "paraphrase_len2_executor_accuracy": 0.0,
          "paraphrase_len2_executor_target_mass": 0.0006691679591313004,
          "paraphrase_len2_init_accuracy": 0.5,
          "paraphrase_len2_init_pos_accuracy": 0.0,
          "paraphrase_len2_op_accuracy": 0.625,
          "paraphrase_len2_arg_accuracy": 0.0,
          "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": 0.0,
          "paraphrase_len2_state_prefix_fraction": 0.25,
          "paraphrase_len2_state_mean_correct_prefix": 0.5,
          "paraphrase_len3_direct_accuracy": NaN,
          "paraphrase_len3_direct_target_mass": NaN,
          "paraphrase_len3_executor_accuracy": 0.0,
          "paraphrase_len3_executor_target_mass": 0.0019151861197315156,
          "paraphrase_len3_init_accuracy": 0.25,
          "paraphrase_len3_init_pos_accuracy": 0.0,
          "paraphrase_len3_op_accuracy": 0.5,
          "paraphrase_len3_arg_accuracy": 0.0,
          "paraphrase_len3_op_pos_accuracy": 0.0,
          "paraphrase_len3_arg_pos_accuracy": 0.0,
          "paraphrase_len3_program_exact": 0.0,
          "paraphrase_len3_state_accuracy": 0.0,
          "paraphrase_len3_state_all_exact": 0.0,
          "paraphrase_len3_state_prefix_fraction": 0.0,
          "paraphrase_len3_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": 0.12842862117031473,
          "paired_len2_init_accuracy": 0.375,
          "paired_len2_init_pos_accuracy": 0.0,
          "paired_len2_op_accuracy": 0.5,
          "paired_len2_arg_accuracy": 0.0,
          "paired_len2_op_pos_accuracy": 0.0,
          "paired_len2_arg_pos_accuracy": 0.0,
          "paired_len2_program_exact": 0.0,
          "paired_len2_state_accuracy": 0.0625,
          "paired_len2_state_all_exact": 0.0,
          "paired_len2_state_prefix_fraction": 0.0625,
          "paired_len2_state_mean_correct_prefix": 0.125,
          "paired_len2_pair_true_answer_consistency": 1.0,
          "paired_len2_pair_true_length_consistency": 1.0,
          "paired_len2_executor_pair_answer_consistency": 0.75,
          "paired_len2_executor_pair_both_correct": 0.0,
          "paired_len2_compiler_pair_program_consistency": 0.75,
          "paired_len2_compiler_pair_state_consistency": 0.75,
          "paired_len3_direct_accuracy": NaN,
          "paired_len3_direct_target_mass": NaN,
          "paired_len3_executor_accuracy": 0.0,
          "paired_len3_executor_target_mass": 0.0002520301185313656,
          "paired_len3_init_accuracy": 0.625,
          "paired_len3_init_pos_accuracy": 0.0,
          "paired_len3_op_accuracy": 0.5,
          "paired_len3_arg_accuracy": 0.0,
          "paired_len3_op_pos_accuracy": 0.0,
          "paired_len3_arg_pos_accuracy": 0.0,
          "paired_len3_program_exact": 0.0,
          "paired_len3_state_accuracy": 0.0,
          "paired_len3_state_all_exact": 0.0,
          "paired_len3_state_prefix_fraction": 0.0,
          "paired_len3_state_mean_correct_prefix": 0.0,
          "paired_len3_pair_true_answer_consistency": 1.0,
          "paired_len3_pair_true_length_consistency": 1.0,
          "paired_len3_executor_pair_answer_consistency": 0.25,
          "paired_len3_executor_pair_both_correct": 0.0,
          "paired_len3_compiler_pair_program_consistency": 0.25,
          "paired_len3_compiler_pair_state_consistency": 0.25
        },
        {
          "variant": "copy_trace_state_teacher",
          "stage": "trace_state_teacher_long",
          "local_step": 1,
          "step": 3,
          "loss": 92.55281066894531,
          "trace_loss_active": true,
          "executor_loss_active": true,
          "state_loss_active": true,
          "state_loss_weight": 0.25,
          "teacher_position_loss_weight": 0.5,
          "teacher_rep_loss_weight": 0.1,
          "lr_scale": 1.0,
          "executor_loss": 10.53148078918457,
          "state_loss": 7.588039398193359,
          "state_train_accuracy": 0.0,
          "init_loss": 1.2952179908752441,
          "op_loss": 1.3151212930679321,
          "arg_loss": 3.735546112060547,
          "init_attn_loss": 4.50648832321167,
          "op_attn_loss": 6.310990810394287,
          "arg_attn_loss": 6.793941497802734,
          "role_loss": 1.3964895009994507,
          "teacher_init_pos_loss": 4.497407913208008,
          "teacher_op_pos_loss": 6.184901237487793,
          "teacher_arg_pos_loss": 6.70593786239624,
          "teacher_init_rep_loss": 0.7956656813621521,
          "teacher_op_rep_loss": 0.8505997061729431,
          "teacher_arg_rep_loss": 0.9468919634819031,
          "standard_len2_direct_accuracy": NaN,
          "standard_len2_direct_target_mass": NaN,
          "standard_len2_executor_accuracy": 0.0,
          "standard_len2_executor_target_mass": 0.006952959021873539,
          "standard_len2_init_accuracy": 0.5,
          "standard_len2_init_pos_accuracy": 0.0,
          "standard_len2_op_accuracy": 0.625,
          "standard_len2_arg_accuracy": 0.0,
          "standard_len2_op_pos_accuracy": 0.0,
          "standard_len2_arg_pos_accuracy": 0.0,
          "standard_len2_program_exact": 0.0,
          "standard_len2_state_accuracy": 0.125,
          "standard_len2_state_all_exact": 0.0,
          "standard_len2_state_prefix_fraction": 0.125,
          "standard_len2_state_mean_correct_prefix": 0.25,
          "standard_len3_direct_accuracy": NaN,
          "standard_len3_direct_target_mass": NaN,
          "standard_len3_executor_accuracy": 0.0,
          "standard_len3_executor_target_mass": 0.044187156949192286,
          "standard_len3_init_accuracy": 0.25,
          "standard_len3_init_pos_accuracy": 0.0,
          "standard_len3_op_accuracy": 0.6666666666666666,
          "standard_len3_arg_accuracy": 0.0,
          "standard_len3_op_pos_accuracy": 0.0,
          "standard_len3_arg_pos_accuracy": 0.0,
          "standard_len3_program_exact": 0.0,
          "standard_len3_state_accuracy": 0.16666666666666666,
          "standard_len3_state_all_exact": 0.0,
          "standard_len3_state_prefix_fraction": 0.16666666666666666,
          "standard_len3_state_mean_correct_prefix": 0.5,
          "paraphrase_len2_direct_accuracy": NaN,
          "paraphrase_len2_direct_target_mass": NaN,
          "paraphrase_len2_executor_accuracy": 0.0,
          "paraphrase_len2_executor_target_mass": 0.0007134551015042234,
          "paraphrase_len2_init_accuracy": 0.5,
          "paraphrase_len2_init_pos_accuracy": 0.0,
          "paraphrase_len2_op_accuracy": 0.625,
          "paraphrase_len2_arg_accuracy": 0.0,
          "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": 0.0,
          "paraphrase_len2_state_prefix_fraction": 0.25,
          "paraphrase_len2_state_mean_correct_prefix": 0.5,
          "paraphrase_len3_direct_accuracy": NaN,
          "paraphrase_len3_direct_target_mass": NaN,
          "paraphrase_len3_executor_accuracy": 0.0,
          "paraphrase_len3_executor_target_mass": 0.002043754910118878,
          "paraphrase_len3_init_accuracy": 0.25,
          "paraphrase_len3_init_pos_accuracy": 0.0,
          "paraphrase_len3_op_accuracy": 0.5,
          "paraphrase_len3_arg_accuracy": 0.0,
          "paraphrase_len3_op_pos_accuracy": 0.0,
          "paraphrase_len3_arg_pos_accuracy": 0.0,
          "paraphrase_len3_program_exact": 0.0,
          "paraphrase_len3_state_accuracy": 0.0,
          "paraphrase_len3_state_all_exact": 0.0,
          "paraphrase_len3_state_prefix_fraction": 0.0,
          "paraphrase_len3_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": 0.12794948329974432,
          "paired_len2_init_accuracy": 0.375,
          "paired_len2_init_pos_accuracy": 0.0,
          "paired_len2_op_accuracy": 0.5,
          "paired_len2_arg_accuracy": 0.0,
          "paired_len2_op_pos_accuracy": 0.0,
          "paired_len2_arg_pos_accuracy": 0.0,
          "paired_len2_program_exact": 0.0,
          "paired_len2_state_accuracy": 0.0625,
          "paired_len2_state_all_exact": 0.0,
          "paired_len2_state_prefix_fraction": 0.0625,
          "paired_len2_state_mean_correct_prefix": 0.125,
          "paired_len2_pair_true_answer_consistency": 1.0,
          "paired_len2_pair_true_length_consistency": 1.0,
          "paired_len2_executor_pair_answer_consistency": 0.75,
          "paired_len2_executor_pair_both_correct": 0.0,
          "paired_len2_compiler_pair_program_consistency": 0.75,
          "paired_len2_compiler_pair_state_consistency": 0.75,
          "paired_len3_direct_accuracy": NaN,
          "paired_len3_direct_target_mass": NaN,
          "paired_len3_executor_accuracy": 0.0,
          "paired_len3_executor_target_mass": 0.00026905766412710364,
          "paired_len3_init_accuracy": 0.625,
          "paired_len3_init_pos_accuracy": 0.0,
          "paired_len3_op_accuracy": 0.5,
          "paired_len3_arg_accuracy": 0.0,
          "paired_len3_op_pos_accuracy": 0.0,
          "paired_len3_arg_pos_accuracy": 0.0,
          "paired_len3_program_exact": 0.0,
          "paired_len3_state_accuracy": 0.0,
          "paired_len3_state_all_exact": 0.0,
          "paired_len3_state_prefix_fraction": 0.0,
          "paired_len3_state_mean_correct_prefix": 0.0,
          "paired_len3_pair_true_answer_consistency": 1.0,
          "paired_len3_pair_true_length_consistency": 1.0,
          "paired_len3_executor_pair_answer_consistency": 0.25,
          "paired_len3_executor_pair_both_correct": 0.0,
          "paired_len3_compiler_pair_program_consistency": 0.25,
          "paired_len3_compiler_pair_state_consistency": 0.25
        },
        {
          "variant": "copy_trace_state_teacher",
          "stage": "trace_state_teacher_long",
          "local_step": 2,
          "step": 4,
          "loss": 100.60956573486328,
          "trace_loss_active": true,
          "executor_loss_active": true,
          "state_loss_active": true,
          "state_loss_weight": 0.25,
          "teacher_position_loss_weight": 0.5,
          "teacher_rep_loss_weight": 0.1,
          "lr_scale": 1.0,
          "executor_loss": 10.547599792480469,
          "state_loss": 7.6873908042907715,
          "state_train_accuracy": 0.0,
          "init_loss": 1.3260040283203125,
          "op_loss": 1.6560344696044922,
          "arg_loss": 4.245280742645264,
          "init_attn_loss": 4.577536582946777,
          "op_attn_loss": 6.904041767120361,
          "arg_attn_loss": 7.550498962402344,
          "role_loss": 1.4068547487258911,
          "teacher_init_pos_loss": 4.544821262359619,
          "teacher_op_pos_loss": 6.784664154052734,
          "teacher_arg_pos_loss": 7.445737361907959,
          "teacher_init_rep_loss": 0.7903830409049988,
          "teacher_op_rep_loss": 0.910355269908905,
          "teacher_arg_rep_loss": 0.9555702209472656,
          "standard_len2_direct_accuracy": NaN,
          "standard_len2_direct_target_mass": NaN,
          "standard_len2_executor_accuracy": 0.0,
          "standard_len2_executor_target_mass": 0.0071376354917447316,
          "standard_len2_init_accuracy": 0.5,
          "standard_len2_init_pos_accuracy": 0.0,
          "standard_len2_op_accuracy": 0.625,
          "standard_len2_arg_accuracy": 0.0,
          "standard_len2_op_pos_accuracy": 0.0,
          "standard_len2_arg_pos_accuracy": 0.0,
          "standard_len2_program_exact": 0.0,
          "standard_len2_state_accuracy": 0.125,
          "standard_len2_state_all_exact": 0.0,
          "standard_len2_state_prefix_fraction": 0.125,
          "standard_len2_state_mean_correct_prefix": 0.25,
          "standard_len3_direct_accuracy": NaN,
          "standard_len3_direct_target_mass": NaN,
          "standard_len3_executor_accuracy": 0.0,
          "standard_len3_executor_target_mass": 0.04366611037403345,
          "standard_len3_init_accuracy": 0.25,
          "standard_len3_init_pos_accuracy": 0.0,
          "standard_len3_op_accuracy": 0.6666666666666666,
          "standard_len3_arg_accuracy": 0.0,
          "standard_len3_op_pos_accuracy": 0.0,
          "standard_len3_arg_pos_accuracy": 0.0,
          "standard_len3_program_exact": 0.0,
          "standard_len3_state_accuracy": 0.16666666666666666,
          "standard_len3_state_all_exact": 0.0,
          "standard_len3_state_prefix_fraction": 0.16666666666666666,
          "standard_len3_state_mean_correct_prefix": 0.5,
          "paraphrase_len2_direct_accuracy": NaN,
          "paraphrase_len2_direct_target_mass": NaN,
          "paraphrase_len2_executor_accuracy": 0.0,
          "paraphrase_len2_executor_target_mass": 0.000760126600653166,
          "paraphrase_len2_init_accuracy": 0.5,
          "paraphrase_len2_init_pos_accuracy": 0.0,
          "paraphrase_len2_op_accuracy": 0.625,
          "paraphrase_len2_arg_accuracy": 0.0,
          "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": 0.0,
          "paraphrase_len2_state_prefix_fraction": 0.25,
          "paraphrase_len2_state_mean_correct_prefix": 0.5,
          "paraphrase_len3_direct_accuracy": NaN,
          "paraphrase_len3_direct_target_mass": NaN,
          "paraphrase_len3_executor_accuracy": 0.0,
          "paraphrase_len3_executor_target_mass": 0.0021790011669509113,
          "paraphrase_len3_init_accuracy": 0.25,
          "paraphrase_len3_init_pos_accuracy": 0.0,
          "paraphrase_len3_op_accuracy": 0.5,
          "paraphrase_len3_arg_accuracy": 0.0,
          "paraphrase_len3_op_pos_accuracy": 0.0,
          "paraphrase_len3_arg_pos_accuracy": 0.0,
          "paraphrase_len3_program_exact": 0.0,
          "paraphrase_len3_state_accuracy": 0.0,
          "paraphrase_len3_state_all_exact": 0.0,
          "paraphrase_len3_state_prefix_fraction": 0.0,
          "paraphrase_len3_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": 0.1274495626494172,
          "paired_len2_init_accuracy": 0.375,
          "paired_len2_init_pos_accuracy": 0.0,
          "paired_len2_op_accuracy": 0.5,
          "paired_len2_arg_accuracy": 0.0,
          "paired_len2_op_pos_accuracy": 0.0,
          "paired_len2_arg_pos_accuracy": 0.0,
          "paired_len2_program_exact": 0.0,
          "paired_len2_state_accuracy": 0.0625,
          "paired_len2_state_all_exact": 0.0,
          "paired_len2_state_prefix_fraction": 0.0625,
          "paired_len2_state_mean_correct_prefix": 0.125,
          "paired_len2_pair_true_answer_consistency": 1.0,
          "paired_len2_pair_true_length_consistency": 1.0,
          "paired_len2_executor_pair_answer_consistency": 0.75,
          "paired_len2_executor_pair_both_correct": 0.0,
          "paired_len2_compiler_pair_program_consistency": 0.75,
          "paired_len2_compiler_pair_state_consistency": 0.75,
          "paired_len3_direct_accuracy": NaN,
          "paired_len3_direct_target_mass": NaN,
          "paired_len3_executor_accuracy": 0.0,
          "paired_len3_executor_target_mass": 0.0002868220741447658,
          "paired_len3_init_accuracy": 0.625,
          "paired_len3_init_pos_accuracy": 0.0,
          "paired_len3_op_accuracy": 0.5,
          "paired_len3_arg_accuracy": 0.0,
          "paired_len3_op_pos_accuracy": 0.0,
          "paired_len3_arg_pos_accuracy": 0.0,
          "paired_len3_program_exact": 0.0,
          "paired_len3_state_accuracy": 0.0,
          "paired_len3_state_all_exact": 0.0,
          "paired_len3_state_prefix_fraction": 0.0,
          "paired_len3_state_mean_correct_prefix": 0.0,
          "paired_len3_pair_true_answer_consistency": 1.0,
          "paired_len3_pair_true_length_consistency": 1.0,
          "paired_len3_executor_pair_answer_consistency": 0.25,
          "paired_len3_executor_pair_both_correct": 0.0,
          "paired_len3_compiler_pair_program_consistency": 0.25,
          "paired_len3_compiler_pair_state_consistency": 0.25
        }
      ],
      "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": 0.0071376354917447316,
          "init_accuracy": 0.5,
          "init_pos_accuracy": 0.0,
          "op_accuracy": 0.625,
          "arg_accuracy": 0.0,
          "op_pos_accuracy": 0.0,
          "arg_pos_accuracy": 0.0,
          "program_exact": 0.0,
          "state_accuracy": 0.125,
          "state_all_exact": 0.0,
          "state_prefix_fraction": 0.125,
          "state_mean_correct_prefix": 0.25
        },
        "standard_len3": {
          "variant": "copy_trace_state_teacher",
          "n": 4.0,
          "direct_accuracy": NaN,
          "direct_target_mass": NaN,
          "executor_accuracy": 0.0,
          "executor_target_mass": 0.04366611037403345,
          "init_accuracy": 0.25,
          "init_pos_accuracy": 0.0,
          "op_accuracy": 0.6666666666666666,
          "arg_accuracy": 0.0,
          "op_pos_accuracy": 0.0,
          "arg_pos_accuracy": 0.0,
          "program_exact": 0.0,
          "state_accuracy": 0.16666666666666666,
          "state_all_exact": 0.0,
          "state_prefix_fraction": 0.16666666666666666,
          "state_mean_correct_prefix": 0.5
        },
        "paraphrase_len2": {
          "variant": "copy_trace_state_teacher",
          "n": 4.0,
          "direct_accuracy": NaN,
          "direct_target_mass": NaN,
          "executor_accuracy": 0.0,
          "executor_target_mass": 0.000760126600653166,
          "init_accuracy": 0.5,
          "init_pos_accuracy": 0.0,
          "op_accuracy": 0.625,
          "arg_accuracy": 0.0,
          "op_pos_accuracy": 0.0,
          "arg_pos_accuracy": 0.0,
          "program_exact": 0.0,
          "state_accuracy": 0.25,
          "state_all_exact": 0.0,
          "state_prefix_fraction": 0.25,
          "state_mean_correct_prefix": 0.5
        },
        "paraphrase_len3": {
          "variant": "copy_trace_state_teacher",
          "n": 4.0,
          "direct_accuracy": NaN,
          "direct_target_mass": NaN,
          "executor_accuracy": 0.0,
          "executor_target_mass": 0.0021790011669509113,
          "init_accuracy": 0.25,
          "init_pos_accuracy": 0.0,
          "op_accuracy": 0.5,
          "arg_accuracy": 0.0,
          "op_pos_accuracy": 0.0,
          "arg_pos_accuracy": 0.0,
          "program_exact": 0.0,
          "state_accuracy": 0.0,
          "state_all_exact": 0.0,
          "state_prefix_fraction": 0.0,
          "state_mean_correct_prefix": 0.0
        },
        "paired_len2": {
          "variant": "copy_trace_state_teacher",
          "n": 8.0,
          "direct_accuracy": NaN,
          "direct_target_mass": NaN,
          "executor_accuracy": 0.0,
          "executor_target_mass": 0.1274495626494172,
          "init_accuracy": 0.375,
          "init_pos_accuracy": 0.0,
          "op_accuracy": 0.5,
          "arg_accuracy": 0.0,
          "op_pos_accuracy": 0.0,
          "arg_pos_accuracy": 0.0,
          "program_exact": 0.0,
          "state_accuracy": 0.0625,
          "state_all_exact": 0.0,
          "state_prefix_fraction": 0.0625,
          "state_mean_correct_prefix": 0.125,
          "pair_true_answer_consistency": 1.0,
          "pair_true_length_consistency": 1.0,
          "executor_pair_answer_consistency": 0.75,
          "executor_pair_both_correct": 0.0,
          "compiler_pair_program_consistency": 0.75,
          "compiler_pair_state_consistency": 0.75
        },
        "paired_len3": {
          "variant": "copy_trace_state_teacher",
          "n": 8.0,
          "direct_accuracy": NaN,
          "direct_target_mass": NaN,
          "executor_accuracy": 0.0,
          "executor_target_mass": 0.0002868220741447658,
          "init_accuracy": 0.625,
          "init_pos_accuracy": 0.0,
          "op_accuracy": 0.5,
          "arg_accuracy": 0.0,
          "op_pos_accuracy": 0.0,
          "arg_pos_accuracy": 0.0,
          "program_exact": 0.0,
          "state_accuracy": 0.0,
          "state_all_exact": 0.0,
          "state_prefix_fraction": 0.0,
          "state_mean_correct_prefix": 0.0,
          "pair_true_answer_consistency": 1.0,
          "pair_true_length_consistency": 1.0,
          "executor_pair_answer_consistency": 0.25,
          "executor_pair_both_correct": 0.0,
          "compiler_pair_program_consistency": 0.25,
          "compiler_pair_state_consistency": 0.25
        }
      }
    }
  }
}