{
  "vocab": [
    "red",
    "green",
    "stop",
    "go"
  ],
  "inputs": [
    "red",
    "green",
    "red"
  ],
  "targets": [
    "stop",
    "go",
    "stop"
  ],
  "input_ids": [
    0,
    1,
    0
  ],
  "target_ids": [
    2,
    3,
    2
  ],
  "seed": 7,
  "learning_rate": 0.5,
  "shapes": {
    "input_ids": [
      3
    ],
    "embedding": [
      4,
      2
    ],
    "x": [
      3,
      2
    ],
    "weights": [
      2,
      4
    ],
    "logits": [
      3,
      4
    ],
    "bias": [
      4
    ]
  },
  "parameter_count": 20,
  "params_before": {
    "embedding": [
      [
        -0.18,
        -0.35
      ],
      [
        0.15,
        -0.43
      ],
      [
        0.04,
        -0.13
      ],
      [
        -0.44,
        0.01
      ]
    ],
    "weights": [
      [
        -0.46,
        -0.07,
        -0.43,
        -0.41
      ],
      [
        -0.08,
        0.33,
        -0.38,
        -0.28
      ]
    ],
    "bias": [
      0.0,
      0.0,
      0.0,
      0.0
    ]
  },
  "x": [
    [
      -0.18,
      -0.35
    ],
    [
      0.15,
      -0.43
    ],
    [
      -0.18,
      -0.35
    ]
  ],
  "logits": [
    [
      0.1108,
      -0.1029,
      0.2104,
      0.1718
    ],
    [
      -0.0346,
      -0.1524,
      0.0989,
      0.0589
    ],
    [
      0.1108,
      -0.1029,
      0.2104,
      0.1718
    ]
  ],
  "probs": [
    [
      0.251559,
      0.203156,
      0.277904,
      0.267381
    ],
    [
      0.242148,
      0.215239,
      0.276732,
      0.265881
    ],
    [
      0.251559,
      0.203156,
      0.277904,
      0.267381
    ]
  ],
  "losses": [
    1.28048,
    1.324706,
    1.28048
  ],
  "loss_before": 1.295222,
  "grads": {
    "embedding": [
      [
        0.047291,
        0.164298
      ],
      [
        0.018513,
        0.050684
      ],
      [
        0.0,
        0.0
      ],
      [
        0.0,
        0.0
      ]
    ],
    "weights": [
      [
        -0.01808,
        -0.013617,
        0.100488,
        -0.068792
      ],
      [
        -0.093405,
        -0.078254,
        0.128824,
        0.042835
      ]
    ],
    "bias": [
      0.248422,
      0.207184,
      -0.389153,
      -0.066452
    ]
  },
  "gradient_check": {
    "epsilon": 1e-05,
    "max_error_power_of_ten": -11,
    "max_error_overwrite_bug": 0.082149,
    "loss_after_overwrite_bug": 1.142513
  },
  "params_after": {
    "embedding": [
      [
        -0.203646,
        -0.432149
      ],
      [
        0.140743,
        -0.455342
      ],
      [
        0.04,
        -0.13
      ],
      [
        -0.44,
        0.01
      ]
    ],
    "weights": [
      [
        -0.45096,
        -0.063192,
        -0.480244,
        -0.375604
      ],
      [
        -0.033298,
        0.369127,
        -0.444412,
        -0.301417
      ]
    ],
    "bias": [
      -0.124211,
      -0.103592,
      0.194577,
      0.033226
    ]
  },
  "loss_after": 1.134459,
  "learning_rate_sweep": [
    {
      "learning_rate": 0.1,
      "loss_after": 1.261467
    },
    {
      "learning_rate": 0.5,
      "loss_after": 1.134459
    },
    {
      "learning_rate": 1,
      "loss_after": 0.99613
    },
    {
      "learning_rate": 2,
      "loss_after": 0.797525
    },
    {
      "learning_rate": 5,
      "loss_after": 0.751234
    },
    {
      "learning_rate": 10,
      "loss_after": 1.401903
    },
    {
      "learning_rate": 20,
      "loss_after": 3.277132
    }
  ],
  "large_learning_rate": {
    "learning_rate": 20,
    "loss_after": 3.277132
  }
}