{
  "best_metric": 0.46780306100845337,
  "best_model_checkpoint": "data/Mistral-7B_task-2_180-samples_config-2_auto/checkpoint-34",
  "epoch": 10.941176470588236,
  "eval_steps": 500,
  "global_step": 93,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 1.510934591293335,
      "learning_rate": 2.5e-06,
      "loss": 0.7965,
      "step": 1
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.7937220335006714,
      "learning_rate": 5e-06,
      "loss": 0.8296,
      "step": 2
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 1.4419255256652832,
      "learning_rate": 1e-05,
      "loss": 0.7768,
      "step": 4
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 1.228515863418579,
      "learning_rate": 1.5e-05,
      "loss": 0.751,
      "step": 6
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.0313868522644043,
      "learning_rate": 2e-05,
      "loss": 0.7094,
      "step": 8
    },
    {
      "epoch": 0.9411764705882353,
      "eval_loss": 0.6847631931304932,
      "eval_runtime": 46.8051,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 8
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 0.8758216500282288,
      "learning_rate": 2.5e-05,
      "loss": 0.6623,
      "step": 10
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 0.6320995092391968,
      "learning_rate": 3e-05,
      "loss": 0.6117,
      "step": 12
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.625347912311554,
      "learning_rate": 3.5e-05,
      "loss": 0.5908,
      "step": 14
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.5652298927307129,
      "learning_rate": 4e-05,
      "loss": 0.5612,
      "step": 16
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5559717416763306,
      "eval_runtime": 46.8085,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 17
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.6258118748664856,
      "learning_rate": 4.5e-05,
      "loss": 0.5606,
      "step": 18
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.5558798909187317,
      "learning_rate": 5e-05,
      "loss": 0.5038,
      "step": 20
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.5413522720336914,
      "learning_rate": 5.500000000000001e-05,
      "loss": 0.503,
      "step": 22
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.5496213436126709,
      "learning_rate": 6e-05,
      "loss": 0.5167,
      "step": 24
    },
    {
      "epoch": 2.9411764705882355,
      "eval_loss": 0.4976150691509247,
      "eval_runtime": 46.8047,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 25
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 0.5182849168777466,
      "learning_rate": 6.500000000000001e-05,
      "loss": 0.4673,
      "step": 26
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 0.5479615926742554,
      "learning_rate": 7e-05,
      "loss": 0.4569,
      "step": 28
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.5190202593803406,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.4485,
      "step": 30
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 0.5344440937042236,
      "learning_rate": 8e-05,
      "loss": 0.4393,
      "step": 32
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.49562329053878784,
      "learning_rate": 8.5e-05,
      "loss": 0.4072,
      "step": 34
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.46780306100845337,
      "eval_runtime": 46.8038,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 34
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 0.5034579038619995,
      "learning_rate": 9e-05,
      "loss": 0.3904,
      "step": 36
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 0.518248438835144,
      "learning_rate": 9.5e-05,
      "loss": 0.3798,
      "step": 38
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 0.5025274753570557,
      "learning_rate": 0.0001,
      "loss": 0.3683,
      "step": 40
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 0.5955880880355835,
      "learning_rate": 9.999238475781957e-05,
      "loss": 0.3543,
      "step": 42
    },
    {
      "epoch": 4.9411764705882355,
      "eval_loss": 0.46941232681274414,
      "eval_runtime": 46.8103,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 42
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 0.6378198862075806,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.293,
      "step": 44
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 0.548276960849762,
      "learning_rate": 9.99314767377287e-05,
      "loss": 0.2943,
      "step": 46
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 0.6588279008865356,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.2621,
      "step": 48
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 0.693845272064209,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.2826,
      "step": 50
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.49849483370780945,
      "eval_runtime": 46.8153,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 51
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 0.6328510046005249,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.2362,
      "step": 52
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 0.7498703002929688,
      "learning_rate": 9.962730758206611e-05,
      "loss": 0.193,
      "step": 54
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 0.977211594581604,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.1763,
      "step": 56
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 0.9810727834701538,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.1782,
      "step": 58
    },
    {
      "epoch": 6.9411764705882355,
      "eval_loss": 0.55035001039505,
      "eval_runtime": 46.8095,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 59
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 0.8451752662658691,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.1565,
      "step": 60
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 0.7587767243385315,
      "learning_rate": 9.908135917238321e-05,
      "loss": 0.1152,
      "step": 62
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 1.0390617847442627,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.1004,
      "step": 64
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 0.9154000282287598,
      "learning_rate": 9.871850323926177e-05,
      "loss": 0.0862,
      "step": 66
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.7960644364356995,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.0966,
      "step": 68
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.6488373279571533,
      "eval_runtime": 46.8071,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 68
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 0.5699837803840637,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.0557,
      "step": 70
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 0.6975524425506592,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0577,
      "step": 72
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 0.8164039254188538,
      "learning_rate": 9.781523779815179e-05,
      "loss": 0.0552,
      "step": 74
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 1.1949888467788696,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0553,
      "step": 76
    },
    {
      "epoch": 8.941176470588236,
      "eval_loss": 0.7934577465057373,
      "eval_runtime": 46.8043,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 76
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 0.7413657307624817,
      "learning_rate": 9.727592877996585e-05,
      "loss": 0.0395,
      "step": 78
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 0.9031487107276917,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0334,
      "step": 80
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 0.6765309572219849,
      "learning_rate": 9.667902132486009e-05,
      "loss": 0.0307,
      "step": 82
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 0.7007652521133423,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.0336,
      "step": 84
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.7939873933792114,
      "eval_runtime": 46.8167,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 85
    },
    {
      "epoch": 10.117647058823529,
      "grad_norm": 0.4486708343029022,
      "learning_rate": 9.602524267262203e-05,
      "loss": 0.0248,
      "step": 86
    },
    {
      "epoch": 10.352941176470589,
      "grad_norm": 0.5931721329689026,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0205,
      "step": 88
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 0.6534993052482605,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.0214,
      "step": 90
    },
    {
      "epoch": 10.823529411764707,
      "grad_norm": 0.648955225944519,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0233,
      "step": 92
    },
    {
      "epoch": 10.941176470588236,
      "eval_loss": 0.8752700090408325,
      "eval_runtime": 46.8096,
      "eval_samples_per_second": 0.769,
      "eval_steps_per_second": 0.769,
      "step": 93
    },
    {
      "epoch": 10.941176470588236,
      "step": 93,
      "total_flos": 1.8300686077578445e+17,
      "train_loss": 0.3055747908049373,
      "train_runtime": 6614.5513,
      "train_samples_per_second": 1.028,
      "train_steps_per_second": 0.06
    }
  ],
  "logging_steps": 2,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 7,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.8300686077578445e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}