{
  "best_metric": 1.2262005805969238,
  "best_model_checkpoint": "data/Llama-31-8B_task-1_180-samples_config-2/checkpoint-51",
  "epoch": 12.941176470588236,
  "eval_steps": 500,
  "global_step": 110,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 1.594277024269104,
      "learning_rate": 2.5e-06,
      "loss": 2.0252,
      "step": 1
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.6746692657470703,
      "learning_rate": 5e-06,
      "loss": 2.0106,
      "step": 2
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 1.6521005630493164,
      "learning_rate": 1e-05,
      "loss": 2.0401,
      "step": 4
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 1.7186492681503296,
      "learning_rate": 1.5e-05,
      "loss": 2.0802,
      "step": 6
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 1.8471022844314575,
      "learning_rate": 2e-05,
      "loss": 2.0099,
      "step": 8
    },
    {
      "epoch": 0.9411764705882353,
      "eval_loss": 1.9310517311096191,
      "eval_runtime": 14.538,
      "eval_samples_per_second": 2.476,
      "eval_steps_per_second": 2.476,
      "step": 8
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1.4888906478881836,
      "learning_rate": 2.5e-05,
      "loss": 1.9018,
      "step": 10
    },
    {
      "epoch": 1.4117647058823528,
      "grad_norm": 1.471009612083435,
      "learning_rate": 3e-05,
      "loss": 1.8183,
      "step": 12
    },
    {
      "epoch": 1.6470588235294117,
      "grad_norm": 0.9562329053878784,
      "learning_rate": 3.5e-05,
      "loss": 1.6866,
      "step": 14
    },
    {
      "epoch": 1.8823529411764706,
      "grad_norm": 0.6349982023239136,
      "learning_rate": 4e-05,
      "loss": 1.5434,
      "step": 16
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.5801305770874023,
      "eval_runtime": 14.5041,
      "eval_samples_per_second": 2.482,
      "eval_steps_per_second": 2.482,
      "step": 17
    },
    {
      "epoch": 2.1176470588235294,
      "grad_norm": 0.8308390378952026,
      "learning_rate": 4.5e-05,
      "loss": 1.4958,
      "step": 18
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 0.6930317282676697,
      "learning_rate": 5e-05,
      "loss": 1.5195,
      "step": 20
    },
    {
      "epoch": 2.588235294117647,
      "grad_norm": 0.5881927609443665,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.5246,
      "step": 22
    },
    {
      "epoch": 2.8235294117647056,
      "grad_norm": 0.5433686971664429,
      "learning_rate": 6e-05,
      "loss": 1.4423,
      "step": 24
    },
    {
      "epoch": 2.9411764705882355,
      "eval_loss": 1.4169615507125854,
      "eval_runtime": 14.4948,
      "eval_samples_per_second": 2.484,
      "eval_steps_per_second": 2.484,
      "step": 25
    },
    {
      "epoch": 3.0588235294117645,
      "grad_norm": 0.5738654136657715,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.3585,
      "step": 26
    },
    {
      "epoch": 3.2941176470588234,
      "grad_norm": 0.47962501645088196,
      "learning_rate": 7e-05,
      "loss": 1.3292,
      "step": 28
    },
    {
      "epoch": 3.5294117647058822,
      "grad_norm": 0.557539701461792,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.3115,
      "step": 30
    },
    {
      "epoch": 3.764705882352941,
      "grad_norm": 0.5750067830085754,
      "learning_rate": 8e-05,
      "loss": 1.2283,
      "step": 32
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.5792177319526672,
      "learning_rate": 8.5e-05,
      "loss": 1.2232,
      "step": 34
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.2907806634902954,
      "eval_runtime": 14.4908,
      "eval_samples_per_second": 2.484,
      "eval_steps_per_second": 2.484,
      "step": 34
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 0.583920955657959,
      "learning_rate": 9e-05,
      "loss": 1.1841,
      "step": 36
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 0.5953171849250793,
      "learning_rate": 9.5e-05,
      "loss": 1.1332,
      "step": 38
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 0.6098026633262634,
      "learning_rate": 0.0001,
      "loss": 1.1051,
      "step": 40
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 0.6841650605201721,
      "learning_rate": 9.999238475781957e-05,
      "loss": 1.0943,
      "step": 42
    },
    {
      "epoch": 4.9411764705882355,
      "eval_loss": 1.2430223226547241,
      "eval_runtime": 14.4963,
      "eval_samples_per_second": 2.483,
      "eval_steps_per_second": 2.483,
      "step": 42
    },
    {
      "epoch": 5.176470588235294,
      "grad_norm": 0.653698205947876,
      "learning_rate": 9.99695413509548e-05,
      "loss": 1.0148,
      "step": 44
    },
    {
      "epoch": 5.411764705882353,
      "grad_norm": 0.6952411532402039,
      "learning_rate": 9.99314767377287e-05,
      "loss": 1.0029,
      "step": 46
    },
    {
      "epoch": 5.647058823529412,
      "grad_norm": 0.8762359023094177,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.9173,
      "step": 48
    },
    {
      "epoch": 5.882352941176471,
      "grad_norm": 0.8874304890632629,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.9751,
      "step": 50
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.2262005805969238,
      "eval_runtime": 14.5023,
      "eval_samples_per_second": 2.482,
      "eval_steps_per_second": 2.482,
      "step": 51
    },
    {
      "epoch": 6.117647058823529,
      "grad_norm": 0.8299031853675842,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.8749,
      "step": 52
    },
    {
      "epoch": 6.352941176470588,
      "grad_norm": 0.8120145201683044,
      "learning_rate": 9.962730758206611e-05,
      "loss": 0.7804,
      "step": 54
    },
    {
      "epoch": 6.588235294117647,
      "grad_norm": 1.1619277000427246,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.7835,
      "step": 56
    },
    {
      "epoch": 6.823529411764706,
      "grad_norm": 1.2740905284881592,
      "learning_rate": 9.938441702975689e-05,
      "loss": 0.739,
      "step": 58
    },
    {
      "epoch": 6.9411764705882355,
      "eval_loss": 1.31611168384552,
      "eval_runtime": 14.4968,
      "eval_samples_per_second": 2.483,
      "eval_steps_per_second": 2.483,
      "step": 59
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 1.0338878631591797,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.7389,
      "step": 60
    },
    {
      "epoch": 7.294117647058823,
      "grad_norm": 1.0425236225128174,
      "learning_rate": 9.908135917238321e-05,
      "loss": 0.6262,
      "step": 62
    },
    {
      "epoch": 7.529411764705882,
      "grad_norm": 1.2470753192901611,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.5317,
      "step": 64
    },
    {
      "epoch": 7.764705882352941,
      "grad_norm": 1.6282217502593994,
      "learning_rate": 9.871850323926177e-05,
      "loss": 0.47,
      "step": 66
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.5288211107254028,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.4877,
      "step": 68
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.527818202972412,
      "eval_runtime": 14.5091,
      "eval_samples_per_second": 2.481,
      "eval_steps_per_second": 2.481,
      "step": 68
    },
    {
      "epoch": 8.235294117647058,
      "grad_norm": 1.4172755479812622,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.338,
      "step": 70
    },
    {
      "epoch": 8.470588235294118,
      "grad_norm": 1.6513177156448364,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.3503,
      "step": 72
    },
    {
      "epoch": 8.705882352941176,
      "grad_norm": 2.9190142154693604,
      "learning_rate": 9.781523779815179e-05,
      "loss": 0.278,
      "step": 74
    },
    {
      "epoch": 8.941176470588236,
      "grad_norm": 2.2860896587371826,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.2813,
      "step": 76
    },
    {
      "epoch": 8.941176470588236,
      "eval_loss": 1.8160711526870728,
      "eval_runtime": 14.4996,
      "eval_samples_per_second": 2.483,
      "eval_steps_per_second": 2.483,
      "step": 76
    },
    {
      "epoch": 9.176470588235293,
      "grad_norm": 1.3478325605392456,
      "learning_rate": 9.727592877996585e-05,
      "loss": 0.1755,
      "step": 78
    },
    {
      "epoch": 9.411764705882353,
      "grad_norm": 1.748975396156311,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.1449,
      "step": 80
    },
    {
      "epoch": 9.647058823529411,
      "grad_norm": 2.5144476890563965,
      "learning_rate": 9.667902132486009e-05,
      "loss": 0.1405,
      "step": 82
    },
    {
      "epoch": 9.882352941176471,
      "grad_norm": 2.384411096572876,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.1579,
      "step": 84
    },
    {
      "epoch": 10.0,
      "eval_loss": 2.2197160720825195,
      "eval_runtime": 14.4999,
      "eval_samples_per_second": 2.483,
      "eval_steps_per_second": 2.483,
      "step": 85
    },
    {
      "epoch": 10.117647058823529,
      "grad_norm": 1.4405394792556763,
      "learning_rate": 9.602524267262203e-05,
      "loss": 0.129,
      "step": 86
    },
    {
      "epoch": 10.352941176470589,
      "grad_norm": 1.8295742273330688,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0734,
      "step": 88
    },
    {
      "epoch": 10.588235294117647,
      "grad_norm": 1.2115999460220337,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.087,
      "step": 90
    },
    {
      "epoch": 10.823529411764707,
      "grad_norm": 2.196491003036499,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.0849,
      "step": 92
    },
    {
      "epoch": 10.941176470588236,
      "eval_loss": 2.5829787254333496,
      "eval_runtime": 14.5058,
      "eval_samples_per_second": 2.482,
      "eval_steps_per_second": 2.482,
      "step": 93
    },
    {
      "epoch": 11.058823529411764,
      "grad_norm": 1.5755882263183594,
      "learning_rate": 9.45503262094184e-05,
      "loss": 0.0685,
      "step": 94
    },
    {
      "epoch": 11.294117647058824,
      "grad_norm": 1.3116846084594727,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0423,
      "step": 96
    },
    {
      "epoch": 11.529411764705882,
      "grad_norm": 1.1361216306686401,
      "learning_rate": 9.373098535696979e-05,
      "loss": 0.0358,
      "step": 98
    },
    {
      "epoch": 11.764705882352942,
      "grad_norm": 1.342253565788269,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0406,
      "step": 100
    },
    {
      "epoch": 12.0,
      "grad_norm": 1.5391757488250732,
      "learning_rate": 9.285836503510562e-05,
      "loss": 0.0474,
      "step": 102
    },
    {
      "epoch": 12.0,
      "eval_loss": 2.6015219688415527,
      "eval_runtime": 14.5281,
      "eval_samples_per_second": 2.478,
      "eval_steps_per_second": 2.478,
      "step": 102
    },
    {
      "epoch": 12.235294117647058,
      "grad_norm": 1.122894287109375,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0254,
      "step": 104
    },
    {
      "epoch": 12.470588235294118,
      "grad_norm": 1.0225309133529663,
      "learning_rate": 9.193352839727121e-05,
      "loss": 0.0274,
      "step": 106
    },
    {
      "epoch": 12.705882352941176,
      "grad_norm": 1.7044038772583008,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.0388,
      "step": 108
    },
    {
      "epoch": 12.941176470588236,
      "grad_norm": 1.8882803916931152,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.0374,
      "step": 110
    },
    {
      "epoch": 12.941176470588236,
      "eval_loss": 2.7205264568328857,
      "eval_runtime": 14.5458,
      "eval_samples_per_second": 2.475,
      "eval_steps_per_second": 2.475,
      "step": 110
    },
    {
      "epoch": 12.941176470588236,
      "step": 110,
      "total_flos": 2.814245083283456e+16,
      "train_loss": 0.8109949659894813,
      "train_runtime": 2087.7074,
      "train_samples_per_second": 3.257,
      "train_steps_per_second": 0.192
    }
  ],
  "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": 2.814245083283456e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}