{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.1533632286995517,
  "eval_steps": 500,
  "global_step": 2736,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.9999999844947046e-05,
      "loss": 1.7024,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.999961237011484e-05,
      "loss": 1.1507,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.9998449510510744e-05,
      "loss": 1.0928,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.999651151133954e-05,
      "loss": 1.0793,
      "step": 150
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.999379852284651e-05,
      "loss": 1.0867,
      "step": 200
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.999031075535873e-05,
      "loss": 1.0857,
      "step": 250
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9986048479268788e-05,
      "loss": 1.0721,
      "step": 300
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.99810120250138e-05,
      "loss": 1.0923,
      "step": 350
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9975201783049804e-05,
      "loss": 1.0836,
      "step": 400
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9968618203821487e-05,
      "loss": 1.0769,
      "step": 450
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9961261797727256e-05,
      "loss": 1.0574,
      "step": 500
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9953133135079686e-05,
      "loss": 1.042,
      "step": 550
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9944232846061284e-05,
      "loss": 1.0554,
      "step": 600
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.993456162067566e-05,
      "loss": 1.0735,
      "step": 650
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.992412020869401e-05,
      "loss": 1.0785,
      "step": 700
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9912909419596993e-05,
      "loss": 1.0654,
      "step": 750
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9900930122511993e-05,
      "loss": 1.0606,
      "step": 800
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.988818324614572e-05,
      "loss": 1.0664,
      "step": 850
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.9874669778712215e-05,
      "loss": 1.0604,
      "step": 900
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9860390767856244e-05,
      "loss": 1.0674,
      "step": 950
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.984534732057208e-05,
      "loss": 1.042,
      "step": 1000
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9829540603117667e-05,
      "loss": 1.0452,
      "step": 1050
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9812971840924222e-05,
      "loss": 1.0577,
      "step": 1100
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.979564231850122e-05,
      "loss": 1.0471,
      "step": 1150
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.977755337933682e-05,
      "loss": 1.0704,
      "step": 1200
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.9758706425793702e-05,
      "loss": 1.0282,
      "step": 1250
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.973910291900036e-05,
      "loss": 1.0515,
      "step": 1300
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.97187443787378e-05,
      "loss": 1.0548,
      "step": 1350
    },
    {
      "epoch": 0.15,
      "eval_loss": 1.0247304439544678,
      "eval_runtime": 4.5889,
      "eval_samples_per_second": 108.959,
      "eval_steps_per_second": 13.729,
      "step": 1368
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.9697632383321755e-05,
      "loss": 0.9636,
      "step": 1400
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.96757685694803e-05,
      "loss": 0.9026,
      "step": 1450
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.965315463222695e-05,
      "loss": 0.8808,
      "step": 1500
    },
    {
      "epoch": 1.02,
      "learning_rate": 1.9629792324729302e-05,
      "loss": 0.8712,
      "step": 1550
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.960568345817306e-05,
      "loss": 0.8967,
      "step": 1600
    },
    {
      "epoch": 1.03,
      "learning_rate": 1.9580829901621666e-05,
      "loss": 0.8676,
      "step": 1650
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.9555233581871366e-05,
      "loss": 0.8723,
      "step": 1700
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.9528896483301866e-05,
      "loss": 0.9122,
      "step": 1750
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.9501820647722458e-05,
      "loss": 0.8687,
      "step": 1800
    },
    {
      "epoch": 1.05,
      "learning_rate": 1.947400817421375e-05,
      "loss": 0.8726,
      "step": 1850
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.944546121896493e-05,
      "loss": 0.8505,
      "step": 1900
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.9416181995106585e-05,
      "loss": 0.8458,
      "step": 1950
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.9386172772539162e-05,
      "loss": 0.8721,
      "step": 2000
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.9355435877756957e-05,
      "loss": 0.8676,
      "step": 2050
    },
    {
      "epoch": 1.08,
      "learning_rate": 1.9323973693667762e-05,
      "loss": 0.8826,
      "step": 2100
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.929178865940815e-05,
      "loss": 0.8607,
      "step": 2150
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.925888327015434e-05,
      "loss": 0.8561,
      "step": 2200
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.9225260076928783e-05,
      "loss": 0.8687,
      "step": 2250
    },
    {
      "epoch": 1.1,
      "learning_rate": 1.919092168640239e-05,
      "loss": 0.874,
      "step": 2300
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.915587076069243e-05,
      "loss": 0.8563,
      "step": 2350
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.9120110017156172e-05,
      "loss": 0.8445,
      "step": 2400
    },
    {
      "epoch": 1.12,
      "learning_rate": 1.908364222818019e-05,
      "loss": 0.8646,
      "step": 2450
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.9046470220965457e-05,
      "loss": 0.8479,
      "step": 2500
    },
    {
      "epoch": 1.13,
      "learning_rate": 1.9008596877308157e-05,
      "loss": 0.8788,
      "step": 2550
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.8970025133376252e-05,
      "loss": 0.9,
      "step": 2600
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.893075797948188e-05,
      "loss": 0.8791,
      "step": 2650
    },
    {
      "epoch": 1.15,
      "learning_rate": 1.889079845984951e-05,
      "loss": 0.9254,
      "step": 2700
    },
    {
      "epoch": 1.15,
      "eval_loss": 1.0676991939544678,
      "eval_runtime": 4.5191,
      "eval_samples_per_second": 110.641,
      "eval_steps_per_second": 13.941,
      "step": 2736
    },
    {
      "epoch": 1.15,
      "step": 2736,
      "total_flos": 572810393026560.0,
      "train_loss": 0.9719247023264567,
      "train_runtime": 13352.0365,
      "train_samples_per_second": 42.755,
      "train_steps_per_second": 1.336
    }
  ],
  "logging_steps": 50,
  "max_steps": 17840,
  "num_train_epochs": 2,
  "save_steps": 500,
  "total_flos": 572810393026560.0,
  "trial_name": null,
  "trial_params": null
}