{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.22148394241417496,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008859357696566999,
      "grad_norm": 10.282384872436523,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3774,
      "step": 1
    },
    {
      "epoch": 0.008859357696566999,
      "eval_loss": 0.4578593969345093,
      "eval_runtime": 32.6988,
      "eval_samples_per_second": 2.905,
      "eval_steps_per_second": 1.468,
      "step": 1
    },
    {
      "epoch": 0.017718715393133997,
      "grad_norm": 10.4387788772583,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.6036,
      "step": 2
    },
    {
      "epoch": 0.026578073089700997,
      "grad_norm": 10.090304374694824,
      "learning_rate": 0.0001,
      "loss": 1.8095,
      "step": 3
    },
    {
      "epoch": 0.035437430786267994,
      "grad_norm": 9.6649808883667,
      "learning_rate": 9.99524110790929e-05,
      "loss": 1.6976,
      "step": 4
    },
    {
      "epoch": 0.044296788482835,
      "grad_norm": 10.416516304016113,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.4104,
      "step": 5
    },
    {
      "epoch": 0.053156146179401995,
      "grad_norm": 8.030714988708496,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.9224,
      "step": 6
    },
    {
      "epoch": 0.06201550387596899,
      "grad_norm": 9.158958435058594,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.0338,
      "step": 7
    },
    {
      "epoch": 0.07087486157253599,
      "grad_norm": 10.988117218017578,
      "learning_rate": 9.881480035599667e-05,
      "loss": 1.9548,
      "step": 8
    },
    {
      "epoch": 0.07973421926910298,
      "grad_norm": 8.427650451660156,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.1079,
      "step": 9
    },
    {
      "epoch": 0.08859357696567,
      "grad_norm": 8.841338157653809,
      "learning_rate": 9.768584753741134e-05,
      "loss": 1.8842,
      "step": 10
    },
    {
      "epoch": 0.09745293466223699,
      "grad_norm": 8.063060760498047,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.3119,
      "step": 11
    },
    {
      "epoch": 0.10631229235880399,
      "grad_norm": 13.610594749450684,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.4325,
      "step": 12
    },
    {
      "epoch": 0.11517165005537099,
      "grad_norm": 7.284789562225342,
      "learning_rate": 9.53153893518325e-05,
      "loss": 1.4195,
      "step": 13
    },
    {
      "epoch": 0.12403100775193798,
      "grad_norm": 6.768807888031006,
      "learning_rate": 9.435054165891109e-05,
      "loss": 1.0552,
      "step": 14
    },
    {
      "epoch": 0.132890365448505,
      "grad_norm": 7.928319454193115,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.2176,
      "step": 15
    },
    {
      "epoch": 0.14174972314507198,
      "grad_norm": 8.217719078063965,
      "learning_rate": 9.21695722906443e-05,
      "loss": 1.6128,
      "step": 16
    },
    {
      "epoch": 0.150609080841639,
      "grad_norm": 19.084928512573242,
      "learning_rate": 9.09576022144496e-05,
      "loss": 1.9317,
      "step": 17
    },
    {
      "epoch": 0.15946843853820597,
      "grad_norm": 15.333611488342285,
      "learning_rate": 8.966766701456177e-05,
      "loss": 1.9728,
      "step": 18
    },
    {
      "epoch": 0.16832779623477298,
      "grad_norm": 12.080218315124512,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.5498,
      "step": 19
    },
    {
      "epoch": 0.17718715393134,
      "grad_norm": 12.198057174682617,
      "learning_rate": 8.68638668405062e-05,
      "loss": 2.8962,
      "step": 20
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 12.76229476928711,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.3625,
      "step": 21
    },
    {
      "epoch": 0.19490586932447398,
      "grad_norm": 10.231610298156738,
      "learning_rate": 8.377951038078302e-05,
      "loss": 1.7069,
      "step": 22
    },
    {
      "epoch": 0.20376522702104097,
      "grad_norm": 9.231905937194824,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.7236,
      "step": 23
    },
    {
      "epoch": 0.21262458471760798,
      "grad_norm": 12.690796852111816,
      "learning_rate": 8.043807145043604e-05,
      "loss": 1.6465,
      "step": 24
    },
    {
      "epoch": 0.22148394241417496,
      "grad_norm": 8.044271469116211,
      "learning_rate": 7.86788218175523e-05,
      "loss": 1.3221,
      "step": 25
    },
    {
      "epoch": 0.22148394241417496,
      "eval_loss": 0.17975519597530365,
      "eval_runtime": 33.0538,
      "eval_samples_per_second": 2.874,
      "eval_steps_per_second": 1.452,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.53626333642752e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}