{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07328691828508611,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029314767314034445,
      "grad_norm": 4.896785259246826,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.4996,
      "step": 1
    },
    {
      "epoch": 0.0029314767314034445,
      "eval_loss": 1.0614820718765259,
      "eval_runtime": 20.3602,
      "eval_samples_per_second": 14.145,
      "eval_steps_per_second": 7.073,
      "step": 1
    },
    {
      "epoch": 0.005862953462806889,
      "grad_norm": 2.8189775943756104,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.1143,
      "step": 2
    },
    {
      "epoch": 0.008794430194210334,
      "grad_norm": 2.35616135597229,
      "learning_rate": 0.0001,
      "loss": 0.8383,
      "step": 3
    },
    {
      "epoch": 0.011725906925613778,
      "grad_norm": 1.8003149032592773,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.6748,
      "step": 4
    },
    {
      "epoch": 0.014657383657017223,
      "grad_norm": 2.207160472869873,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.7224,
      "step": 5
    },
    {
      "epoch": 0.01758886038842067,
      "grad_norm": 2.059014320373535,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.7348,
      "step": 6
    },
    {
      "epoch": 0.020520337119824112,
      "grad_norm": 1.301095962524414,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.4525,
      "step": 7
    },
    {
      "epoch": 0.023451813851227556,
      "grad_norm": 1.3723230361938477,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.4029,
      "step": 8
    },
    {
      "epoch": 0.026383290582631,
      "grad_norm": 1.4173338413238525,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.3076,
      "step": 9
    },
    {
      "epoch": 0.029314767314034446,
      "grad_norm": 1.3965848684310913,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.2697,
      "step": 10
    },
    {
      "epoch": 0.03224624404543789,
      "grad_norm": 1.271812081336975,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2067,
      "step": 11
    },
    {
      "epoch": 0.03517772077684134,
      "grad_norm": 1.1979728937149048,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2204,
      "step": 12
    },
    {
      "epoch": 0.03810919750824478,
      "grad_norm": 1.1956003904342651,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.1251,
      "step": 13
    },
    {
      "epoch": 0.041040674239648224,
      "grad_norm": 0.7809640765190125,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.0761,
      "step": 14
    },
    {
      "epoch": 0.043972150971051664,
      "grad_norm": 0.9528048634529114,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1389,
      "step": 15
    },
    {
      "epoch": 0.04690362770245511,
      "grad_norm": 0.7418190240859985,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.0984,
      "step": 16
    },
    {
      "epoch": 0.04983510443385856,
      "grad_norm": 0.8109403252601624,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.1611,
      "step": 17
    },
    {
      "epoch": 0.052766581165262,
      "grad_norm": 0.6052976846694946,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0726,
      "step": 18
    },
    {
      "epoch": 0.055698057896665445,
      "grad_norm": 0.6859976053237915,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0853,
      "step": 19
    },
    {
      "epoch": 0.05862953462806889,
      "grad_norm": 0.8153113126754761,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.133,
      "step": 20
    },
    {
      "epoch": 0.06156101135947233,
      "grad_norm": 0.6893975734710693,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0523,
      "step": 21
    },
    {
      "epoch": 0.06449248809087578,
      "grad_norm": 0.7115774750709534,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.0751,
      "step": 22
    },
    {
      "epoch": 0.06742396482227922,
      "grad_norm": 0.7574334740638733,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0751,
      "step": 23
    },
    {
      "epoch": 0.07035544155368267,
      "grad_norm": 0.7631270289421082,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.091,
      "step": 24
    },
    {
      "epoch": 0.07328691828508611,
      "grad_norm": 0.4982626438140869,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.0477,
      "step": 25
    },
    {
      "epoch": 0.07328691828508611,
      "eval_loss": 0.08081666380167007,
      "eval_runtime": 20.8896,
      "eval_samples_per_second": 13.787,
      "eval_steps_per_second": 6.893,
      "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": 5365118024024064.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}