{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.011479738261967628,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004591895304787051,
      "grad_norm": 1.1419830322265625,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.0269,
      "step": 1
    },
    {
      "epoch": 0.0004591895304787051,
      "eval_loss": 1.300444483757019,
      "eval_runtime": 461.8779,
      "eval_samples_per_second": 3.971,
      "eval_steps_per_second": 1.985,
      "step": 1
    },
    {
      "epoch": 0.0009183790609574102,
      "grad_norm": 1.1880234479904175,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.036,
      "step": 2
    },
    {
      "epoch": 0.0013775685914361152,
      "grad_norm": 1.1058253049850464,
      "learning_rate": 0.0001,
      "loss": 1.0533,
      "step": 3
    },
    {
      "epoch": 0.0018367581219148204,
      "grad_norm": 0.8739814758300781,
      "learning_rate": 9.99524110790929e-05,
      "loss": 1.0222,
      "step": 4
    },
    {
      "epoch": 0.0022959476523935255,
      "grad_norm": 1.1297332048416138,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.0771,
      "step": 5
    },
    {
      "epoch": 0.0027551371828722303,
      "grad_norm": 1.0218960046768188,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.9766,
      "step": 6
    },
    {
      "epoch": 0.0032143267133509356,
      "grad_norm": 0.9368105530738831,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.9208,
      "step": 7
    },
    {
      "epoch": 0.003673516243829641,
      "grad_norm": 0.7900261878967285,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.9225,
      "step": 8
    },
    {
      "epoch": 0.004132705774308346,
      "grad_norm": 0.7937513589859009,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.8457,
      "step": 9
    },
    {
      "epoch": 0.004591895304787051,
      "grad_norm": 0.7547521591186523,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.834,
      "step": 10
    },
    {
      "epoch": 0.005051084835265756,
      "grad_norm": 0.7325078845024109,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.8298,
      "step": 11
    },
    {
      "epoch": 0.005510274365744461,
      "grad_norm": 0.6860811114311218,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.8015,
      "step": 12
    },
    {
      "epoch": 0.005969463896223166,
      "grad_norm": 0.6838340759277344,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.7436,
      "step": 13
    },
    {
      "epoch": 0.006428653426701871,
      "grad_norm": 0.7004528045654297,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.7086,
      "step": 14
    },
    {
      "epoch": 0.006887842957180576,
      "grad_norm": 0.6048188209533691,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.7169,
      "step": 15
    },
    {
      "epoch": 0.007347032487659282,
      "grad_norm": 0.5844050049781799,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.707,
      "step": 16
    },
    {
      "epoch": 0.007806222018137987,
      "grad_norm": 0.5827935934066772,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.6838,
      "step": 17
    },
    {
      "epoch": 0.008265411548616692,
      "grad_norm": 0.6372345089912415,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.6679,
      "step": 18
    },
    {
      "epoch": 0.008724601079095397,
      "grad_norm": 0.6254321336746216,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.6719,
      "step": 19
    },
    {
      "epoch": 0.009183790609574102,
      "grad_norm": 0.6155533790588379,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.7132,
      "step": 20
    },
    {
      "epoch": 0.009642980140052807,
      "grad_norm": 0.5951682329177856,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6667,
      "step": 21
    },
    {
      "epoch": 0.010102169670531512,
      "grad_norm": 0.5539524555206299,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.6211,
      "step": 22
    },
    {
      "epoch": 0.010561359201010216,
      "grad_norm": 0.5512757897377014,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.6512,
      "step": 23
    },
    {
      "epoch": 0.011020548731488921,
      "grad_norm": 0.5660426616668701,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.6527,
      "step": 24
    },
    {
      "epoch": 0.011479738261967628,
      "grad_norm": 0.5754444003105164,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.6099,
      "step": 25
    },
    {
      "epoch": 0.011479738261967628,
      "eval_loss": 0.6897526979446411,
      "eval_runtime": 464.8934,
      "eval_samples_per_second": 3.945,
      "eval_steps_per_second": 1.972,
      "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": 3.73005226082304e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}