{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0010664960273022983,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.265984109209193e-05,
      "grad_norm": 0.9969995617866516,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 3.9588,
      "step": 1
    },
    {
      "epoch": 4.265984109209193e-05,
      "eval_loss": 0.8528421521186829,
      "eval_runtime": 6712.1472,
      "eval_samples_per_second": 2.941,
      "eval_steps_per_second": 1.47,
      "step": 1
    },
    {
      "epoch": 8.531968218418386e-05,
      "grad_norm": 1.190828561782837,
      "learning_rate": 6.666666666666667e-05,
      "loss": 5.243,
      "step": 2
    },
    {
      "epoch": 0.0001279795232762758,
      "grad_norm": 1.4397765398025513,
      "learning_rate": 0.0001,
      "loss": 5.3963,
      "step": 3
    },
    {
      "epoch": 0.00017063936436836772,
      "grad_norm": 1.6313406229019165,
      "learning_rate": 9.99524110790929e-05,
      "loss": 5.5734,
      "step": 4
    },
    {
      "epoch": 0.00021329920546045967,
      "grad_norm": 2.044528007507324,
      "learning_rate": 9.980973490458728e-05,
      "loss": 5.304,
      "step": 5
    },
    {
      "epoch": 0.0002559590465525516,
      "grad_norm": 2.162430763244629,
      "learning_rate": 9.957224306869053e-05,
      "loss": 4.6854,
      "step": 6
    },
    {
      "epoch": 0.0002986188876446435,
      "grad_norm": 2.0912225246429443,
      "learning_rate": 9.924038765061042e-05,
      "loss": 4.6928,
      "step": 7
    },
    {
      "epoch": 0.00034127872873673543,
      "grad_norm": 2.985011100769043,
      "learning_rate": 9.881480035599667e-05,
      "loss": 4.4166,
      "step": 8
    },
    {
      "epoch": 0.00038393856982882736,
      "grad_norm": 2.7205920219421387,
      "learning_rate": 9.829629131445342e-05,
      "loss": 3.8685,
      "step": 9
    },
    {
      "epoch": 0.00042659841092091935,
      "grad_norm": 4.159798622131348,
      "learning_rate": 9.768584753741134e-05,
      "loss": 4.0564,
      "step": 10
    },
    {
      "epoch": 0.0004692582520130113,
      "grad_norm": 4.382631778717041,
      "learning_rate": 9.698463103929542e-05,
      "loss": 3.5491,
      "step": 11
    },
    {
      "epoch": 0.0005119180931051031,
      "grad_norm": 3.656183958053589,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.3898,
      "step": 12
    },
    {
      "epoch": 0.0005545779341971951,
      "grad_norm": 3.396904230117798,
      "learning_rate": 9.53153893518325e-05,
      "loss": 3.3838,
      "step": 13
    },
    {
      "epoch": 0.000597237775289287,
      "grad_norm": 2.346179485321045,
      "learning_rate": 9.435054165891109e-05,
      "loss": 3.0043,
      "step": 14
    },
    {
      "epoch": 0.0006398976163813789,
      "grad_norm": 2.402644395828247,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.357,
      "step": 15
    },
    {
      "epoch": 0.0006825574574734709,
      "grad_norm": 2.4477994441986084,
      "learning_rate": 9.21695722906443e-05,
      "loss": 3.5046,
      "step": 16
    },
    {
      "epoch": 0.0007252172985655628,
      "grad_norm": 2.0487022399902344,
      "learning_rate": 9.09576022144496e-05,
      "loss": 3.5617,
      "step": 17
    },
    {
      "epoch": 0.0007678771396576547,
      "grad_norm": 2.190971612930298,
      "learning_rate": 8.966766701456177e-05,
      "loss": 3.5747,
      "step": 18
    },
    {
      "epoch": 0.0008105369807497467,
      "grad_norm": 2.8272922039031982,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.9758,
      "step": 19
    },
    {
      "epoch": 0.0008531968218418387,
      "grad_norm": 2.4170966148376465,
      "learning_rate": 8.68638668405062e-05,
      "loss": 3.2795,
      "step": 20
    },
    {
      "epoch": 0.0008958566629339306,
      "grad_norm": 2.1180191040039062,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.2033,
      "step": 21
    },
    {
      "epoch": 0.0009385165040260225,
      "grad_norm": 2.2295899391174316,
      "learning_rate": 8.377951038078302e-05,
      "loss": 3.5037,
      "step": 22
    },
    {
      "epoch": 0.0009811763451181145,
      "grad_norm": 2.3293685913085938,
      "learning_rate": 8.213938048432697e-05,
      "loss": 2.943,
      "step": 23
    },
    {
      "epoch": 0.0010238361862102063,
      "grad_norm": 2.344874858856201,
      "learning_rate": 8.043807145043604e-05,
      "loss": 3.3558,
      "step": 24
    },
    {
      "epoch": 0.0010664960273022983,
      "grad_norm": 2.393409252166748,
      "learning_rate": 7.86788218175523e-05,
      "loss": 3.4156,
      "step": 25
    },
    {
      "epoch": 0.0010664960273022983,
      "eval_loss": 0.40573301911354065,
      "eval_runtime": 6738.675,
      "eval_samples_per_second": 2.929,
      "eval_steps_per_second": 1.465,
      "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": 3.303407560635187e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}