[
  {
    "loss": 8.703079986572266,
    "grad_norm": 55.47663497924805,
    "learning_rate": 0.00011250000000000001,
    "epoch": 0.06504065040650407,
    "step": 10
  },
  {
    "eval_loss": 1.79399573802948,
    "eval_runtime": 93.2017,
    "eval_samples_per_second": 2.961,
    "eval_steps_per_second": 1.481,
    "epoch": 0.06504065040650407,
    "step": 10
  },
  {
    "loss": 6.914659881591797,
    "grad_norm": 18.564268112182617,
    "learning_rate": 0.0001956521739130435,
    "epoch": 0.13008130081300814,
    "step": 20
  },
  {
    "eval_loss": 1.4378732442855835,
    "eval_runtime": 92.8107,
    "eval_samples_per_second": 2.974,
    "eval_steps_per_second": 1.487,
    "epoch": 0.13008130081300814,
    "step": 20
  },
  {
    "loss": 5.270082092285156,
    "grad_norm": 6.949378490447998,
    "learning_rate": 0.00018115942028985507,
    "epoch": 0.1951219512195122,
    "step": 30
  },
  {
    "eval_loss": 1.3564187288284302,
    "eval_runtime": 92.968,
    "eval_samples_per_second": 2.969,
    "eval_steps_per_second": 1.484,
    "epoch": 0.1951219512195122,
    "step": 30
  },
  {
    "loss": 5.4691619873046875,
    "grad_norm": 18.938419342041016,
    "learning_rate": 0.0001666666666666667,
    "epoch": 0.2601626016260163,
    "step": 40
  },
  {
    "eval_loss": 1.2968977689743042,
    "eval_runtime": 92.9333,
    "eval_samples_per_second": 2.97,
    "eval_steps_per_second": 1.485,
    "epoch": 0.2601626016260163,
    "step": 40
  },
  {
    "loss": 4.866386032104492,
    "grad_norm": 4.205469131469727,
    "learning_rate": 0.00015217391304347827,
    "epoch": 0.3252032520325203,
    "step": 50
  },
  {
    "eval_loss": 1.3045886754989624,
    "eval_runtime": 92.8006,
    "eval_samples_per_second": 2.974,
    "eval_steps_per_second": 1.487,
    "epoch": 0.3252032520325203,
    "step": 50
  },
  {
    "loss": 5.203897476196289,
    "grad_norm": 6.2034478187561035,
    "learning_rate": 0.00013768115942028986,
    "epoch": 0.3902439024390244,
    "step": 60
  },
  {
    "eval_loss": 1.2741440534591675,
    "eval_runtime": 92.7552,
    "eval_samples_per_second": 2.976,
    "eval_steps_per_second": 1.488,
    "epoch": 0.3902439024390244,
    "step": 60
  },
  {
    "loss": 5.226799392700196,
    "grad_norm": 5.329586029052734,
    "learning_rate": 0.00012318840579710145,
    "epoch": 0.45528455284552843,
    "step": 70
  },
  {
    "eval_loss": 1.2608736753463745,
    "eval_runtime": 92.7677,
    "eval_samples_per_second": 2.975,
    "eval_steps_per_second": 1.488,
    "epoch": 0.45528455284552843,
    "step": 70
  },
  {
    "loss": 4.7585094451904295,
    "grad_norm": 6.022779941558838,
    "learning_rate": 0.00010869565217391305,
    "epoch": 0.5203252032520326,
    "step": 80
  },
  {
    "eval_loss": 1.2409065961837769,
    "eval_runtime": 92.9603,
    "eval_samples_per_second": 2.969,
    "eval_steps_per_second": 1.485,
    "epoch": 0.5203252032520326,
    "step": 80
  },
  {
    "loss": 5.141559982299805,
    "grad_norm": 6.975116729736328,
    "learning_rate": 9.420289855072463e-05,
    "epoch": 0.5853658536585366,
    "step": 90
  },
  {
    "eval_loss": 1.2473307847976685,
    "eval_runtime": 93.0257,
    "eval_samples_per_second": 2.967,
    "eval_steps_per_second": 1.483,
    "epoch": 0.5853658536585366,
    "step": 90
  },
  {
    "loss": 4.915719604492187,
    "grad_norm": 5.658397197723389,
    "learning_rate": 7.971014492753623e-05,
    "epoch": 0.6504065040650406,
    "step": 100
  },
  {
    "eval_loss": 1.2207982540130615,
    "eval_runtime": 92.9926,
    "eval_samples_per_second": 2.968,
    "eval_steps_per_second": 1.484,
    "epoch": 0.6504065040650406,
    "step": 100
  },
  {
    "loss": 4.71471939086914,
    "grad_norm": 4.068330764770508,
    "learning_rate": 6.521739130434783e-05,
    "epoch": 0.7154471544715447,
    "step": 110
  },
  {
    "eval_loss": 1.2062972784042358,
    "eval_runtime": 93.0862,
    "eval_samples_per_second": 2.965,
    "eval_steps_per_second": 1.482,
    "epoch": 0.7154471544715447,
    "step": 110
  },
  {
    "loss": 5.122110748291016,
    "grad_norm": 4.539018154144287,
    "learning_rate": 5.072463768115943e-05,
    "epoch": 0.7804878048780488,
    "step": 120
  },
  {
    "eval_loss": 1.1862434148788452,
    "eval_runtime": 92.8886,
    "eval_samples_per_second": 2.971,
    "eval_steps_per_second": 1.486,
    "epoch": 0.7804878048780488,
    "step": 120
  },
  {
    "loss": 5.124646377563477,
    "grad_norm": 2.0783629417419434,
    "learning_rate": 3.6231884057971014e-05,
    "epoch": 0.8455284552845529,
    "step": 130
  },
  {
    "eval_loss": 1.1823657751083374,
    "eval_runtime": 93.3157,
    "eval_samples_per_second": 2.958,
    "eval_steps_per_second": 1.479,
    "epoch": 0.8455284552845529,
    "step": 130
  },
  {
    "loss": 4.650765609741211,
    "grad_norm": 2.456535816192627,
    "learning_rate": 2.173913043478261e-05,
    "epoch": 0.9105691056910569,
    "step": 140
  },
  {
    "eval_loss": 1.1808730363845825,
    "eval_runtime": 93.0255,
    "eval_samples_per_second": 2.967,
    "eval_steps_per_second": 1.483,
    "epoch": 0.9105691056910569,
    "step": 140
  },
  {
    "loss": 4.547821807861328,
    "grad_norm": 3.2700843811035156,
    "learning_rate": 7.246376811594203e-06,
    "epoch": 0.975609756097561,
    "step": 150
  },
  {
    "eval_loss": 1.1744519472122192,
    "eval_runtime": 92.9911,
    "eval_samples_per_second": 2.968,
    "eval_steps_per_second": 1.484,
    "epoch": 0.975609756097561,
    "step": 150
  },
  {
    "eval_loss": 1.1732834577560425,
    "eval_runtime": 93.2831,
    "eval_samples_per_second": 2.959,
    "eval_steps_per_second": 1.479,
    "epoch": 1.0,
    "step": 154
  },
  {
    "train_runtime": 3434.9466,
    "train_samples_per_second": 0.358,
    "train_steps_per_second": 0.045,
    "total_flos": 5.38753752607488e+16,
    "train_loss": 5.347667557852609,
    "epoch": 1.0,
    "step": 154
  }
]