{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 10,
  "global_step": 154,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 55.47663497924805,
      "learning_rate": 0.00011250000000000001,
      "loss": 8.703079986572266,
      "step": 10
    },
    {
      "epoch": 0.06504065040650407,
      "eval_loss": 1.79399573802948,
      "eval_runtime": 93.2017,
      "eval_samples_per_second": 2.961,
      "eval_steps_per_second": 1.481,
      "step": 10
    },
    {
      "epoch": 0.13008130081300814,
      "grad_norm": 18.564268112182617,
      "learning_rate": 0.0001956521739130435,
      "loss": 6.914659881591797,
      "step": 20
    },
    {
      "epoch": 0.13008130081300814,
      "eval_loss": 1.4378732442855835,
      "eval_runtime": 92.8107,
      "eval_samples_per_second": 2.974,
      "eval_steps_per_second": 1.487,
      "step": 20
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 6.949378490447998,
      "learning_rate": 0.00018115942028985507,
      "loss": 5.270082092285156,
      "step": 30
    },
    {
      "epoch": 0.1951219512195122,
      "eval_loss": 1.3564187288284302,
      "eval_runtime": 92.968,
      "eval_samples_per_second": 2.969,
      "eval_steps_per_second": 1.484,
      "step": 30
    },
    {
      "epoch": 0.2601626016260163,
      "grad_norm": 18.938419342041016,
      "learning_rate": 0.0001666666666666667,
      "loss": 5.4691619873046875,
      "step": 40
    },
    {
      "epoch": 0.2601626016260163,
      "eval_loss": 1.2968977689743042,
      "eval_runtime": 92.9333,
      "eval_samples_per_second": 2.97,
      "eval_steps_per_second": 1.485,
      "step": 40
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 4.205469131469727,
      "learning_rate": 0.00015217391304347827,
      "loss": 4.866386032104492,
      "step": 50
    },
    {
      "epoch": 0.3252032520325203,
      "eval_loss": 1.3045886754989624,
      "eval_runtime": 92.8006,
      "eval_samples_per_second": 2.974,
      "eval_steps_per_second": 1.487,
      "step": 50
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 6.2034478187561035,
      "learning_rate": 0.00013768115942028986,
      "loss": 5.203897476196289,
      "step": 60
    },
    {
      "epoch": 0.3902439024390244,
      "eval_loss": 1.2741440534591675,
      "eval_runtime": 92.7552,
      "eval_samples_per_second": 2.976,
      "eval_steps_per_second": 1.488,
      "step": 60
    },
    {
      "epoch": 0.45528455284552843,
      "grad_norm": 5.329586029052734,
      "learning_rate": 0.00012318840579710145,
      "loss": 5.226799392700196,
      "step": 70
    },
    {
      "epoch": 0.45528455284552843,
      "eval_loss": 1.2608736753463745,
      "eval_runtime": 92.7677,
      "eval_samples_per_second": 2.975,
      "eval_steps_per_second": 1.488,
      "step": 70
    },
    {
      "epoch": 0.5203252032520326,
      "grad_norm": 6.022779941558838,
      "learning_rate": 0.00010869565217391305,
      "loss": 4.7585094451904295,
      "step": 80
    },
    {
      "epoch": 0.5203252032520326,
      "eval_loss": 1.2409065961837769,
      "eval_runtime": 92.9603,
      "eval_samples_per_second": 2.969,
      "eval_steps_per_second": 1.485,
      "step": 80
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 6.975116729736328,
      "learning_rate": 9.420289855072463e-05,
      "loss": 5.141559982299805,
      "step": 90
    },
    {
      "epoch": 0.5853658536585366,
      "eval_loss": 1.2473307847976685,
      "eval_runtime": 93.0257,
      "eval_samples_per_second": 2.967,
      "eval_steps_per_second": 1.483,
      "step": 90
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 5.658397197723389,
      "learning_rate": 7.971014492753623e-05,
      "loss": 4.915719604492187,
      "step": 100
    },
    {
      "epoch": 0.6504065040650406,
      "eval_loss": 1.2207982540130615,
      "eval_runtime": 92.9926,
      "eval_samples_per_second": 2.968,
      "eval_steps_per_second": 1.484,
      "step": 100
    },
    {
      "epoch": 0.7154471544715447,
      "grad_norm": 4.068330764770508,
      "learning_rate": 6.521739130434783e-05,
      "loss": 4.71471939086914,
      "step": 110
    },
    {
      "epoch": 0.7154471544715447,
      "eval_loss": 1.2062972784042358,
      "eval_runtime": 93.0862,
      "eval_samples_per_second": 2.965,
      "eval_steps_per_second": 1.482,
      "step": 110
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 4.539018154144287,
      "learning_rate": 5.072463768115943e-05,
      "loss": 5.122110748291016,
      "step": 120
    },
    {
      "epoch": 0.7804878048780488,
      "eval_loss": 1.1862434148788452,
      "eval_runtime": 92.8886,
      "eval_samples_per_second": 2.971,
      "eval_steps_per_second": 1.486,
      "step": 120
    },
    {
      "epoch": 0.8455284552845529,
      "grad_norm": 2.0783629417419434,
      "learning_rate": 3.6231884057971014e-05,
      "loss": 5.124646377563477,
      "step": 130
    },
    {
      "epoch": 0.8455284552845529,
      "eval_loss": 1.1823657751083374,
      "eval_runtime": 93.3157,
      "eval_samples_per_second": 2.958,
      "eval_steps_per_second": 1.479,
      "step": 130
    },
    {
      "epoch": 0.9105691056910569,
      "grad_norm": 2.456535816192627,
      "learning_rate": 2.173913043478261e-05,
      "loss": 4.650765609741211,
      "step": 140
    },
    {
      "epoch": 0.9105691056910569,
      "eval_loss": 1.1808730363845825,
      "eval_runtime": 93.0255,
      "eval_samples_per_second": 2.967,
      "eval_steps_per_second": 1.483,
      "step": 140
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 3.2700843811035156,
      "learning_rate": 7.246376811594203e-06,
      "loss": 4.547821807861328,
      "step": 150
    },
    {
      "epoch": 0.975609756097561,
      "eval_loss": 1.1744519472122192,
      "eval_runtime": 92.9911,
      "eval_samples_per_second": 2.968,
      "eval_steps_per_second": 1.484,
      "step": 150
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.1732834577560425,
      "eval_runtime": 93.2831,
      "eval_samples_per_second": 2.959,
      "eval_steps_per_second": 1.479,
      "step": 154
    }
  ],
  "logging_steps": 10,
  "max_steps": 154,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.38753752607488e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}