{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 12260,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4078303425774878,
      "grad_norm": 14.478927612304688,
      "learning_rate": 0.00019993920556849446,
      "loss": 0.8999,
      "step": 500
    },
    {
      "epoch": 0.8156606851549756,
      "grad_norm": 2.973954200744629,
      "learning_rate": 0.00019860945509081267,
      "loss": 0.376,
      "step": 1000
    },
    {
      "epoch": 1.2234910277324633,
      "grad_norm": 0.7534143924713135,
      "learning_rate": 0.0001955617290630555,
      "loss": 0.2706,
      "step": 1500
    },
    {
      "epoch": 1.631321370309951,
      "grad_norm": 0.533855140209198,
      "learning_rate": 0.00019084912501825553,
      "loss": 0.2597,
      "step": 2000
    },
    {
      "epoch": 2.039151712887439,
      "grad_norm": 1.9753663539886475,
      "learning_rate": 0.0001845537460216685,
      "loss": 0.2481,
      "step": 2500
    },
    {
      "epoch": 2.4469820554649266,
      "grad_norm": 2.5512447357177734,
      "learning_rate": 0.00017678527026981862,
      "loss": 0.1971,
      "step": 3000
    },
    {
      "epoch": 2.8548123980424145,
      "grad_norm": 1.973365068435669,
      "learning_rate": 0.000167679040275153,
      "loss": 0.1924,
      "step": 3500
    },
    {
      "epoch": 3.262642740619902,
      "grad_norm": 1.4714034795761108,
      "learning_rate": 0.0001573937049265616,
      "loss": 0.1546,
      "step": 4000
    },
    {
      "epoch": 3.6704730831973897,
      "grad_norm": 0.18751826882362366,
      "learning_rate": 0.00014610845550582294,
      "loss": 0.156,
      "step": 4500
    },
    {
      "epoch": 4.078303425774878,
      "grad_norm": 3.124044895172119,
      "learning_rate": 0.00013401990381414286,
      "loss": 0.1549,
      "step": 5000
    },
    {
      "epoch": 4.486133768352365,
      "grad_norm": 0.6213807463645935,
      "learning_rate": 0.00012133865679811696,
      "loss": 0.1253,
      "step": 5500
    },
    {
      "epoch": 4.893964110929853,
      "grad_norm": 1.664085030555725,
      "learning_rate": 0.00010828564735203954,
      "loss": 0.1266,
      "step": 6000
    },
    {
      "epoch": 5.301794453507341,
      "grad_norm": 0.2742406725883484,
      "learning_rate": 9.508828522138191e-05,
      "loss": 0.1109,
      "step": 6500
    },
    {
      "epoch": 5.709624796084829,
      "grad_norm": 0.24402563273906708,
      "learning_rate": 8.19764950664627e-05,
      "loss": 0.1081,
      "step": 7000
    },
    {
      "epoch": 6.117455138662317,
      "grad_norm": 2.361426830291748,
      "learning_rate": 6.91787107112304e-05,
      "loss": 0.0916,
      "step": 7500
    },
    {
      "epoch": 6.525285481239804,
      "grad_norm": 1.8119088411331177,
      "learning_rate": 5.69178953654216e-05,
      "loss": 0.0881,
      "step": 8000
    },
    {
      "epoch": 6.933115823817292,
      "grad_norm": 1.1984834671020508,
      "learning_rate": 4.540765715585027e-05,
      "loss": 0.0828,
      "step": 8500
    },
    {
      "epoch": 7.3409461663947795,
      "grad_norm": 0.19523586332798004,
      "learning_rate": 3.484852764210548e-05,
      "loss": 0.074,
      "step": 9000
    },
    {
      "epoch": 7.748776508972267,
      "grad_norm": 0.11153391003608704,
      "learning_rate": 2.542446815241867e-05,
      "loss": 0.0721,
      "step": 9500
    },
    {
      "epoch": 8.156606851549755,
      "grad_norm": 0.17387154698371887,
      "learning_rate": 1.729966480637476e-05,
      "loss": 0.0749,
      "step": 10000
    },
    {
      "epoch": 8.564437194127244,
      "grad_norm": 0.8619000315666199,
      "learning_rate": 1.0615668061633398e-05,
      "loss": 0.0632,
      "step": 10500
    },
    {
      "epoch": 8.97226753670473,
      "grad_norm": 0.3366154432296753,
      "learning_rate": 5.488926619525248e-06,
      "loss": 0.0658,
      "step": 11000
    },
    {
      "epoch": 9.380097879282218,
      "grad_norm": 0.2561167776584625,
      "learning_rate": 2.008758653860221e-06,
      "loss": 0.0608,
      "step": 11500
    },
    {
      "epoch": 9.787928221859707,
      "grad_norm": 0.24642044305801392,
      "learning_rate": 2.3579570823278885e-07,
      "loss": 0.0594,
      "step": 12000
    }
  ],
  "logging_steps": 500,
  "max_steps": 12260,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.03414156147584e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}