{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.5280855941918228,
  "eval_steps": 500,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07642338555598013,
      "grad_norm": 0.04852772876620293,
      "learning_rate": 0.00019991780772074993,
      "loss": 0.631,
      "step": 100
    },
    {
      "epoch": 0.15284677111196027,
      "grad_norm": 0.06019178777933121,
      "learning_rate": 0.00019926107993313918,
      "loss": 0.4967,
      "step": 200
    },
    {
      "epoch": 0.2292701566679404,
      "grad_norm": 0.06423385441303253,
      "learning_rate": 0.00019795194081958614,
      "loss": 0.4377,
      "step": 300
    },
    {
      "epoch": 0.30569354222392053,
      "grad_norm": 0.05076967179775238,
      "learning_rate": 0.00019599899493270587,
      "loss": 0.4121,
      "step": 400
    },
    {
      "epoch": 0.38211692777990064,
      "grad_norm": 0.06871291249990463,
      "learning_rate": 0.00019341507836108832,
      "loss": 0.3974,
      "step": 500
    },
    {
      "epoch": 0.4585403133358808,
      "grad_norm": 0.062317609786987305,
      "learning_rate": 0.00019021717436179406,
      "loss": 0.3826,
      "step": 600
    },
    {
      "epoch": 0.5349636988918609,
      "grad_norm": 0.054332610219717026,
      "learning_rate": 0.00018642630173483835,
      "loss": 0.3695,
      "step": 700
    },
    {
      "epoch": 0.6113870844478411,
      "grad_norm": 0.07528349757194519,
      "learning_rate": 0.00018206737667334231,
      "loss": 0.3589,
      "step": 800
    },
    {
      "epoch": 0.6878104700038211,
      "grad_norm": 0.07792173326015472,
      "learning_rate": 0.00017716904899736617,
      "loss": 0.3527,
      "step": 900
    },
    {
      "epoch": 0.7642338555598013,
      "grad_norm": 0.08550075441598892,
      "learning_rate": 0.00017176351384780628,
      "loss": 0.3407,
      "step": 1000
    },
    {
      "epoch": 0.8406572411157814,
      "grad_norm": 0.09895286709070206,
      "learning_rate": 0.00016588630007803324,
      "loss": 0.3292,
      "step": 1100
    },
    {
      "epoch": 0.9170806266717616,
      "grad_norm": 0.05582467094063759,
      "learning_rate": 0.00015957603673410394,
      "loss": 0.321,
      "step": 1200
    },
    {
      "epoch": 0.9935040122277417,
      "grad_norm": 0.05442088469862938,
      "learning_rate": 0.00015287419915839849,
      "loss": 0.3202,
      "step": 1300
    },
    {
      "epoch": 1.0695452808559418,
      "grad_norm": 0.07129843533039093,
      "learning_rate": 0.00014582483638546267,
      "loss": 0.3075,
      "step": 1400
    },
    {
      "epoch": 1.145968666411922,
      "grad_norm": 0.06552577763795853,
      "learning_rate": 0.00013847428162179422,
      "loss": 0.3008,
      "step": 1500
    },
    {
      "epoch": 1.2223920519679021,
      "grad_norm": 0.07303871214389801,
      "learning_rate": 0.00013087084771249831,
      "loss": 0.2948,
      "step": 1600
    },
    {
      "epoch": 1.2988154375238823,
      "grad_norm": 0.12717650830745697,
      "learning_rate": 0.00012306450959641117,
      "loss": 0.2948,
      "step": 1700
    },
    {
      "epoch": 1.3752388230798624,
      "grad_norm": 0.05392363294959068,
      "learning_rate": 0.00011510657583681364,
      "loss": 0.2887,
      "step": 1800
    },
    {
      "epoch": 1.4516622086358426,
      "grad_norm": 0.07771366834640503,
      "learning_rate": 0.00010704935138665758,
      "loss": 0.286,
      "step": 1900
    },
    {
      "epoch": 1.5280855941918228,
      "grad_norm": 0.056173793971538544,
      "learning_rate": 9.894579380484204e-05,
      "loss": 0.2874,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 3924,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.400738054418727e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}