{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 145,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03466204506065858,
      "grad_norm": 1.530611515045166,
      "learning_rate": 0.0002,
      "loss": 3.0151,
      "step": 5
    },
    {
      "epoch": 0.06932409012131716,
      "grad_norm": 1.7004058361053467,
      "learning_rate": 0.0002,
      "loss": 2.0235,
      "step": 10
    },
    {
      "epoch": 0.10398613518197573,
      "grad_norm": 1.933908462524414,
      "learning_rate": 0.0002,
      "loss": 1.1225,
      "step": 15
    },
    {
      "epoch": 0.1386481802426343,
      "grad_norm": 0.9951248168945312,
      "learning_rate": 0.0002,
      "loss": 0.5422,
      "step": 20
    },
    {
      "epoch": 0.1733102253032929,
      "grad_norm": 6.152623176574707,
      "learning_rate": 0.0002,
      "loss": 1.5639,
      "step": 25
    },
    {
      "epoch": 0.20797227036395147,
      "grad_norm": 8.008278846740723,
      "learning_rate": 0.0002,
      "loss": 2.6486,
      "step": 30
    },
    {
      "epoch": 0.24263431542461006,
      "grad_norm": 4.960943222045898,
      "learning_rate": 0.0002,
      "loss": 2.6059,
      "step": 35
    },
    {
      "epoch": 0.2772963604852686,
      "grad_norm": 4.607645511627197,
      "learning_rate": 0.0002,
      "loss": 1.6898,
      "step": 40
    },
    {
      "epoch": 0.3119584055459272,
      "grad_norm": 0.8448249101638794,
      "learning_rate": 0.0002,
      "loss": 0.799,
      "step": 45
    },
    {
      "epoch": 0.3466204506065858,
      "grad_norm": 0.46238261461257935,
      "learning_rate": 0.0002,
      "loss": 0.5374,
      "step": 50
    },
    {
      "epoch": 0.38128249566724437,
      "grad_norm": 0.3575257956981659,
      "learning_rate": 0.0002,
      "loss": 0.4247,
      "step": 55
    },
    {
      "epoch": 0.41594454072790293,
      "grad_norm": 2.5151493549346924,
      "learning_rate": 0.0002,
      "loss": 0.7472,
      "step": 60
    },
    {
      "epoch": 0.4506065857885615,
      "grad_norm": 17.38052749633789,
      "learning_rate": 0.0002,
      "loss": 1.8466,
      "step": 65
    },
    {
      "epoch": 0.4852686308492201,
      "grad_norm": 15.523968696594238,
      "learning_rate": 0.0002,
      "loss": 2.1105,
      "step": 70
    },
    {
      "epoch": 0.5199306759098787,
      "grad_norm": 1.0907574892044067,
      "learning_rate": 0.0002,
      "loss": 1.1052,
      "step": 75
    },
    {
      "epoch": 0.5545927209705372,
      "grad_norm": 0.5225581526756287,
      "learning_rate": 0.0002,
      "loss": 0.5663,
      "step": 80
    },
    {
      "epoch": 0.5892547660311959,
      "grad_norm": 0.3306778073310852,
      "learning_rate": 0.0002,
      "loss": 0.4648,
      "step": 85
    },
    {
      "epoch": 0.6239168110918544,
      "grad_norm": 0.33595138788223267,
      "learning_rate": 0.0002,
      "loss": 0.3762,
      "step": 90
    },
    {
      "epoch": 0.658578856152513,
      "grad_norm": 1.978458285331726,
      "learning_rate": 0.0002,
      "loss": 0.9162,
      "step": 95
    },
    {
      "epoch": 0.6932409012131716,
      "grad_norm": 1.1226632595062256,
      "learning_rate": 0.0002,
      "loss": 1.5477,
      "step": 100
    },
    {
      "epoch": 0.7279029462738301,
      "grad_norm": 22.263992309570312,
      "learning_rate": 0.0002,
      "loss": 1.8063,
      "step": 105
    },
    {
      "epoch": 0.7625649913344887,
      "grad_norm": 1.3690563440322876,
      "learning_rate": 0.0002,
      "loss": 1.3102,
      "step": 110
    },
    {
      "epoch": 0.7972270363951474,
      "grad_norm": 0.5651267766952515,
      "learning_rate": 0.0002,
      "loss": 0.553,
      "step": 115
    },
    {
      "epoch": 0.8318890814558059,
      "grad_norm": 0.3272489011287689,
      "learning_rate": 0.0002,
      "loss": 0.4813,
      "step": 120
    },
    {
      "epoch": 0.8665511265164645,
      "grad_norm": 0.30475500226020813,
      "learning_rate": 0.0002,
      "loss": 0.3746,
      "step": 125
    },
    {
      "epoch": 0.901213171577123,
      "grad_norm": 0.2812097370624542,
      "learning_rate": 0.0002,
      "loss": 0.284,
      "step": 130
    },
    {
      "epoch": 0.9358752166377816,
      "grad_norm": 1.159839391708374,
      "learning_rate": 0.0002,
      "loss": 1.5179,
      "step": 135
    },
    {
      "epoch": 0.9705372616984402,
      "grad_norm": 4.740174770355225,
      "learning_rate": 0.0002,
      "loss": 1.549,
      "step": 140
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.613008499145508,
      "learning_rate": 0.0002,
      "loss": 1.3938,
      "step": 145
    }
  ],
  "logging_steps": 5,
  "max_steps": 1440,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3381737531633664.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}