{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9970501474926253,
  "eval_steps": 500,
  "global_step": 169,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.029498525073746312,
      "grad_norm": 15.842525482177734,
      "learning_rate": 0.0002,
      "loss": 1.3605,
      "step": 5
    },
    {
      "epoch": 0.058997050147492625,
      "grad_norm": 1.1057137250900269,
      "learning_rate": 0.0002,
      "loss": 0.6189,
      "step": 10
    },
    {
      "epoch": 0.08849557522123894,
      "grad_norm": 0.7712059020996094,
      "learning_rate": 0.0002,
      "loss": 0.4282,
      "step": 15
    },
    {
      "epoch": 0.11799410029498525,
      "grad_norm": 1.1073462963104248,
      "learning_rate": 0.0002,
      "loss": 0.4143,
      "step": 20
    },
    {
      "epoch": 0.14749262536873156,
      "grad_norm": 0.6461352705955505,
      "learning_rate": 0.0002,
      "loss": 0.3758,
      "step": 25
    },
    {
      "epoch": 0.17699115044247787,
      "grad_norm": 0.6348222494125366,
      "learning_rate": 0.0002,
      "loss": 0.3761,
      "step": 30
    },
    {
      "epoch": 0.20648967551622419,
      "grad_norm": 0.558731198310852,
      "learning_rate": 0.0002,
      "loss": 0.3652,
      "step": 35
    },
    {
      "epoch": 0.2359882005899705,
      "grad_norm": 0.5885202884674072,
      "learning_rate": 0.0002,
      "loss": 0.3611,
      "step": 40
    },
    {
      "epoch": 0.26548672566371684,
      "grad_norm": 0.5200619697570801,
      "learning_rate": 0.0002,
      "loss": 0.3584,
      "step": 45
    },
    {
      "epoch": 0.2949852507374631,
      "grad_norm": 0.6615349650382996,
      "learning_rate": 0.0002,
      "loss": 0.3352,
      "step": 50
    },
    {
      "epoch": 0.32448377581120946,
      "grad_norm": 0.6481220126152039,
      "learning_rate": 0.0002,
      "loss": 0.3245,
      "step": 55
    },
    {
      "epoch": 0.35398230088495575,
      "grad_norm": 0.5189281702041626,
      "learning_rate": 0.0002,
      "loss": 0.3277,
      "step": 60
    },
    {
      "epoch": 0.3834808259587021,
      "grad_norm": 0.5450770854949951,
      "learning_rate": 0.0002,
      "loss": 0.3394,
      "step": 65
    },
    {
      "epoch": 0.41297935103244837,
      "grad_norm": 0.5216971635818481,
      "learning_rate": 0.0002,
      "loss": 0.3303,
      "step": 70
    },
    {
      "epoch": 0.4424778761061947,
      "grad_norm": 0.5718809962272644,
      "learning_rate": 0.0002,
      "loss": 0.3503,
      "step": 75
    },
    {
      "epoch": 0.471976401179941,
      "grad_norm": 0.46456339955329895,
      "learning_rate": 0.0002,
      "loss": 0.3363,
      "step": 80
    },
    {
      "epoch": 0.5014749262536873,
      "grad_norm": 0.8590409755706787,
      "learning_rate": 0.0002,
      "loss": 0.3111,
      "step": 85
    },
    {
      "epoch": 0.5309734513274337,
      "grad_norm": 0.4512447714805603,
      "learning_rate": 0.0002,
      "loss": 0.3142,
      "step": 90
    },
    {
      "epoch": 0.56047197640118,
      "grad_norm": 1.0052748918533325,
      "learning_rate": 0.0002,
      "loss": 0.3146,
      "step": 95
    },
    {
      "epoch": 0.5899705014749262,
      "grad_norm": 0.41449859738349915,
      "learning_rate": 0.0002,
      "loss": 0.2949,
      "step": 100
    },
    {
      "epoch": 0.6194690265486725,
      "grad_norm": 4.5440354347229,
      "learning_rate": 0.0002,
      "loss": 0.2879,
      "step": 105
    },
    {
      "epoch": 0.6489675516224189,
      "grad_norm": 0.37434083223342896,
      "learning_rate": 0.0002,
      "loss": 0.2943,
      "step": 110
    },
    {
      "epoch": 0.6784660766961652,
      "grad_norm": 0.3563149571418762,
      "learning_rate": 0.0002,
      "loss": 0.3082,
      "step": 115
    },
    {
      "epoch": 0.7079646017699115,
      "grad_norm": 0.40530529618263245,
      "learning_rate": 0.0002,
      "loss": 0.308,
      "step": 120
    },
    {
      "epoch": 0.7374631268436578,
      "grad_norm": 0.39032211899757385,
      "learning_rate": 0.0002,
      "loss": 0.3079,
      "step": 125
    },
    {
      "epoch": 0.7669616519174042,
      "grad_norm": 0.3619149327278137,
      "learning_rate": 0.0002,
      "loss": 0.2861,
      "step": 130
    },
    {
      "epoch": 0.7964601769911505,
      "grad_norm": 0.3519650995731354,
      "learning_rate": 0.0002,
      "loss": 0.2942,
      "step": 135
    },
    {
      "epoch": 0.8259587020648967,
      "grad_norm": 0.33940911293029785,
      "learning_rate": 0.0002,
      "loss": 0.288,
      "step": 140
    },
    {
      "epoch": 0.855457227138643,
      "grad_norm": 0.31343740224838257,
      "learning_rate": 0.0002,
      "loss": 0.2961,
      "step": 145
    },
    {
      "epoch": 0.8849557522123894,
      "grad_norm": 0.4065489172935486,
      "learning_rate": 0.0002,
      "loss": 0.2824,
      "step": 150
    },
    {
      "epoch": 0.9144542772861357,
      "grad_norm": 0.35969874262809753,
      "learning_rate": 0.0002,
      "loss": 0.2918,
      "step": 155
    },
    {
      "epoch": 0.943952802359882,
      "grad_norm": 0.35074159502983093,
      "learning_rate": 0.0002,
      "loss": 0.285,
      "step": 160
    },
    {
      "epoch": 0.9734513274336283,
      "grad_norm": 0.3305889964103699,
      "learning_rate": 0.0002,
      "loss": 0.2761,
      "step": 165
    },
    {
      "epoch": 0.9970501474926253,
      "step": 169,
      "total_flos": 1.3410656498535629e+17,
      "train_loss": 0.3628283569798667,
      "train_runtime": 1720.2693,
      "train_samples_per_second": 1.574,
      "train_steps_per_second": 0.098
    }
  ],
  "logging_steps": 5,
  "max_steps": 169,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3410656498535629e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}