{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "eval_steps": 0,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 6.734264373779297,
      "learning_rate": 8.576691395183485e-05,
      "loss": 3.5009,
      "step": 10
    },
    {
      "epoch": 0.02,
      "grad_norm": 0.29098451137542725,
      "learning_rate": 9.653382790366966e-05,
      "loss": 0.1027,
      "step": 20
    },
    {
      "epoch": 0.03,
      "grad_norm": 0.09549916535615921,
      "learning_rate": 0.0001,
      "loss": 0.0191,
      "step": 30
    },
    {
      "epoch": 0.04,
      "grad_norm": 0.3484920263290405,
      "learning_rate": 0.0001,
      "loss": 0.0222,
      "step": 40
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.33001908659935,
      "learning_rate": 0.0001,
      "loss": 0.021,
      "step": 50
    },
    {
      "epoch": 0.06,
      "grad_norm": 0.057511646300554276,
      "learning_rate": 0.0001,
      "loss": 0.0135,
      "step": 60
    },
    {
      "epoch": 0.07,
      "grad_norm": 0.05701196566224098,
      "learning_rate": 0.0001,
      "loss": 0.0117,
      "step": 70
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.043988876044750214,
      "learning_rate": 0.0001,
      "loss": 0.0107,
      "step": 80
    },
    {
      "epoch": 0.09,
      "grad_norm": 0.03720390796661377,
      "learning_rate": 0.0001,
      "loss": 0.0098,
      "step": 90
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.0470854677259922,
      "learning_rate": 0.0001,
      "loss": 0.0091,
      "step": 100
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.035510435700416565,
      "learning_rate": 0.0001,
      "loss": 0.0075,
      "step": 110
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.0346401073038578,
      "learning_rate": 0.0001,
      "loss": 0.0069,
      "step": 120
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.0329650416970253,
      "learning_rate": 0.0001,
      "loss": 0.0064,
      "step": 130
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.056529607623815536,
      "learning_rate": 0.0001,
      "loss": 0.0061,
      "step": 140
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.049417588859796524,
      "learning_rate": 0.0001,
      "loss": 0.0058,
      "step": 150
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.031275127083063126,
      "learning_rate": 0.0001,
      "loss": 0.0046,
      "step": 160
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.026077693328261375,
      "learning_rate": 0.0001,
      "loss": 0.0043,
      "step": 170
    },
    {
      "epoch": 0.18,
      "grad_norm": 0.03110571764409542,
      "learning_rate": 0.0001,
      "loss": 0.0035,
      "step": 180
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.0256363395601511,
      "learning_rate": 0.0001,
      "loss": 0.0039,
      "step": 190
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.13061155378818512,
      "learning_rate": 0.0001,
      "loss": 0.0042,
      "step": 200
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.022342098876833916,
      "learning_rate": 0.0001,
      "loss": 0.0029,
      "step": 210
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.06658010929822922,
      "learning_rate": 0.0001,
      "loss": 0.0028,
      "step": 220
    },
    {
      "epoch": 0.23,
      "grad_norm": 0.02203432098031044,
      "learning_rate": 0.0001,
      "loss": 0.0028,
      "step": 230
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.04879545792937279,
      "learning_rate": 0.0001,
      "loss": 0.0022,
      "step": 240
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.044768281280994415,
      "learning_rate": 0.0001,
      "loss": 0.0026,
      "step": 250
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.030401039868593216,
      "learning_rate": 0.0001,
      "loss": 0.0018,
      "step": 260
    },
    {
      "epoch": 0.27,
      "grad_norm": 0.10380243510007858,
      "learning_rate": 0.0001,
      "loss": 0.0015,
      "step": 270
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.019732531160116196,
      "learning_rate": 0.0001,
      "loss": 0.0017,
      "step": 280
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.015292245894670486,
      "learning_rate": 0.0001,
      "loss": 0.0019,
      "step": 290
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.030675368383526802,
      "learning_rate": 0.0001,
      "loss": 0.0022,
      "step": 300
    },
    {
      "epoch": 0.31,
      "grad_norm": 0.029702844098210335,
      "learning_rate": 0.0001,
      "loss": 0.0014,
      "step": 310
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.016342662274837494,
      "learning_rate": 0.0001,
      "loss": 0.0014,
      "step": 320
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.013499235734343529,
      "learning_rate": 0.0001,
      "loss": 0.0013,
      "step": 330
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.011413372121751308,
      "learning_rate": 0.0001,
      "loss": 0.0012,
      "step": 340
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.09215894341468811,
      "learning_rate": 0.0001,
      "loss": 0.0073,
      "step": 350
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.06609797477722168,
      "learning_rate": 0.0001,
      "loss": 0.0084,
      "step": 360
    },
    {
      "epoch": 0.37,
      "grad_norm": 0.03970978036522865,
      "learning_rate": 0.0001,
      "loss": 0.0075,
      "step": 370
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.029625259339809418,
      "learning_rate": 0.0001,
      "loss": 0.0059,
      "step": 380
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.02456456422805786,
      "learning_rate": 0.0001,
      "loss": 0.005,
      "step": 390
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.03191933035850525,
      "learning_rate": 0.0001,
      "loss": 0.0045,
      "step": 400
    },
    {
      "epoch": 0.41,
      "grad_norm": 0.01918269693851471,
      "learning_rate": 0.0001,
      "loss": 0.0037,
      "step": 410
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.018161766231060028,
      "learning_rate": 0.0001,
      "loss": 0.0031,
      "step": 420
    },
    {
      "epoch": 0.43,
      "grad_norm": 0.019575210288167,
      "learning_rate": 0.0001,
      "loss": 0.0026,
      "step": 430
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.026317287236452103,
      "learning_rate": 0.0001,
      "loss": 0.0023,
      "step": 440
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.040029872208833694,
      "learning_rate": 0.0001,
      "loss": 0.0026,
      "step": 450
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.013975433073937893,
      "learning_rate": 0.0001,
      "loss": 0.0022,
      "step": 460
    },
    {
      "epoch": 0.47,
      "grad_norm": 0.03210354968905449,
      "learning_rate": 0.0001,
      "loss": 0.0017,
      "step": 470
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.01889188587665558,
      "learning_rate": 0.0001,
      "loss": 0.0019,
      "step": 480
    },
    {
      "epoch": 0.49,
      "grad_norm": 0.013832672499120235,
      "learning_rate": 0.0001,
      "loss": 0.0016,
      "step": 490
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.057756196707487106,
      "learning_rate": 0.0001,
      "loss": 0.0018,
      "step": 500
    },
    {
      "epoch": 0.5,
      "step": 500,
      "total_flos": 6.856066495152128e+17,
      "train_loss": 0.07727908698283135,
      "train_runtime": 9003.3191,
      "train_samples_per_second": 1.111,
      "train_steps_per_second": 0.056
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.856066495152128e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}