{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.49875311720698257,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012468827930174564,
      "grad_norm": 0.0348743200302124,
      "learning_rate": 4.9995205016168205e-05,
      "loss": 0.4047,
      "step": 5
    },
    {
      "epoch": 0.02493765586034913,
      "grad_norm": 0.052354972809553146,
      "learning_rate": 4.998082190402241e-05,
      "loss": 0.3855,
      "step": 10
    },
    {
      "epoch": 0.03740648379052369,
      "grad_norm": 0.02390989102423191,
      "learning_rate": 4.995685618090584e-05,
      "loss": 0.3818,
      "step": 15
    },
    {
      "epoch": 0.04987531172069826,
      "grad_norm": 0.01846301183104515,
      "learning_rate": 4.9923317040038885e-05,
      "loss": 0.3884,
      "step": 20
    },
    {
      "epoch": 0.06234413965087282,
      "grad_norm": 0.018641460686922073,
      "learning_rate": 4.988021734699259e-05,
      "loss": 0.3713,
      "step": 25
    },
    {
      "epoch": 0.07481296758104738,
      "grad_norm": 0.016644474118947983,
      "learning_rate": 4.982757363475346e-05,
      "loss": 0.3492,
      "step": 30
    },
    {
      "epoch": 0.08728179551122195,
      "grad_norm": 0.01785973273217678,
      "learning_rate": 4.9765406097381426e-05,
      "loss": 0.3596,
      "step": 35
    },
    {
      "epoch": 0.09975062344139651,
      "grad_norm": 0.01776760071516037,
      "learning_rate": 4.96937385822634e-05,
      "loss": 0.3792,
      "step": 40
    },
    {
      "epoch": 0.11221945137157108,
      "grad_norm": 0.019663693383336067,
      "learning_rate": 4.96125985809655e-05,
      "loss": 0.3393,
      "step": 45
    },
    {
      "epoch": 0.12468827930174564,
      "grad_norm": 0.036602046340703964,
      "learning_rate": 4.952201721868727e-05,
      "loss": 0.3433,
      "step": 50
    },
    {
      "epoch": 0.1371571072319202,
      "grad_norm": 0.020088447257876396,
      "learning_rate": 4.94220292423221e-05,
      "loss": 0.3563,
      "step": 55
    },
    {
      "epoch": 0.14962593516209477,
      "grad_norm": 0.023927291855216026,
      "learning_rate": 4.9312673007128405e-05,
      "loss": 0.3543,
      "step": 60
    },
    {
      "epoch": 0.16209476309226933,
      "grad_norm": 0.023712489753961563,
      "learning_rate": 4.919399046201656e-05,
      "loss": 0.3442,
      "step": 65
    },
    {
      "epoch": 0.1745635910224439,
      "grad_norm": 0.02708962745964527,
      "learning_rate": 4.906602713345735e-05,
      "loss": 0.344,
      "step": 70
    },
    {
      "epoch": 0.18703241895261846,
      "grad_norm": 0.026062602177262306,
      "learning_rate": 4.8928832108018106e-05,
      "loss": 0.3426,
      "step": 75
    },
    {
      "epoch": 0.19950124688279303,
      "grad_norm": 0.025727244094014168,
      "learning_rate": 4.878245801353313e-05,
      "loss": 0.3677,
      "step": 80
    },
    {
      "epoch": 0.2119700748129676,
      "grad_norm": 0.03201605752110481,
      "learning_rate": 4.862696099891573e-05,
      "loss": 0.333,
      "step": 85
    },
    {
      "epoch": 0.22443890274314215,
      "grad_norm": 0.03317998722195625,
      "learning_rate": 4.846240071261959e-05,
      "loss": 0.3596,
      "step": 90
    },
    {
      "epoch": 0.23690773067331672,
      "grad_norm": 0.02743816375732422,
      "learning_rate": 4.828884027975768e-05,
      "loss": 0.3156,
      "step": 95
    },
    {
      "epoch": 0.24937655860349128,
      "grad_norm": 0.030033418908715248,
      "learning_rate": 4.810634627788756e-05,
      "loss": 0.3355,
      "step": 100
    },
    {
      "epoch": 0.26184538653366585,
      "grad_norm": 0.031716831028461456,
      "learning_rate": 4.791498871147229e-05,
      "loss": 0.3518,
      "step": 105
    },
    {
      "epoch": 0.2743142144638404,
      "grad_norm": 0.03049326501786709,
      "learning_rate": 4.7714840985026834e-05,
      "loss": 0.3031,
      "step": 110
    },
    {
      "epoch": 0.286783042394015,
      "grad_norm": 0.03361716866493225,
      "learning_rate": 4.7505979874960184e-05,
      "loss": 0.3452,
      "step": 115
    },
    {
      "epoch": 0.29925187032418954,
      "grad_norm": 0.0355195626616478,
      "learning_rate": 4.728848550012399e-05,
      "loss": 0.343,
      "step": 120
    },
    {
      "epoch": 0.3117206982543641,
      "grad_norm": 0.04162430390715599,
      "learning_rate": 4.706244129107914e-05,
      "loss": 0.3234,
      "step": 125
    },
    {
      "epoch": 0.32418952618453867,
      "grad_norm": 0.04150069132447243,
      "learning_rate": 4.682793395809184e-05,
      "loss": 0.3238,
      "step": 130
    },
    {
      "epoch": 0.33665835411471323,
      "grad_norm": 0.04490313306450844,
      "learning_rate": 4.658505345787169e-05,
      "loss": 0.3337,
      "step": 135
    },
    {
      "epoch": 0.3491271820448878,
      "grad_norm": 0.03981255367398262,
      "learning_rate": 4.633389295906443e-05,
      "loss": 0.3422,
      "step": 140
    },
    {
      "epoch": 0.36159600997506236,
      "grad_norm": 0.04022540897130966,
      "learning_rate": 4.607454880651253e-05,
      "loss": 0.315,
      "step": 145
    },
    {
      "epoch": 0.3740648379052369,
      "grad_norm": 0.03891991823911667,
      "learning_rate": 4.580712048429746e-05,
      "loss": 0.3213,
      "step": 150
    },
    {
      "epoch": 0.3865336658354115,
      "grad_norm": 0.04148748144507408,
      "learning_rate": 4.553171057757772e-05,
      "loss": 0.3326,
      "step": 155
    },
    {
      "epoch": 0.39900249376558605,
      "grad_norm": 0.04601826146245003,
      "learning_rate": 4.5248424733237294e-05,
      "loss": 0.3264,
      "step": 160
    },
    {
      "epoch": 0.4114713216957606,
      "grad_norm": 0.04266240820288658,
      "learning_rate": 4.4957371619359644e-05,
      "loss": 0.3422,
      "step": 165
    },
    {
      "epoch": 0.4239401496259352,
      "grad_norm": 0.04361332580447197,
      "learning_rate": 4.46586628835428e-05,
      "loss": 0.3136,
      "step": 170
    },
    {
      "epoch": 0.43640897755610975,
      "grad_norm": 0.051424313336610794,
      "learning_rate": 4.435241311007146e-05,
      "loss": 0.335,
      "step": 175
    },
    {
      "epoch": 0.4488778054862843,
      "grad_norm": 0.04484390467405319,
      "learning_rate": 4.403873977596258e-05,
      "loss": 0.3188,
      "step": 180
    },
    {
      "epoch": 0.4613466334164589,
      "grad_norm": 0.04609343037009239,
      "learning_rate": 4.371776320590143e-05,
      "loss": 0.3355,
      "step": 185
    },
    {
      "epoch": 0.47381546134663344,
      "grad_norm": 0.052802663296461105,
      "learning_rate": 4.3389606526085115e-05,
      "loss": 0.3358,
      "step": 190
    },
    {
      "epoch": 0.486284289276808,
      "grad_norm": 0.0500580295920372,
      "learning_rate": 4.305439561699154e-05,
      "loss": 0.2961,
      "step": 195
    },
    {
      "epoch": 0.49875311720698257,
      "grad_norm": 0.05000691115856171,
      "learning_rate": 4.271225906509186e-05,
      "loss": 0.3014,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 802,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5685471391082086e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}