{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.469850121993726,
  "eval_steps": 500,
  "global_step": 2109,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006971070059254096,
      "grad_norm": 2.962728261947632,
      "learning_rate": 0.0,
      "loss": 1.1855,
      "step": 1
    },
    {
      "epoch": 0.03485535029627048,
      "grad_norm": 1.953801155090332,
      "learning_rate": 1.9999434046461045e-05,
      "loss": 0.9795,
      "step": 50
    },
    {
      "epoch": 0.06971070059254096,
      "grad_norm": 1.6633161306381226,
      "learning_rate": 1.996249692618611e-05,
      "loss": 0.8103,
      "step": 100
    },
    {
      "epoch": 0.10456605088881143,
      "grad_norm": 1.8373701572418213,
      "learning_rate": 1.9868053167196865e-05,
      "loss": 0.7672,
      "step": 150
    },
    {
      "epoch": 0.13942140118508192,
      "grad_norm": 1.503631830215454,
      "learning_rate": 1.971664792831919e-05,
      "loss": 0.7452,
      "step": 200
    },
    {
      "epoch": 0.17427675148135238,
      "grad_norm": 1.5163464546203613,
      "learning_rate": 1.9509155167802316e-05,
      "loss": 0.7248,
      "step": 250
    },
    {
      "epoch": 0.20913210177762287,
      "grad_norm": 1.4677717685699463,
      "learning_rate": 1.9246772598559302e-05,
      "loss": 0.7107,
      "step": 300
    },
    {
      "epoch": 0.24398745207389333,
      "grad_norm": 1.4698961973190308,
      "learning_rate": 1.8931014774594656e-05,
      "loss": 0.7002,
      "step": 350
    },
    {
      "epoch": 0.27884280237016384,
      "grad_norm": 1.5015199184417725,
      "learning_rate": 1.8563704348526337e-05,
      "loss": 0.6954,
      "step": 400
    },
    {
      "epoch": 0.3136981526664343,
      "grad_norm": 1.4707640409469604,
      "learning_rate": 1.8146961550666525e-05,
      "loss": 0.6895,
      "step": 450
    },
    {
      "epoch": 0.34855350296270476,
      "grad_norm": 1.4305927753448486,
      "learning_rate": 1.7683191950391142e-05,
      "loss": 0.6779,
      "step": 500
    },
    {
      "epoch": 0.3834088532589753,
      "grad_norm": 1.4896072149276733,
      "learning_rate": 1.717507257044331e-05,
      "loss": 0.6669,
      "step": 550
    },
    {
      "epoch": 0.41826420355524574,
      "grad_norm": 1.4289474487304688,
      "learning_rate": 1.6625536434323358e-05,
      "loss": 0.663,
      "step": 600
    },
    {
      "epoch": 0.4531195538515162,
      "grad_norm": 1.3936972618103027,
      "learning_rate": 1.6037755635962587e-05,
      "loss": 0.6581,
      "step": 650
    },
    {
      "epoch": 0.48797490414778666,
      "grad_norm": 1.4336333274841309,
      "learning_rate": 1.5415123029408046e-05,
      "loss": 0.6487,
      "step": 700
    },
    {
      "epoch": 0.5228302544440572,
      "grad_norm": 1.4300156831741333,
      "learning_rate": 1.4761232644210963e-05,
      "loss": 0.645,
      "step": 750
    },
    {
      "epoch": 0.5576856047403277,
      "grad_norm": 1.3896256685256958,
      "learning_rate": 1.4079858939567557e-05,
      "loss": 0.6366,
      "step": 800
    },
    {
      "epoch": 0.5925409550365981,
      "grad_norm": 1.2966829538345337,
      "learning_rate": 1.3374935016963595e-05,
      "loss": 0.6314,
      "step": 850
    },
    {
      "epoch": 0.6273963053328686,
      "grad_norm": 1.304624319076538,
      "learning_rate": 1.2650529917086232e-05,
      "loss": 0.6287,
      "step": 900
    },
    {
      "epoch": 0.6622516556291391,
      "grad_norm": 1.3826805353164673,
      "learning_rate": 1.1910825132052356e-05,
      "loss": 0.6233,
      "step": 950
    },
    {
      "epoch": 0.6971070059254095,
      "grad_norm": 1.3912091255187988,
      "learning_rate": 1.1160090468532266e-05,
      "loss": 0.6255,
      "step": 1000
    },
    {
      "epoch": 0.73196235622168,
      "grad_norm": 1.2622112035751343,
      "learning_rate": 1.0402659401094154e-05,
      "loss": 0.6141,
      "step": 1050
    },
    {
      "epoch": 0.7668177065179506,
      "grad_norm": 1.3311121463775635,
      "learning_rate": 9.642904058037667e-06,
      "loss": 0.6095,
      "step": 1100
    },
    {
      "epoch": 0.801673056814221,
      "grad_norm": 1.393316626548767,
      "learning_rate": 8.885209984106072e-06,
      "loss": 0.6027,
      "step": 1150
    },
    {
      "epoch": 0.8365284071104915,
      "grad_norm": 1.3410212993621826,
      "learning_rate": 8.133950825754511e-06,
      "loss": 0.6068,
      "step": 1200
    },
    {
      "epoch": 0.8713837574067619,
      "grad_norm": 1.365545392036438,
      "learning_rate": 7.393463085098886e-06,
      "loss": 0.6012,
      "step": 1250
    },
    {
      "epoch": 0.9062391077030324,
      "grad_norm": 1.3484421968460083,
      "learning_rate": 6.6680210882734805e-06,
      "loss": 0.6005,
      "step": 1300
    },
    {
      "epoch": 0.9410944579993029,
      "grad_norm": 1.7153867483139038,
      "learning_rate": 5.961812312687689e-06,
      "loss": 0.594,
      "step": 1350
    },
    {
      "epoch": 0.9759498082955733,
      "grad_norm": 1.308719515800476,
      "learning_rate": 5.278913215600714e-06,
      "loss": 0.5852,
      "step": 1400
    },
    {
      "epoch": 1.0104566050888812,
      "grad_norm": 1.4866747856140137,
      "learning_rate": 4.623265703539146e-06,
      "loss": 0.5385,
      "step": 1450
    },
    {
      "epoch": 1.0453119553851515,
      "grad_norm": 1.4509928226470947,
      "learning_rate": 3.998654378383361e-06,
      "loss": 0.4257,
      "step": 1500
    },
    {
      "epoch": 1.080167305681422,
      "grad_norm": 1.2705004215240479,
      "learning_rate": 3.408684691465355e-06,
      "loss": 0.4253,
      "step": 1550
    },
    {
      "epoch": 1.1150226559776926,
      "grad_norm": 1.35167396068573,
      "learning_rate": 2.85676213177945e-06,
      "loss": 0.4221,
      "step": 1600
    },
    {
      "epoch": 1.149878006273963,
      "grad_norm": 1.313473105430603,
      "learning_rate": 2.3460725684379002e-06,
      "loss": 0.4244,
      "step": 1650
    },
    {
      "epoch": 1.1847333565702336,
      "grad_norm": 1.3406174182891846,
      "learning_rate": 1.8795638608410016e-06,
      "loss": 0.4162,
      "step": 1700
    },
    {
      "epoch": 1.219588706866504,
      "grad_norm": 1.263272762298584,
      "learning_rate": 1.4599288427134283e-06,
      "loss": 0.4189,
      "step": 1750
    },
    {
      "epoch": 1.2544440571627744,
      "grad_norm": 1.3713723421096802,
      "learning_rate": 1.0895897782283305e-06,
      "loss": 0.4181,
      "step": 1800
    },
    {
      "epoch": 1.289299407459045,
      "grad_norm": 1.3794862031936646,
      "learning_rate": 7.706843799431985e-07,
      "loss": 0.4166,
      "step": 1850
    },
    {
      "epoch": 1.3241547577553154,
      "grad_norm": 1.3196351528167725,
      "learning_rate": 5.050534692564358e-07,
      "loss": 0.4125,
      "step": 1900
    },
    {
      "epoch": 1.359010108051586,
      "grad_norm": 1.3097676038742065,
      "learning_rate": 2.94230350612239e-07,
      "loss": 0.4089,
      "step": 1950
    },
    {
      "epoch": 1.3938654583478565,
      "grad_norm": 1.329222559928894,
      "learning_rate": 1.3943196078924247e-07,
      "loss": 0.4135,
      "step": 2000
    },
    {
      "epoch": 1.428720808644127,
      "grad_norm": 1.3468352556228638,
      "learning_rate": 4.155184436196669e-08,
      "loss": 0.4138,
      "step": 2050
    },
    {
      "epoch": 1.4635761589403973,
      "grad_norm": 1.3396908044815063,
      "learning_rate": 1.154995882924892e-09,
      "loss": 0.4112,
      "step": 2100
    },
    {
      "epoch": 1.469850121993726,
      "step": 2109,
      "total_flos": 5.7513841193385984e+17,
      "train_loss": 0.5876018210235169,
      "train_runtime": 8852.0342,
      "train_samples_per_second": 1.906,
      "train_steps_per_second": 0.238
    }
  ],
  "logging_steps": 50,
  "max_steps": 2109,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 5.7513841193385984e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}