{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.2718600953895072,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03179650238473768,
      "grad_norm": 2.815408945083618,
      "learning_rate": 4.998609830681734e-05,
      "loss": 2.9252,
      "step": 5
    },
    {
      "epoch": 0.06359300476947535,
      "grad_norm": 2.5928449630737305,
      "learning_rate": 4.994440868783522e-05,
      "loss": 2.4825,
      "step": 10
    },
    {
      "epoch": 0.09538950715421304,
      "grad_norm": 1.5238102674484253,
      "learning_rate": 4.987497750755702e-05,
      "loss": 2.2139,
      "step": 15
    },
    {
      "epoch": 0.1271860095389507,
      "grad_norm": 1.1545639038085938,
      "learning_rate": 4.977788198285995e-05,
      "loss": 2.0351,
      "step": 20
    },
    {
      "epoch": 0.1589825119236884,
      "grad_norm": 0.9941776990890503,
      "learning_rate": 4.965323009711954e-05,
      "loss": 2.1238,
      "step": 25
    },
    {
      "epoch": 0.1907790143084261,
      "grad_norm": 1.0189181566238403,
      "learning_rate": 4.950116048011739e-05,
      "loss": 1.9683,
      "step": 30
    },
    {
      "epoch": 0.22257551669316375,
      "grad_norm": 0.8917892575263977,
      "learning_rate": 4.9321842253866136e-05,
      "loss": 1.912,
      "step": 35
    },
    {
      "epoch": 0.2543720190779014,
      "grad_norm": 0.8906163573265076,
      "learning_rate": 4.911547484452286e-05,
      "loss": 1.916,
      "step": 40
    },
    {
      "epoch": 0.2861685214626391,
      "grad_norm": 0.9791882038116455,
      "learning_rate": 4.888228776060016e-05,
      "loss": 1.8891,
      "step": 45
    },
    {
      "epoch": 0.3179650238473768,
      "grad_norm": 0.9773047566413879,
      "learning_rate": 4.862254033772164e-05,
      "loss": 1.9039,
      "step": 50
    },
    {
      "epoch": 0.3497615262321145,
      "grad_norm": 1.0379596948623657,
      "learning_rate": 4.833652145020551e-05,
      "loss": 1.8915,
      "step": 55
    },
    {
      "epoch": 0.3815580286168522,
      "grad_norm": 0.9040148854255676,
      "learning_rate": 4.8024549189797276e-05,
      "loss": 1.887,
      "step": 60
    },
    {
      "epoch": 0.4133545310015898,
      "grad_norm": 1.0032649040222168,
      "learning_rate": 4.7686970511908594e-05,
      "loss": 1.9291,
      "step": 65
    },
    {
      "epoch": 0.4451510333863275,
      "grad_norm": 1.0851433277130127,
      "learning_rate": 4.732416084975585e-05,
      "loss": 1.8363,
      "step": 70
    },
    {
      "epoch": 0.4769475357710652,
      "grad_norm": 0.9705031514167786,
      "learning_rate": 4.6936523696827615e-05,
      "loss": 1.8624,
      "step": 75
    },
    {
      "epoch": 0.5087440381558028,
      "grad_norm": 0.991225004196167,
      "learning_rate": 4.652449015814518e-05,
      "loss": 1.8554,
      "step": 80
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 1.061652660369873,
      "learning_rate": 4.608851847081542e-05,
      "loss": 1.8476,
      "step": 85
    },
    {
      "epoch": 0.5723370429252782,
      "grad_norm": 1.126745581626892,
      "learning_rate": 4.562909349440899e-05,
      "loss": 1.7998,
      "step": 90
    },
    {
      "epoch": 0.604133545310016,
      "grad_norm": 1.155612826347351,
      "learning_rate": 4.514672617173091e-05,
      "loss": 1.9258,
      "step": 95
    },
    {
      "epoch": 0.6359300476947536,
      "grad_norm": 1.0810774564743042,
      "learning_rate": 4.4641952960582877e-05,
      "loss": 1.7941,
      "step": 100
    },
    {
      "epoch": 0.6677265500794912,
      "grad_norm": 1.1277074813842773,
      "learning_rate": 4.411533523714954e-05,
      "loss": 1.8889,
      "step": 105
    },
    {
      "epoch": 0.699523052464229,
      "grad_norm": 1.1673099994659424,
      "learning_rate": 4.3567458671672154e-05,
      "loss": 1.8287,
      "step": 110
    },
    {
      "epoch": 0.7313195548489666,
      "grad_norm": 1.141694188117981,
      "learning_rate": 4.299893257710394e-05,
      "loss": 1.7811,
      "step": 115
    },
    {
      "epoch": 0.7631160572337043,
      "grad_norm": 1.0848796367645264,
      "learning_rate": 4.241038923147154e-05,
      "loss": 1.7925,
      "step": 120
    },
    {
      "epoch": 0.794912559618442,
      "grad_norm": 1.1177420616149902,
      "learning_rate": 4.1802483174696214e-05,
      "loss": 1.8646,
      "step": 125
    },
    {
      "epoch": 0.8267090620031796,
      "grad_norm": 1.2627627849578857,
      "learning_rate": 4.117589048065677e-05,
      "loss": 1.8213,
      "step": 130
    },
    {
      "epoch": 0.8585055643879174,
      "grad_norm": 1.107101321220398,
      "learning_rate": 4.053130800530386e-05,
      "loss": 1.8301,
      "step": 135
    },
    {
      "epoch": 0.890302066772655,
      "grad_norm": 1.219338059425354,
      "learning_rate": 3.986945261166174e-05,
      "loss": 1.8081,
      "step": 140
    },
    {
      "epoch": 0.9220985691573926,
      "grad_norm": 1.2252509593963623,
      "learning_rate": 3.91910603725795e-05,
      "loss": 1.8472,
      "step": 145
    },
    {
      "epoch": 0.9538950715421304,
      "grad_norm": 1.1074373722076416,
      "learning_rate": 3.849688575211836e-05,
      "loss": 1.8186,
      "step": 150
    },
    {
      "epoch": 0.985691573926868,
      "grad_norm": 1.1255358457565308,
      "learning_rate": 3.778770076648543e-05,
      "loss": 1.8542,
      "step": 155
    },
    {
      "epoch": 1.0174880763116056,
      "grad_norm": 1.2812623977661133,
      "learning_rate": 3.706429412544711e-05,
      "loss": 1.6997,
      "step": 160
    },
    {
      "epoch": 1.0492845786963434,
      "grad_norm": 1.1419382095336914,
      "learning_rate": 3.632747035517701e-05,
      "loss": 1.8274,
      "step": 165
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 1.2307173013687134,
      "learning_rate": 3.557804890351383e-05,
      "loss": 1.766,
      "step": 170
    },
    {
      "epoch": 1.1128775834658187,
      "grad_norm": 1.2607144117355347,
      "learning_rate": 3.481686322862443e-05,
      "loss": 1.7501,
      "step": 175
    },
    {
      "epoch": 1.1446740858505564,
      "grad_norm": 1.174317717552185,
      "learning_rate": 3.404475987208539e-05,
      "loss": 1.7754,
      "step": 180
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1.224722146987915,
      "learning_rate": 3.326259751741414e-05,
      "loss": 1.8031,
      "step": 185
    },
    {
      "epoch": 1.2082670906200317,
      "grad_norm": 1.4189472198486328,
      "learning_rate": 3.247124603509659e-05,
      "loss": 1.7226,
      "step": 190
    },
    {
      "epoch": 1.2400635930047694,
      "grad_norm": 1.2927441596984863,
      "learning_rate": 3.167158551517326e-05,
      "loss": 1.7752,
      "step": 195
    },
    {
      "epoch": 1.2718600953895072,
      "grad_norm": 1.361237645149231,
      "learning_rate": 3.0864505288460034e-05,
      "loss": 1.7353,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 471,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 4.963049291671142e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}