{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9515938606847696,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0590318772136954,
      "grad_norm": 6.553243637084961,
      "learning_rate": 2.45e-05,
      "loss": 4.6761,
      "step": 50
    },
    {
      "epoch": 0.1180637544273908,
      "grad_norm": 8.582610130310059,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 4.2203,
      "step": 100
    },
    {
      "epoch": 0.1770956316410862,
      "grad_norm": 9.231163024902344,
      "learning_rate": 4.8996312986480954e-05,
      "loss": 3.9576,
      "step": 150
    },
    {
      "epoch": 0.2361275088547816,
      "grad_norm": 7.166695594787598,
      "learning_rate": 4.7972142564522735e-05,
      "loss": 3.8839,
      "step": 200
    },
    {
      "epoch": 0.29515938606847697,
      "grad_norm": 7.867295265197754,
      "learning_rate": 4.6947972142564524e-05,
      "loss": 3.9156,
      "step": 250
    },
    {
      "epoch": 0.3541912632821724,
      "grad_norm": 9.70073127746582,
      "learning_rate": 4.592380172060631e-05,
      "loss": 3.7892,
      "step": 300
    },
    {
      "epoch": 0.4132231404958678,
      "grad_norm": 10.692851066589355,
      "learning_rate": 4.48996312986481e-05,
      "loss": 3.7978,
      "step": 350
    },
    {
      "epoch": 0.4722550177095632,
      "grad_norm": 8.353034019470215,
      "learning_rate": 4.387546087668988e-05,
      "loss": 3.6882,
      "step": 400
    },
    {
      "epoch": 0.5312868949232585,
      "grad_norm": 7.379666328430176,
      "learning_rate": 4.285129045473167e-05,
      "loss": 3.6928,
      "step": 450
    },
    {
      "epoch": 0.5903187721369539,
      "grad_norm": 8.379216194152832,
      "learning_rate": 4.182712003277345e-05,
      "loss": 3.697,
      "step": 500
    },
    {
      "epoch": 0.6493506493506493,
      "grad_norm": 5.806574821472168,
      "learning_rate": 4.080294961081524e-05,
      "loss": 3.6493,
      "step": 550
    },
    {
      "epoch": 0.7083825265643447,
      "grad_norm": 5.262754917144775,
      "learning_rate": 3.977877918885703e-05,
      "loss": 3.6309,
      "step": 600
    },
    {
      "epoch": 0.7674144037780402,
      "grad_norm": 7.273934364318848,
      "learning_rate": 3.875460876689882e-05,
      "loss": 3.6006,
      "step": 650
    },
    {
      "epoch": 0.8264462809917356,
      "grad_norm": 9.894654273986816,
      "learning_rate": 3.77304383449406e-05,
      "loss": 3.5184,
      "step": 700
    },
    {
      "epoch": 0.885478158205431,
      "grad_norm": 7.7802510261535645,
      "learning_rate": 3.670626792298239e-05,
      "loss": 3.5088,
      "step": 750
    },
    {
      "epoch": 0.9445100354191264,
      "grad_norm": 4.538764953613281,
      "learning_rate": 3.568209750102417e-05,
      "loss": 3.5163,
      "step": 800
    },
    {
      "epoch": 1.0035419126328218,
      "grad_norm": 9.740047454833984,
      "learning_rate": 3.465792707906596e-05,
      "loss": 3.4815,
      "step": 850
    },
    {
      "epoch": 1.062573789846517,
      "grad_norm": 5.822250843048096,
      "learning_rate": 3.3633756657107746e-05,
      "loss": 3.3865,
      "step": 900
    },
    {
      "epoch": 1.1216056670602126,
      "grad_norm": 8.263042449951172,
      "learning_rate": 3.260958623514953e-05,
      "loss": 3.3305,
      "step": 950
    },
    {
      "epoch": 1.1806375442739079,
      "grad_norm": 5.721621513366699,
      "learning_rate": 3.1585415813191316e-05,
      "loss": 3.2901,
      "step": 1000
    },
    {
      "epoch": 1.2396694214876034,
      "grad_norm": 5.100550651550293,
      "learning_rate": 3.05612453912331e-05,
      "loss": 3.2108,
      "step": 1050
    },
    {
      "epoch": 1.2987012987012987,
      "grad_norm": 6.78065299987793,
      "learning_rate": 2.9537074969274887e-05,
      "loss": 3.2782,
      "step": 1100
    },
    {
      "epoch": 1.3577331759149942,
      "grad_norm": 6.02623176574707,
      "learning_rate": 2.851290454731668e-05,
      "loss": 3.2726,
      "step": 1150
    },
    {
      "epoch": 1.4167650531286895,
      "grad_norm": 6.936172962188721,
      "learning_rate": 2.7488734125358463e-05,
      "loss": 3.3236,
      "step": 1200
    },
    {
      "epoch": 1.4757969303423848,
      "grad_norm": 6.60649299621582,
      "learning_rate": 2.646456370340025e-05,
      "loss": 3.2326,
      "step": 1250
    },
    {
      "epoch": 1.5348288075560803,
      "grad_norm": 9.457938194274902,
      "learning_rate": 2.5440393281442034e-05,
      "loss": 3.2819,
      "step": 1300
    },
    {
      "epoch": 1.5938606847697758,
      "grad_norm": 8.299750328063965,
      "learning_rate": 2.441622285948382e-05,
      "loss": 3.1736,
      "step": 1350
    },
    {
      "epoch": 1.6528925619834711,
      "grad_norm": 6.856365203857422,
      "learning_rate": 2.3392052437525604e-05,
      "loss": 3.2544,
      "step": 1400
    },
    {
      "epoch": 1.7119244391971664,
      "grad_norm": 7.17230224609375,
      "learning_rate": 2.236788201556739e-05,
      "loss": 3.2322,
      "step": 1450
    },
    {
      "epoch": 1.770956316410862,
      "grad_norm": 5.7366814613342285,
      "learning_rate": 2.1343711593609177e-05,
      "loss": 3.1887,
      "step": 1500
    },
    {
      "epoch": 1.8299881936245572,
      "grad_norm": 8.30285358428955,
      "learning_rate": 2.0319541171650962e-05,
      "loss": 3.2267,
      "step": 1550
    },
    {
      "epoch": 1.8890200708382525,
      "grad_norm": 9.261168479919434,
      "learning_rate": 1.929537074969275e-05,
      "loss": 3.1754,
      "step": 1600
    },
    {
      "epoch": 1.948051948051948,
      "grad_norm": 7.7448248863220215,
      "learning_rate": 1.8271200327734536e-05,
      "loss": 3.2218,
      "step": 1650
    },
    {
      "epoch": 2.0070838252656436,
      "grad_norm": 6.691303730010986,
      "learning_rate": 1.724702990577632e-05,
      "loss": 3.1039,
      "step": 1700
    },
    {
      "epoch": 2.0661157024793386,
      "grad_norm": 6.595968723297119,
      "learning_rate": 1.622285948381811e-05,
      "loss": 3.0747,
      "step": 1750
    },
    {
      "epoch": 2.125147579693034,
      "grad_norm": 9.761649131774902,
      "learning_rate": 1.5198689061859894e-05,
      "loss": 3.0566,
      "step": 1800
    },
    {
      "epoch": 2.1841794569067297,
      "grad_norm": 4.652196407318115,
      "learning_rate": 1.417451863990168e-05,
      "loss": 3.1184,
      "step": 1850
    },
    {
      "epoch": 2.243211334120425,
      "grad_norm": 9.410402297973633,
      "learning_rate": 1.3150348217943468e-05,
      "loss": 3.0613,
      "step": 1900
    },
    {
      "epoch": 2.3022432113341202,
      "grad_norm": 6.215067386627197,
      "learning_rate": 1.2126177795985253e-05,
      "loss": 3.1054,
      "step": 1950
    },
    {
      "epoch": 2.3612750885478158,
      "grad_norm": 7.889769077301025,
      "learning_rate": 1.110200737402704e-05,
      "loss": 2.999,
      "step": 2000
    },
    {
      "epoch": 2.4203069657615113,
      "grad_norm": 5.15559720993042,
      "learning_rate": 1.0077836952068826e-05,
      "loss": 3.0281,
      "step": 2050
    },
    {
      "epoch": 2.479338842975207,
      "grad_norm": 5.545195579528809,
      "learning_rate": 9.053666530110611e-06,
      "loss": 3.0612,
      "step": 2100
    },
    {
      "epoch": 2.538370720188902,
      "grad_norm": 9.813671112060547,
      "learning_rate": 8.029496108152396e-06,
      "loss": 3.03,
      "step": 2150
    },
    {
      "epoch": 2.5974025974025974,
      "grad_norm": 9.66518783569336,
      "learning_rate": 7.005325686194184e-06,
      "loss": 3.0564,
      "step": 2200
    },
    {
      "epoch": 2.656434474616293,
      "grad_norm": 7.902320384979248,
      "learning_rate": 5.981155264235969e-06,
      "loss": 2.9861,
      "step": 2250
    },
    {
      "epoch": 2.7154663518299884,
      "grad_norm": 5.70012092590332,
      "learning_rate": 4.956984842277755e-06,
      "loss": 3.0116,
      "step": 2300
    },
    {
      "epoch": 2.7744982290436835,
      "grad_norm": 6.998533725738525,
      "learning_rate": 3.9328144203195416e-06,
      "loss": 3.008,
      "step": 2350
    },
    {
      "epoch": 2.833530106257379,
      "grad_norm": 5.67135763168335,
      "learning_rate": 2.9086439983613274e-06,
      "loss": 3.03,
      "step": 2400
    },
    {
      "epoch": 2.8925619834710745,
      "grad_norm": 8.523286819458008,
      "learning_rate": 1.8844735764031136e-06,
      "loss": 2.9847,
      "step": 2450
    },
    {
      "epoch": 2.9515938606847696,
      "grad_norm": 4.999369144439697,
      "learning_rate": 8.603031544448998e-07,
      "loss": 3.0083,
      "step": 2500
    }
  ],
  "logging_steps": 50,
  "max_steps": 2541,
  "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": 2612183615668224.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}