{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.978540772532189,
  "eval_steps": 500,
  "global_step": 348,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08583690987124463,
      "grad_norm": 5.144778728485107,
      "learning_rate": 2.9938918800982563e-05,
      "loss": 0.8269,
      "num_input_tokens_seen": 25888,
      "step": 10
    },
    {
      "epoch": 0.17167381974248927,
      "grad_norm": 4.5363545417785645,
      "learning_rate": 2.975617265898004e-05,
      "loss": 0.1558,
      "num_input_tokens_seen": 53280,
      "step": 20
    },
    {
      "epoch": 0.2575107296137339,
      "grad_norm": 3.198505401611328,
      "learning_rate": 2.9453249887788343e-05,
      "loss": 0.1655,
      "num_input_tokens_seen": 79904,
      "step": 30
    },
    {
      "epoch": 0.34334763948497854,
      "grad_norm": 3.3528692722320557,
      "learning_rate": 2.9032617538884018e-05,
      "loss": 0.1686,
      "num_input_tokens_seen": 106464,
      "step": 40
    },
    {
      "epoch": 0.4291845493562232,
      "grad_norm": 3.4683921337127686,
      "learning_rate": 2.84977013093626e-05,
      "loss": 0.128,
      "num_input_tokens_seen": 132672,
      "step": 50
    },
    {
      "epoch": 0.5150214592274678,
      "grad_norm": 6.693175792694092,
      "learning_rate": 2.7852857642513838e-05,
      "loss": 0.1581,
      "num_input_tokens_seen": 161312,
      "step": 60
    },
    {
      "epoch": 0.6008583690987125,
      "grad_norm": 1.5621659755706787,
      "learning_rate": 2.7103338248251055e-05,
      "loss": 0.1106,
      "num_input_tokens_seen": 187680,
      "step": 70
    },
    {
      "epoch": 0.6866952789699571,
      "grad_norm": 1.8518391847610474,
      "learning_rate": 2.6255247332346036e-05,
      "loss": 0.1401,
      "num_input_tokens_seen": 214400,
      "step": 80
    },
    {
      "epoch": 0.7725321888412017,
      "grad_norm": 2.3987910747528076,
      "learning_rate": 2.531549188280135e-05,
      "loss": 0.1282,
      "num_input_tokens_seen": 240480,
      "step": 90
    },
    {
      "epoch": 0.8583690987124464,
      "grad_norm": 3.301926612854004,
      "learning_rate": 2.4291725418235848e-05,
      "loss": 0.0936,
      "num_input_tokens_seen": 267360,
      "step": 100
    },
    {
      "epoch": 0.944206008583691,
      "grad_norm": 7.198034286499023,
      "learning_rate": 2.3192285656405456e-05,
      "loss": 0.1569,
      "num_input_tokens_seen": 294720,
      "step": 110
    },
    {
      "epoch": 1.0257510729613735,
      "grad_norm": 4.04252290725708,
      "learning_rate": 2.2026126610496852e-05,
      "loss": 0.0904,
      "num_input_tokens_seen": 319184,
      "step": 120
    },
    {
      "epoch": 1.111587982832618,
      "grad_norm": 5.508508682250977,
      "learning_rate": 2.0802745666212592e-05,
      "loss": 0.073,
      "num_input_tokens_seen": 345680,
      "step": 130
    },
    {
      "epoch": 1.1974248927038627,
      "grad_norm": 1.6325355768203735,
      "learning_rate": 1.953210623354359e-05,
      "loss": 0.058,
      "num_input_tokens_seen": 371824,
      "step": 140
    },
    {
      "epoch": 1.2832618025751072,
      "grad_norm": 1.3446625471115112,
      "learning_rate": 1.8224556603165363e-05,
      "loss": 0.0818,
      "num_input_tokens_seen": 398480,
      "step": 150
    },
    {
      "epoch": 1.3690987124463518,
      "grad_norm": 2.4645965099334717,
      "learning_rate": 1.689074566830434e-05,
      "loss": 0.0715,
      "num_input_tokens_seen": 424656,
      "step": 160
    },
    {
      "epoch": 1.4549356223175964,
      "grad_norm": 2.872417688369751,
      "learning_rate": 1.5541536198449044e-05,
      "loss": 0.0691,
      "num_input_tokens_seen": 451088,
      "step": 170
    },
    {
      "epoch": 1.5407725321888412,
      "grad_norm": 2.7769811153411865,
      "learning_rate": 1.4187916371218739e-05,
      "loss": 0.0713,
      "num_input_tokens_seen": 478320,
      "step": 180
    },
    {
      "epoch": 1.6266094420600858,
      "grad_norm": 3.642953634262085,
      "learning_rate": 1.2840910282888211e-05,
      "loss": 0.0985,
      "num_input_tokens_seen": 505328,
      "step": 190
    },
    {
      "epoch": 1.7124463519313304,
      "grad_norm": 4.070372104644775,
      "learning_rate": 1.1511488166385349e-05,
      "loss": 0.0728,
      "num_input_tokens_seen": 531920,
      "step": 200
    },
    {
      "epoch": 1.7982832618025753,
      "grad_norm": 6.3663740158081055,
      "learning_rate": 1.0210477047960303e-05,
      "loss": 0.1002,
      "num_input_tokens_seen": 560496,
      "step": 210
    },
    {
      "epoch": 1.8841201716738198,
      "grad_norm": 2.0767858028411865,
      "learning_rate": 8.948472570152874e-06,
      "loss": 0.0976,
      "num_input_tokens_seen": 586384,
      "step": 220
    },
    {
      "epoch": 1.9699570815450644,
      "grad_norm": 4.728202819824219,
      "learning_rate": 7.735752699185711e-06,
      "loss": 0.0801,
      "num_input_tokens_seen": 612496,
      "step": 230
    },
    {
      "epoch": 2.051502145922747,
      "grad_norm": 0.5934279561042786,
      "learning_rate": 6.582194019564266e-06,
      "loss": 0.0533,
      "num_input_tokens_seen": 637448,
      "step": 240
    },
    {
      "epoch": 2.1373390557939915,
      "grad_norm": 2.772380828857422,
      "learning_rate": 5.497191297593647e-06,
      "loss": 0.059,
      "num_input_tokens_seen": 663528,
      "step": 250
    },
    {
      "epoch": 2.223175965665236,
      "grad_norm": 1.757418155670166,
      "learning_rate": 4.4895809688998655e-06,
      "loss": 0.0505,
      "num_input_tokens_seen": 689384,
      "step": 260
    },
    {
      "epoch": 2.3090128755364807,
      "grad_norm": 2.6222424507141113,
      "learning_rate": 3.567569173085455e-06,
      "loss": 0.0404,
      "num_input_tokens_seen": 715560,
      "step": 270
    },
    {
      "epoch": 2.3948497854077253,
      "grad_norm": 2.2118000984191895,
      "learning_rate": 2.7386649216166233e-06,
      "loss": 0.059,
      "num_input_tokens_seen": 741960,
      "step": 280
    },
    {
      "epoch": 2.48068669527897,
      "grad_norm": 4.022334098815918,
      "learning_rate": 2.0096189432334194e-06,
      "loss": 0.0429,
      "num_input_tokens_seen": 768808,
      "step": 290
    },
    {
      "epoch": 2.5665236051502145,
      "grad_norm": 0.4254824221134186,
      "learning_rate": 1.3863687049356465e-06,
      "loss": 0.0341,
      "num_input_tokens_seen": 795176,
      "step": 300
    },
    {
      "epoch": 2.652360515021459,
      "grad_norm": 2.2265915870666504,
      "learning_rate": 8.7399005630238e-07,
      "loss": 0.0349,
      "num_input_tokens_seen": 821864,
      "step": 310
    },
    {
      "epoch": 2.7381974248927037,
      "grad_norm": 1.5945826768875122,
      "learning_rate": 4.766558909615504e-07,
      "loss": 0.0375,
      "num_input_tokens_seen": 849800,
      "step": 320
    },
    {
      "epoch": 2.8240343347639483,
      "grad_norm": 3.1935954093933105,
      "learning_rate": 1.9760216187710788e-07,
      "loss": 0.0184,
      "num_input_tokens_seen": 876616,
      "step": 330
    },
    {
      "epoch": 2.909871244635193,
      "grad_norm": 2.1143760681152344,
      "learning_rate": 3.910152723075322e-08,
      "loss": 0.0583,
      "num_input_tokens_seen": 903048,
      "step": 340
    },
    {
      "epoch": 2.978540772532189,
      "num_input_tokens_seen": 924488,
      "step": 348,
      "total_flos": 3.957609622319923e+16,
      "train_loss": 0.10672961984728944,
      "train_runtime": 329.4461,
      "train_samples_per_second": 8.46,
      "train_steps_per_second": 1.056
    }
  ],
  "logging_steps": 10,
  "max_steps": 348,
  "num_input_tokens_seen": 924488,
  "num_train_epochs": 3,
  "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": 3.957609622319923e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}