{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9995956328346138,
  "eval_steps": 500,
  "global_step": 618,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016174686615446826,
      "grad_norm": 6.084117889404297,
      "learning_rate": 3.225806451612903e-06,
      "loss": 0.7994,
      "step": 10
    },
    {
      "epoch": 0.03234937323089365,
      "grad_norm": 2.019094467163086,
      "learning_rate": 6.451612903225806e-06,
      "loss": 0.339,
      "step": 20
    },
    {
      "epoch": 0.04852405984634048,
      "grad_norm": 1.6682400703430176,
      "learning_rate": 9.67741935483871e-06,
      "loss": 0.1355,
      "step": 30
    },
    {
      "epoch": 0.0646987464617873,
      "grad_norm": 0.7796459794044495,
      "learning_rate": 1.2903225806451613e-05,
      "loss": 0.0864,
      "step": 40
    },
    {
      "epoch": 0.08087343307723413,
      "grad_norm": 0.7346309423446655,
      "learning_rate": 1.6129032258064517e-05,
      "loss": 0.0771,
      "step": 50
    },
    {
      "epoch": 0.09704811969268096,
      "grad_norm": 0.5999702215194702,
      "learning_rate": 1.935483870967742e-05,
      "loss": 0.0616,
      "step": 60
    },
    {
      "epoch": 0.11322280630812778,
      "grad_norm": 0.6098871231079102,
      "learning_rate": 1.9989785286500294e-05,
      "loss": 0.068,
      "step": 70
    },
    {
      "epoch": 0.1293974929235746,
      "grad_norm": 0.6197764277458191,
      "learning_rate": 1.994832377542755e-05,
      "loss": 0.0532,
      "step": 80
    },
    {
      "epoch": 0.14557217953902143,
      "grad_norm": 0.5199822783470154,
      "learning_rate": 1.9875109281794828e-05,
      "loss": 0.0531,
      "step": 90
    },
    {
      "epoch": 0.16174686615446826,
      "grad_norm": 0.44315075874328613,
      "learning_rate": 1.9770375491054264e-05,
      "loss": 0.0543,
      "step": 100
    },
    {
      "epoch": 0.1779215527699151,
      "grad_norm": 0.4719191789627075,
      "learning_rate": 1.9634456691705705e-05,
      "loss": 0.0506,
      "step": 110
    },
    {
      "epoch": 0.1940962393853619,
      "grad_norm": 0.454826295375824,
      "learning_rate": 1.9467786708317257e-05,
      "loss": 0.0436,
      "step": 120
    },
    {
      "epoch": 0.21027092600080874,
      "grad_norm": 0.5078369379043579,
      "learning_rate": 1.9270897516847406e-05,
      "loss": 0.0421,
      "step": 130
    },
    {
      "epoch": 0.22644561261625556,
      "grad_norm": 0.3744693994522095,
      "learning_rate": 1.9044417546688295e-05,
      "loss": 0.047,
      "step": 140
    },
    {
      "epoch": 0.2426202992317024,
      "grad_norm": 0.4639657139778137,
      "learning_rate": 1.878906967484966e-05,
      "loss": 0.0421,
      "step": 150
    },
    {
      "epoch": 0.2587949858471492,
      "grad_norm": 0.4336051642894745,
      "learning_rate": 1.8505668918685603e-05,
      "loss": 0.0433,
      "step": 160
    },
    {
      "epoch": 0.274969672462596,
      "grad_norm": 0.5246915817260742,
      "learning_rate": 1.8195119834528535e-05,
      "loss": 0.0426,
      "step": 170
    },
    {
      "epoch": 0.29114435907804287,
      "grad_norm": 0.3944627642631531,
      "learning_rate": 1.7858413630533305e-05,
      "loss": 0.0397,
      "step": 180
    },
    {
      "epoch": 0.30731904569348967,
      "grad_norm": 0.4689359664916992,
      "learning_rate": 1.7496625002946702e-05,
      "loss": 0.0418,
      "step": 190
    },
    {
      "epoch": 0.3234937323089365,
      "grad_norm": 0.42653799057006836,
      "learning_rate": 1.7110908705900322e-05,
      "loss": 0.0322,
      "step": 200
    },
    {
      "epoch": 0.3396684189243833,
      "grad_norm": 0.4104606807231903,
      "learning_rate": 1.670249586567531e-05,
      "loss": 0.0344,
      "step": 210
    },
    {
      "epoch": 0.3558431055398302,
      "grad_norm": 0.3860621452331543,
      "learning_rate": 1.627269005120304e-05,
      "loss": 0.0329,
      "step": 220
    },
    {
      "epoch": 0.37201779215527697,
      "grad_norm": 0.4381610155105591,
      "learning_rate": 1.5822863113343934e-05,
      "loss": 0.034,
      "step": 230
    },
    {
      "epoch": 0.3881924787707238,
      "grad_norm": 0.32563912868499756,
      "learning_rate": 1.5354450806224553e-05,
      "loss": 0.04,
      "step": 240
    },
    {
      "epoch": 0.4043671653861706,
      "grad_norm": 0.21232913434505463,
      "learning_rate": 1.48689482046087e-05,
      "loss": 0.0335,
      "step": 250
    },
    {
      "epoch": 0.4205418520016175,
      "grad_norm": 0.3260803818702698,
      "learning_rate": 1.4367904931929422e-05,
      "loss": 0.0316,
      "step": 260
    },
    {
      "epoch": 0.4367165386170643,
      "grad_norm": 0.33327850699424744,
      "learning_rate": 1.3852920214212966e-05,
      "loss": 0.0329,
      "step": 270
    },
    {
      "epoch": 0.45289122523251113,
      "grad_norm": 0.35602909326553345,
      "learning_rate": 1.3325637775681561e-05,
      "loss": 0.0337,
      "step": 280
    },
    {
      "epoch": 0.46906591184795793,
      "grad_norm": 0.40170156955718994,
      "learning_rate": 1.2787740592327232e-05,
      "loss": 0.0342,
      "step": 290
    },
    {
      "epoch": 0.4852405984634048,
      "grad_norm": 0.32156628370285034,
      "learning_rate": 1.2240945520202079e-05,
      "loss": 0.0309,
      "step": 300
    },
    {
      "epoch": 0.5014152850788516,
      "grad_norm": 0.24567893147468567,
      "learning_rate": 1.1686997815570473e-05,
      "loss": 0.0273,
      "step": 310
    },
    {
      "epoch": 0.5175899716942984,
      "grad_norm": 0.31566041707992554,
      "learning_rate": 1.112766556441367e-05,
      "loss": 0.0342,
      "step": 320
    },
    {
      "epoch": 0.5337646583097453,
      "grad_norm": 0.26993805170059204,
      "learning_rate": 1.05647340390667e-05,
      "loss": 0.0307,
      "step": 330
    },
    {
      "epoch": 0.549939344925192,
      "grad_norm": 0.25027933716773987,
      "learning_rate": 1e-05,
      "loss": 0.0283,
      "step": 340
    },
    {
      "epoch": 0.5661140315406389,
      "grad_norm": 0.29696565866470337,
      "learning_rate": 9.435265960933304e-06,
      "loss": 0.0327,
      "step": 350
    },
    {
      "epoch": 0.5822887181560857,
      "grad_norm": 0.21952570974826813,
      "learning_rate": 8.872334435586333e-06,
      "loss": 0.024,
      "step": 360
    },
    {
      "epoch": 0.5984634047715326,
      "grad_norm": 0.36718422174453735,
      "learning_rate": 8.313002184429529e-06,
      "loss": 0.027,
      "step": 370
    },
    {
      "epoch": 0.6146380913869793,
      "grad_norm": 0.34000155329704285,
      "learning_rate": 7.759054479797924e-06,
      "loss": 0.0286,
      "step": 380
    },
    {
      "epoch": 0.6308127780024262,
      "grad_norm": 0.35067811608314514,
      "learning_rate": 7.2122594076727705e-06,
      "loss": 0.0251,
      "step": 390
    },
    {
      "epoch": 0.646987464617873,
      "grad_norm": 0.22097982466220856,
      "learning_rate": 6.6743622243184405e-06,
      "loss": 0.0237,
      "step": 400
    },
    {
      "epoch": 0.6631621512333199,
      "grad_norm": 0.23619405925273895,
      "learning_rate": 6.147079785787038e-06,
      "loss": 0.0277,
      "step": 410
    },
    {
      "epoch": 0.6793368378487666,
      "grad_norm": 0.24173900485038757,
      "learning_rate": 5.6320950680705826e-06,
      "loss": 0.0295,
      "step": 420
    },
    {
      "epoch": 0.6955115244642135,
      "grad_norm": 0.31293392181396484,
      "learning_rate": 5.131051795391302e-06,
      "loss": 0.0264,
      "step": 430
    },
    {
      "epoch": 0.7116862110796603,
      "grad_norm": 0.2306731641292572,
      "learning_rate": 4.645549193775452e-06,
      "loss": 0.0271,
      "step": 440
    },
    {
      "epoch": 0.7278608976951072,
      "grad_norm": 0.2935221195220947,
      "learning_rate": 4.177136886656067e-06,
      "loss": 0.0222,
      "step": 450
    },
    {
      "epoch": 0.7440355843105539,
      "grad_norm": 0.22359654307365417,
      "learning_rate": 3.727309948796963e-06,
      "loss": 0.0255,
      "step": 460
    },
    {
      "epoch": 0.7602102709260008,
      "grad_norm": 0.17210273444652557,
      "learning_rate": 3.2975041343246937e-06,
      "loss": 0.0273,
      "step": 470
    },
    {
      "epoch": 0.7763849575414477,
      "grad_norm": 0.2949126660823822,
      "learning_rate": 2.8890912940996784e-06,
      "loss": 0.0258,
      "step": 480
    },
    {
      "epoch": 0.7925596441568945,
      "grad_norm": 0.1924426257610321,
      "learning_rate": 2.5033749970533015e-06,
      "loss": 0.0287,
      "step": 490
    },
    {
      "epoch": 0.8087343307723412,
      "grad_norm": 0.2463998794555664,
      "learning_rate": 2.1415863694666973e-06,
      "loss": 0.0255,
      "step": 500
    },
    {
      "epoch": 0.8249090173877881,
      "grad_norm": 0.33545950055122375,
      "learning_rate": 1.8048801654714687e-06,
      "loss": 0.0259,
      "step": 510
    },
    {
      "epoch": 0.841083704003235,
      "grad_norm": 0.2482132911682129,
      "learning_rate": 1.4943310813144006e-06,
      "loss": 0.0228,
      "step": 520
    },
    {
      "epoch": 0.8572583906186818,
      "grad_norm": 0.3056134581565857,
      "learning_rate": 1.2109303251503434e-06,
      "loss": 0.0272,
      "step": 530
    },
    {
      "epoch": 0.8734330772341286,
      "grad_norm": 0.2144118696451187,
      "learning_rate": 9.555824533117064e-07,
      "loss": 0.0227,
      "step": 540
    },
    {
      "epoch": 0.8896077638495754,
      "grad_norm": 0.38680920004844666,
      "learning_rate": 7.291024831525961e-07,
      "loss": 0.022,
      "step": 550
    },
    {
      "epoch": 0.9057824504650223,
      "grad_norm": 0.3151616156101227,
      "learning_rate": 5.322132916827483e-07,
      "loss": 0.0252,
      "step": 560
    },
    {
      "epoch": 0.9219571370804691,
      "grad_norm": 0.20920976996421814,
      "learning_rate": 3.6554330829429716e-07,
      "loss": 0.0223,
      "step": 570
    },
    {
      "epoch": 0.9381318236959159,
      "grad_norm": 0.18968930840492249,
      "learning_rate": 2.2962450894573606e-07,
      "loss": 0.0219,
      "step": 580
    },
    {
      "epoch": 0.9543065103113627,
      "grad_norm": 0.27189257740974426,
      "learning_rate": 1.2489071820517394e-07,
      "loss": 0.0264,
      "step": 590
    },
    {
      "epoch": 0.9704811969268096,
      "grad_norm": 0.3213247060775757,
      "learning_rate": 5.1676224572452246e-08,
      "loss": 0.0262,
      "step": 600
    },
    {
      "epoch": 0.9866558835422564,
      "grad_norm": 0.25112277269363403,
      "learning_rate": 1.0214713499706596e-08,
      "loss": 0.0224,
      "step": 610
    },
    {
      "epoch": 0.9995956328346138,
      "step": 618,
      "total_flos": 2.6734690727624704e+17,
      "train_loss": 0.053742153359076734,
      "train_runtime": 8084.4069,
      "train_samples_per_second": 2.447,
      "train_steps_per_second": 0.076
    }
  ],
  "logging_steps": 10,
  "max_steps": 618,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6734690727624704e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}