{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5,
  "eval_steps": 500,
  "global_step": 555,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009009009009009009,
      "grad_norm": 1.4058982133865356,
      "learning_rate": 1.785714285714286e-05,
      "loss": 3.0329,
      "step": 10
    },
    {
      "epoch": 0.018018018018018018,
      "grad_norm": 1.5084704160690308,
      "learning_rate": 3.571428571428572e-05,
      "loss": 2.963,
      "step": 20
    },
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 1.8131718635559082,
      "learning_rate": 5.3571428571428575e-05,
      "loss": 2.5483,
      "step": 30
    },
    {
      "epoch": 0.036036036036036036,
      "grad_norm": 1.7166498899459839,
      "learning_rate": 7.142857142857143e-05,
      "loss": 2.2173,
      "step": 40
    },
    {
      "epoch": 0.04504504504504504,
      "grad_norm": 1.9339869022369385,
      "learning_rate": 8.92857142857143e-05,
      "loss": 2.0999,
      "step": 50
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 1.7656594514846802,
      "learning_rate": 9.998414611537681e-05,
      "loss": 2.065,
      "step": 60
    },
    {
      "epoch": 0.06306306306306306,
      "grad_norm": 1.831594467163086,
      "learning_rate": 9.980590535514233e-05,
      "loss": 2.0001,
      "step": 70
    },
    {
      "epoch": 0.07207207207207207,
      "grad_norm": 1.879267692565918,
      "learning_rate": 9.943031509146825e-05,
      "loss": 1.9977,
      "step": 80
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 1.8009542226791382,
      "learning_rate": 9.885886355253758e-05,
      "loss": 2.0185,
      "step": 90
    },
    {
      "epoch": 0.09009009009009009,
      "grad_norm": 1.7639012336730957,
      "learning_rate": 9.809381504168234e-05,
      "loss": 1.9265,
      "step": 100
    },
    {
      "epoch": 0.0990990990990991,
      "grad_norm": 1.8977757692337036,
      "learning_rate": 9.713820096537225e-05,
      "loss": 1.9129,
      "step": 110
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 2.3275864124298096,
      "learning_rate": 9.599580782165598e-05,
      "loss": 1.9642,
      "step": 120
    },
    {
      "epoch": 0.11711711711711711,
      "grad_norm": 1.7085381746292114,
      "learning_rate": 9.467116219664894e-05,
      "loss": 1.9043,
      "step": 130
    },
    {
      "epoch": 0.12612612612612611,
      "grad_norm": 1.9735201597213745,
      "learning_rate": 9.316951282851707e-05,
      "loss": 1.8833,
      "step": 140
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 1.8018202781677246,
      "learning_rate": 9.149680981002609e-05,
      "loss": 1.9395,
      "step": 150
    },
    {
      "epoch": 0.14414414414414414,
      "grad_norm": 2.0004780292510986,
      "learning_rate": 8.965968101206291e-05,
      "loss": 1.8237,
      "step": 160
    },
    {
      "epoch": 0.15315315315315314,
      "grad_norm": 1.8323822021484375,
      "learning_rate": 8.766540582154859e-05,
      "loss": 1.9039,
      "step": 170
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 2.0277061462402344,
      "learning_rate": 8.552188629780244e-05,
      "loss": 1.8434,
      "step": 180
    },
    {
      "epoch": 0.17117117117117117,
      "grad_norm": 1.9151962995529175,
      "learning_rate": 8.323761586164695e-05,
      "loss": 1.8668,
      "step": 190
    },
    {
      "epoch": 0.18018018018018017,
      "grad_norm": 1.985343098640442,
      "learning_rate": 8.082164564131845e-05,
      "loss": 1.8238,
      "step": 200
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 1.9954603910446167,
      "learning_rate": 7.828354860853399e-05,
      "loss": 1.8616,
      "step": 210
    },
    {
      "epoch": 0.1981981981981982,
      "grad_norm": 2.0763890743255615,
      "learning_rate": 7.563338164682036e-05,
      "loss": 1.795,
      "step": 220
    },
    {
      "epoch": 0.2072072072072072,
      "grad_norm": 2.1642045974731445,
      "learning_rate": 7.288164570240463e-05,
      "loss": 1.7992,
      "step": 230
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 1.9592050313949585,
      "learning_rate": 7.003924417556343e-05,
      "loss": 1.7634,
      "step": 240
    },
    {
      "epoch": 0.22522522522522523,
      "grad_norm": 2.011563777923584,
      "learning_rate": 6.711743971729967e-05,
      "loss": 1.796,
      "step": 250
    },
    {
      "epoch": 0.23423423423423423,
      "grad_norm": 2.1861069202423096,
      "learning_rate": 6.412780960253436e-05,
      "loss": 1.839,
      "step": 260
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 2.18581223487854,
      "learning_rate": 6.108219985664161e-05,
      "loss": 1.8259,
      "step": 270
    },
    {
      "epoch": 0.25225225225225223,
      "grad_norm": 2.018559694290161,
      "learning_rate": 5.799267831709442e-05,
      "loss": 1.7566,
      "step": 280
    },
    {
      "epoch": 0.26126126126126126,
      "grad_norm": 2.043818950653076,
      "learning_rate": 5.487148681620862e-05,
      "loss": 1.7795,
      "step": 290
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 2.263270854949951,
      "learning_rate": 5.173099267445451e-05,
      "loss": 1.7507,
      "step": 300
    },
    {
      "epoch": 0.27927927927927926,
      "grad_norm": 2.139925241470337,
      "learning_rate": 4.858363969653781e-05,
      "loss": 1.7462,
      "step": 310
    },
    {
      "epoch": 0.2882882882882883,
      "grad_norm": 2.1028239727020264,
      "learning_rate": 4.544189886442162e-05,
      "loss": 1.8059,
      "step": 320
    },
    {
      "epoch": 0.2972972972972973,
      "grad_norm": 2.3162405490875244,
      "learning_rate": 4.23182189226621e-05,
      "loss": 1.7456,
      "step": 330
    },
    {
      "epoch": 0.3063063063063063,
      "grad_norm": 2.153001546859741,
      "learning_rate": 3.9224977051856904e-05,
      "loss": 1.7294,
      "step": 340
    },
    {
      "epoch": 0.3153153153153153,
      "grad_norm": 2.3347864151000977,
      "learning_rate": 3.6174429825656685e-05,
      "loss": 1.7287,
      "step": 350
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 2.408170700073242,
      "learning_rate": 3.3178664645666066e-05,
      "loss": 1.7555,
      "step": 360
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 2.102254629135132,
      "learning_rate": 3.0249551846667207e-05,
      "loss": 1.7149,
      "step": 370
    },
    {
      "epoch": 0.34234234234234234,
      "grad_norm": 2.818976640701294,
      "learning_rate": 2.739869766194263e-05,
      "loss": 1.7532,
      "step": 380
    },
    {
      "epoch": 0.35135135135135137,
      "grad_norm": 2.4131245613098145,
      "learning_rate": 2.4637398235066527e-05,
      "loss": 1.6948,
      "step": 390
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 2.3351337909698486,
      "learning_rate": 2.1976594860386597e-05,
      "loss": 1.7533,
      "step": 400
    },
    {
      "epoch": 0.36936936936936937,
      "grad_norm": 2.7150731086730957,
      "learning_rate": 1.9426830629550242e-05,
      "loss": 1.7752,
      "step": 410
    },
    {
      "epoch": 0.3783783783783784,
      "grad_norm": 2.3618431091308594,
      "learning_rate": 1.6998208655858137e-05,
      "loss": 1.7286,
      "step": 420
    },
    {
      "epoch": 0.38738738738738737,
      "grad_norm": 2.6013503074645996,
      "learning_rate": 1.4700352041975168e-05,
      "loss": 1.7331,
      "step": 430
    },
    {
      "epoch": 0.3963963963963964,
      "grad_norm": 2.411003351211548,
      "learning_rate": 1.2542365749622049e-05,
      "loss": 1.7582,
      "step": 440
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 2.211366891860962,
      "learning_rate": 1.0532800522333902e-05,
      "loss": 1.6628,
      "step": 450
    },
    {
      "epoch": 0.4144144144144144,
      "grad_norm": 2.5683863162994385,
      "learning_rate": 8.67961900423711e-06,
      "loss": 1.6957,
      "step": 460
    },
    {
      "epoch": 0.42342342342342343,
      "grad_norm": 2.2518529891967773,
      "learning_rate": 6.990164189094589e-06,
      "loss": 1.7118,
      "step": 470
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 2.4307000637054443,
      "learning_rate": 5.4711303246361144e-06,
      "loss": 1.6488,
      "step": 480
    },
    {
      "epoch": 0.44144144144144143,
      "grad_norm": 2.3331761360168457,
      "learning_rate": 4.12853638746134e-06,
      "loss": 1.6793,
      "step": 490
    },
    {
      "epoch": 0.45045045045045046,
      "grad_norm": 2.3686130046844482,
      "learning_rate": 2.9677022336181413e-06,
      "loss": 1.6649,
      "step": 500
    },
    {
      "epoch": 0.45045045045045046,
      "eval_loss": 1.7574011087417603,
      "eval_runtime": 51.3954,
      "eval_samples_per_second": 76.758,
      "eval_steps_per_second": 19.204,
      "step": 500
    },
    {
      "epoch": 0.4594594594594595,
      "grad_norm": 2.348306655883789,
      "learning_rate": 1.993227519356189e-06,
      "loss": 1.7905,
      "step": 510
    },
    {
      "epoch": 0.46846846846846846,
      "grad_norm": 2.5951645374298096,
      "learning_rate": 1.208973475579761e-06,
      "loss": 1.7358,
      "step": 520
    },
    {
      "epoch": 0.4774774774774775,
      "grad_norm": 2.408781051635742,
      "learning_rate": 6.180476082162656e-07,
      "loss": 1.7079,
      "step": 530
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 2.519191265106201,
      "learning_rate": 2.2279138512300567e-07,
      "loss": 1.6984,
      "step": 540
    },
    {
      "epoch": 0.4954954954954955,
      "grad_norm": 2.511556625366211,
      "learning_rate": 2.4770958321568283e-08,
      "loss": 1.637,
      "step": 550
    },
    {
      "epoch": 0.5,
      "step": 555,
      "total_flos": 1.1620205475764634e+17,
      "train_loss": 1.8654380205515269,
      "train_runtime": 468.8189,
      "train_samples_per_second": 37.866,
      "train_steps_per_second": 1.184
    }
  ],
  "logging_steps": 10,
  "max_steps": 555,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1620205475764634e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}