{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 25070,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1994415636218588,
      "grad_norm": 1.8192601203918457,
      "learning_rate": 4.8005584363781416e-05,
      "loss": 7.5114,
      "step": 500
    },
    {
      "epoch": 0.3988831272437176,
      "grad_norm": 1.543924331665039,
      "learning_rate": 4.601116872756282e-05,
      "loss": 6.6557,
      "step": 1000
    },
    {
      "epoch": 0.5983246908655764,
      "grad_norm": 1.7416774034500122,
      "learning_rate": 4.4016753091344236e-05,
      "loss": 6.2893,
      "step": 1500
    },
    {
      "epoch": 0.7977662544874352,
      "grad_norm": 1.72893488407135,
      "learning_rate": 4.202233745512565e-05,
      "loss": 6.0012,
      "step": 2000
    },
    {
      "epoch": 0.9972078181092939,
      "grad_norm": 2.0189125537872314,
      "learning_rate": 4.002792181890706e-05,
      "loss": 5.7968,
      "step": 2500
    },
    {
      "epoch": 1.1966493817311528,
      "grad_norm": 1.9939076900482178,
      "learning_rate": 3.803350618268847e-05,
      "loss": 5.5695,
      "step": 3000
    },
    {
      "epoch": 1.3960909453530115,
      "grad_norm": 2.0916945934295654,
      "learning_rate": 3.6039090546469884e-05,
      "loss": 5.4321,
      "step": 3500
    },
    {
      "epoch": 1.5955325089748702,
      "grad_norm": 2.1514716148376465,
      "learning_rate": 3.4044674910251304e-05,
      "loss": 5.3137,
      "step": 4000
    },
    {
      "epoch": 1.7949740725967291,
      "grad_norm": 2.0663416385650635,
      "learning_rate": 3.205025927403271e-05,
      "loss": 5.2554,
      "step": 4500
    },
    {
      "epoch": 1.994415636218588,
      "grad_norm": 2.196505546569824,
      "learning_rate": 3.0055843637814124e-05,
      "loss": 5.171,
      "step": 5000
    },
    {
      "epoch": 2.193857199840447,
      "grad_norm": 2.258173704147339,
      "learning_rate": 2.8061428001595534e-05,
      "loss": 4.9799,
      "step": 5500
    },
    {
      "epoch": 2.3932987634623055,
      "grad_norm": 2.3806893825531006,
      "learning_rate": 2.6067012365376948e-05,
      "loss": 4.9378,
      "step": 6000
    },
    {
      "epoch": 2.5927403270841642,
      "grad_norm": 2.332186222076416,
      "learning_rate": 2.4072596729158358e-05,
      "loss": 4.9042,
      "step": 6500
    },
    {
      "epoch": 2.792181890706023,
      "grad_norm": 2.366901159286499,
      "learning_rate": 2.207818109293977e-05,
      "loss": 4.8437,
      "step": 7000
    },
    {
      "epoch": 2.9916234543278817,
      "grad_norm": 2.328530788421631,
      "learning_rate": 2.008376545672118e-05,
      "loss": 4.806,
      "step": 7500
    },
    {
      "epoch": 3.191065017949741,
      "grad_norm": 2.5201773643493652,
      "learning_rate": 1.8089349820502595e-05,
      "loss": 4.6991,
      "step": 8000
    },
    {
      "epoch": 3.3905065815715996,
      "grad_norm": 2.608670949935913,
      "learning_rate": 1.6098923015556443e-05,
      "loss": 4.6476,
      "step": 8500
    },
    {
      "epoch": 3.5899481451934583,
      "grad_norm": 2.5904150009155273,
      "learning_rate": 1.4104507379337855e-05,
      "loss": 4.6051,
      "step": 9000
    },
    {
      "epoch": 3.789389708815317,
      "grad_norm": 2.5216405391693115,
      "learning_rate": 1.2110091743119267e-05,
      "loss": 4.6082,
      "step": 9500
    },
    {
      "epoch": 3.988831272437176,
      "grad_norm": 2.5698513984680176,
      "learning_rate": 1.0115676106900679e-05,
      "loss": 4.5688,
      "step": 10000
    },
    {
      "epoch": 4.188272836059035,
      "grad_norm": 2.6962502002716064,
      "learning_rate": 8.125249301954529e-06,
      "loss": 4.4808,
      "step": 10500
    },
    {
      "epoch": 4.387714399680894,
      "grad_norm": 2.8604938983917236,
      "learning_rate": 6.13083366573594e-06,
      "loss": 4.4745,
      "step": 11000
    },
    {
      "epoch": 4.587155963302752,
      "grad_norm": 2.820222854614258,
      "learning_rate": 4.136418029517352e-06,
      "loss": 4.4775,
      "step": 11500
    },
    {
      "epoch": 4.786597526924611,
      "grad_norm": 2.6641643047332764,
      "learning_rate": 2.1420023932987634e-06,
      "loss": 4.4463,
      "step": 12000
    },
    {
      "epoch": 4.98603909054647,
      "grad_norm": 2.8485090732574463,
      "learning_rate": 1.515755883526127e-07,
      "loss": 4.456,
      "step": 12500
    },
    {
      "epoch": 5.0,
      "step": 12535,
      "total_flos": 2.619975204864e+16,
      "train_loss": 5.155460170506956,
      "train_runtime": 6504.3825,
      "train_samples_per_second": 30.832,
      "train_steps_per_second": 1.927
    },
    {
      "epoch": 5.1854806541683285,
      "grad_norm": 2.8765642642974854,
      "learning_rate": 4.907259672915836e-05,
      "loss": 4.6174,
      "step": 13000
    },
    {
      "epoch": 5.384922217790187,
      "grad_norm": 2.5134449005126953,
      "learning_rate": 4.8075388911049066e-05,
      "loss": 4.5994,
      "step": 13500
    },
    {
      "epoch": 5.584363781412046,
      "grad_norm": 2.6400318145751953,
      "learning_rate": 4.707818109293977e-05,
      "loss": 4.5189,
      "step": 14000
    },
    {
      "epoch": 5.783805345033905,
      "grad_norm": 2.5880420207977295,
      "learning_rate": 4.608097327483047e-05,
      "loss": 4.4798,
      "step": 14500
    },
    {
      "epoch": 5.983246908655763,
      "grad_norm": 2.620410919189453,
      "learning_rate": 4.508376545672118e-05,
      "loss": 4.4567,
      "step": 15000
    },
    {
      "epoch": 6.182688472277623,
      "grad_norm": 2.8458619117736816,
      "learning_rate": 4.4086557638611886e-05,
      "loss": 4.2553,
      "step": 15500
    },
    {
      "epoch": 6.382130035899482,
      "grad_norm": 2.748814105987549,
      "learning_rate": 4.3089349820502596e-05,
      "loss": 4.2376,
      "step": 16000
    },
    {
      "epoch": 6.58157159952134,
      "grad_norm": 2.752399444580078,
      "learning_rate": 4.2092142002393306e-05,
      "loss": 4.2098,
      "step": 16500
    },
    {
      "epoch": 6.781013163143199,
      "grad_norm": 2.8099758625030518,
      "learning_rate": 4.1094934184284e-05,
      "loss": 4.1562,
      "step": 17000
    },
    {
      "epoch": 6.980454726765058,
      "grad_norm": 2.6280643939971924,
      "learning_rate": 4.009772636617471e-05,
      "loss": 4.1439,
      "step": 17500
    },
    {
      "epoch": 7.179896290386917,
      "grad_norm": 2.8597283363342285,
      "learning_rate": 3.9100518548065417e-05,
      "loss": 3.9943,
      "step": 18000
    },
    {
      "epoch": 7.379337854008775,
      "grad_norm": 3.049448251724243,
      "learning_rate": 3.810331072995613e-05,
      "loss": 3.9513,
      "step": 18500
    },
    {
      "epoch": 7.578779417630634,
      "grad_norm": 3.0431199073791504,
      "learning_rate": 3.710610291184683e-05,
      "loss": 3.9371,
      "step": 19000
    },
    {
      "epoch": 7.778220981252493,
      "grad_norm": 2.9101345539093018,
      "learning_rate": 3.610889509373754e-05,
      "loss": 3.9142,
      "step": 19500
    },
    {
      "epoch": 7.9776625448743514,
      "grad_norm": 3.04560923576355,
      "learning_rate": 3.5111687275628244e-05,
      "loss": 3.897,
      "step": 20000
    },
    {
      "epoch": 8.177104108496211,
      "grad_norm": 3.3787050247192383,
      "learning_rate": 3.411447945751895e-05,
      "loss": 3.7559,
      "step": 20500
    },
    {
      "epoch": 8.37654567211807,
      "grad_norm": 3.308147430419922,
      "learning_rate": 3.311926605504587e-05,
      "loss": 3.727,
      "step": 21000
    },
    {
      "epoch": 8.575987235739928,
      "grad_norm": 3.117141008377075,
      "learning_rate": 3.212205823693658e-05,
      "loss": 3.7048,
      "step": 21500
    },
    {
      "epoch": 8.775428799361787,
      "grad_norm": 3.0353927612304688,
      "learning_rate": 3.1124850418827286e-05,
      "loss": 3.6959,
      "step": 22000
    },
    {
      "epoch": 8.974870362983646,
      "grad_norm": 3.1278910636901855,
      "learning_rate": 3.0127642600717993e-05,
      "loss": 3.7229,
      "step": 22500
    },
    {
      "epoch": 9.174311926605505,
      "grad_norm": 3.2263429164886475,
      "learning_rate": 2.9132429198244916e-05,
      "loss": 3.5526,
      "step": 23000
    },
    {
      "epoch": 9.373753490227363,
      "grad_norm": 3.4758195877075195,
      "learning_rate": 2.8135221380135622e-05,
      "loss": 3.5455,
      "step": 23500
    },
    {
      "epoch": 9.573195053849222,
      "grad_norm": 3.5570030212402344,
      "learning_rate": 2.7138013562026326e-05,
      "loss": 3.5792,
      "step": 24000
    },
    {
      "epoch": 9.77263661747108,
      "grad_norm": 3.397296667098999,
      "learning_rate": 2.6140805743917036e-05,
      "loss": 3.5237,
      "step": 24500
    },
    {
      "epoch": 9.97207818109294,
      "grad_norm": 3.1818623542785645,
      "learning_rate": 2.5145592341443958e-05,
      "loss": 3.5251,
      "step": 25000
    },
    {
      "epoch": 10.0,
      "step": 25070,
      "total_flos": 5.239950409728e+16,
      "train_loss": 1.9918543002688176,
      "train_runtime": 6309.7744,
      "train_samples_per_second": 63.565,
      "train_steps_per_second": 3.973
    }
  ],
  "logging_steps": 500,
  "max_steps": 25070,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.239950409728e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}