{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 309,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.032362459546925564,
      "grad_norm": 3.921274423599243,
      "learning_rate": 5.806451612903226e-06,
      "loss": 0.5979,
      "step": 10
    },
    {
      "epoch": 0.06472491909385113,
      "grad_norm": 1.9820393323898315,
      "learning_rate": 1.2258064516129034e-05,
      "loss": 0.2221,
      "step": 20
    },
    {
      "epoch": 0.0970873786407767,
      "grad_norm": 1.2062925100326538,
      "learning_rate": 1.870967741935484e-05,
      "loss": 0.1165,
      "step": 30
    },
    {
      "epoch": 0.12944983818770225,
      "grad_norm": 0.9094163179397583,
      "learning_rate": 1.9959162014075553e-05,
      "loss": 0.0929,
      "step": 40
    },
    {
      "epoch": 0.16181229773462782,
      "grad_norm": 0.5544825792312622,
      "learning_rate": 1.9793829188147406e-05,
      "loss": 0.078,
      "step": 50
    },
    {
      "epoch": 0.1941747572815534,
      "grad_norm": 0.6911172270774841,
      "learning_rate": 1.9503556665478066e-05,
      "loss": 0.0822,
      "step": 60
    },
    {
      "epoch": 0.22653721682847897,
      "grad_norm": 0.6673680543899536,
      "learning_rate": 1.9092047447238775e-05,
      "loss": 0.0634,
      "step": 70
    },
    {
      "epoch": 0.2588996763754045,
      "grad_norm": 0.4891921281814575,
      "learning_rate": 1.856455114887056e-05,
      "loss": 0.0594,
      "step": 80
    },
    {
      "epoch": 0.2912621359223301,
      "grad_norm": 0.4860777258872986,
      "learning_rate": 1.792779703083777e-05,
      "loss": 0.0668,
      "step": 90
    },
    {
      "epoch": 0.32362459546925565,
      "grad_norm": 0.5248063802719116,
      "learning_rate": 1.7189908153577473e-05,
      "loss": 0.0601,
      "step": 100
    },
    {
      "epoch": 0.3559870550161812,
      "grad_norm": 0.5064206123352051,
      "learning_rate": 1.636029775176862e-05,
      "loss": 0.0585,
      "step": 110
    },
    {
      "epoch": 0.3883495145631068,
      "grad_norm": 0.420142263174057,
      "learning_rate": 1.544954914987238e-05,
      "loss": 0.0571,
      "step": 120
    },
    {
      "epoch": 0.42071197411003236,
      "grad_norm": 0.36789119243621826,
      "learning_rate": 1.4469280750858854e-05,
      "loss": 0.0523,
      "step": 130
    },
    {
      "epoch": 0.45307443365695793,
      "grad_norm": 0.3841588497161865,
      "learning_rate": 1.3431997820456592e-05,
      "loss": 0.0488,
      "step": 140
    },
    {
      "epoch": 0.4854368932038835,
      "grad_norm": 0.6112226247787476,
      "learning_rate": 1.2350932957710322e-05,
      "loss": 0.047,
      "step": 150
    },
    {
      "epoch": 0.517799352750809,
      "grad_norm": 0.45051074028015137,
      "learning_rate": 1.1239877286961123e-05,
      "loss": 0.0462,
      "step": 160
    },
    {
      "epoch": 0.5501618122977346,
      "grad_norm": 0.3347930312156677,
      "learning_rate": 1.01130045247298e-05,
      "loss": 0.0497,
      "step": 170
    },
    {
      "epoch": 0.5825242718446602,
      "grad_norm": 0.42931899428367615,
      "learning_rate": 8.98469016587892e-06,
      "loss": 0.0437,
      "step": 180
    },
    {
      "epoch": 0.6148867313915858,
      "grad_norm": 0.3714495599269867,
      "learning_rate": 7.869328095692313e-06,
      "loss": 0.0426,
      "step": 190
    },
    {
      "epoch": 0.6472491909385113,
      "grad_norm": 0.379412978887558,
      "learning_rate": 6.781146967348283e-06,
      "loss": 0.0431,
      "step": 200
    },
    {
      "epoch": 0.6796116504854369,
      "grad_norm": 0.34879937767982483,
      "learning_rate": 5.7340286872557515e-06,
      "loss": 0.0364,
      "step": 210
    },
    {
      "epoch": 0.7119741100323624,
      "grad_norm": 0.3119371235370636,
      "learning_rate": 4.7413313238324556e-06,
      "loss": 0.042,
      "step": 220
    },
    {
      "epoch": 0.7443365695792881,
      "grad_norm": 0.391166627407074,
      "learning_rate": 3.815718698874672e-06,
      "loss": 0.0425,
      "step": 230
    },
    {
      "epoch": 0.7766990291262136,
      "grad_norm": 0.2979751229286194,
      "learning_rate": 2.9689988354181742e-06,
      "loss": 0.0383,
      "step": 240
    },
    {
      "epoch": 0.8090614886731392,
      "grad_norm": 0.3025205433368683,
      "learning_rate": 2.211973323008041e-06,
      "loss": 0.0422,
      "step": 250
    },
    {
      "epoch": 0.8414239482200647,
      "grad_norm": 0.409769743680954,
      "learning_rate": 1.5542995220217961e-06,
      "loss": 0.0416,
      "step": 260
    },
    {
      "epoch": 0.8737864077669902,
      "grad_norm": 0.31411364674568176,
      "learning_rate": 1.0043673649027519e-06,
      "loss": 0.0382,
      "step": 270
    },
    {
      "epoch": 0.9061488673139159,
      "grad_norm": 0.256271630525589,
      "learning_rate": 5.691923259479093e-07,
      "loss": 0.0376,
      "step": 280
    },
    {
      "epoch": 0.9385113268608414,
      "grad_norm": 0.276463121175766,
      "learning_rate": 2.5432592503288e-07,
      "loss": 0.0383,
      "step": 290
    },
    {
      "epoch": 0.970873786407767,
      "grad_norm": 0.33534082770347595,
      "learning_rate": 6.378490697611761e-08,
      "loss": 0.041,
      "step": 300
    },
    {
      "epoch": 1.0,
      "step": 309,
      "total_flos": 3.151751154761728e+17,
      "train_loss": 0.07602016984644831,
      "train_runtime": 2131.4563,
      "train_samples_per_second": 4.639,
      "train_steps_per_second": 0.145
    }
  ],
  "logging_steps": 10,
  "max_steps": 309,
  "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": 3.151751154761728e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}