{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.904333145751266,
  "eval_steps": 500,
  "global_step": 2200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.18007878446820483,
      "grad_norm": 0.6928720474243164,
      "learning_rate": 4.90990990990991e-05,
      "loss": 0.3734,
      "step": 40
    },
    {
      "epoch": 0.36015756893640966,
      "grad_norm": 0.41376394033432007,
      "learning_rate": 4.8198198198198205e-05,
      "loss": 0.2893,
      "step": 80
    },
    {
      "epoch": 0.5402363534046145,
      "grad_norm": 0.3630110025405884,
      "learning_rate": 4.72972972972973e-05,
      "loss": 0.2086,
      "step": 120
    },
    {
      "epoch": 0.7203151378728193,
      "grad_norm": 0.5676272511482239,
      "learning_rate": 4.6396396396396394e-05,
      "loss": 0.1801,
      "step": 160
    },
    {
      "epoch": 0.9003939223410242,
      "grad_norm": 0.43620678782463074,
      "learning_rate": 4.54954954954955e-05,
      "loss": 0.131,
      "step": 200
    },
    {
      "epoch": 1.080472706809229,
      "grad_norm": 0.3849905729293823,
      "learning_rate": 4.4594594594594596e-05,
      "loss": 0.1863,
      "step": 240
    },
    {
      "epoch": 1.2605514912774338,
      "grad_norm": 0.5353094935417175,
      "learning_rate": 4.369369369369369e-05,
      "loss": 0.1294,
      "step": 280
    },
    {
      "epoch": 1.4406302757456388,
      "grad_norm": 0.5001752972602844,
      "learning_rate": 4.27927927927928e-05,
      "loss": 0.1006,
      "step": 320
    },
    {
      "epoch": 1.6207090602138434,
      "grad_norm": 0.39846667647361755,
      "learning_rate": 4.189189189189189e-05,
      "loss": 0.1235,
      "step": 360
    },
    {
      "epoch": 1.8007878446820484,
      "grad_norm": 0.3436274528503418,
      "learning_rate": 4.099099099099099e-05,
      "loss": 0.1121,
      "step": 400
    },
    {
      "epoch": 1.9808666291502532,
      "grad_norm": 0.28420963883399963,
      "learning_rate": 4.0090090090090096e-05,
      "loss": 0.0836,
      "step": 440
    },
    {
      "epoch": 2.160945413618458,
      "grad_norm": 0.36981090903282166,
      "learning_rate": 3.918918918918919e-05,
      "loss": 0.0924,
      "step": 480
    },
    {
      "epoch": 2.341024198086663,
      "grad_norm": 0.32350635528564453,
      "learning_rate": 3.8288288288288285e-05,
      "loss": 0.0786,
      "step": 520
    },
    {
      "epoch": 2.5211029825548676,
      "grad_norm": 0.3884509801864624,
      "learning_rate": 3.738738738738739e-05,
      "loss": 0.0651,
      "step": 560
    },
    {
      "epoch": 2.7011817670230727,
      "grad_norm": 0.453033447265625,
      "learning_rate": 3.648648648648649e-05,
      "loss": 0.0625,
      "step": 600
    },
    {
      "epoch": 2.8812605514912777,
      "grad_norm": 0.4408242106437683,
      "learning_rate": 3.558558558558558e-05,
      "loss": 0.0579,
      "step": 640
    },
    {
      "epoch": 3.0613393359594823,
      "grad_norm": 0.3514708876609802,
      "learning_rate": 3.468468468468469e-05,
      "loss": 0.0729,
      "step": 680
    },
    {
      "epoch": 3.2414181204276873,
      "grad_norm": 0.41110527515411377,
      "learning_rate": 3.3783783783783784e-05,
      "loss": 0.0396,
      "step": 720
    },
    {
      "epoch": 3.421496904895892,
      "grad_norm": 0.4381118714809418,
      "learning_rate": 3.2882882882882886e-05,
      "loss": 0.0421,
      "step": 760
    },
    {
      "epoch": 3.601575689364097,
      "grad_norm": 0.3303312063217163,
      "learning_rate": 3.198198198198199e-05,
      "loss": 0.0452,
      "step": 800
    },
    {
      "epoch": 3.7816544738323015,
      "grad_norm": 0.33113524317741394,
      "learning_rate": 3.108108108108108e-05,
      "loss": 0.0427,
      "step": 840
    },
    {
      "epoch": 3.9617332583005065,
      "grad_norm": 0.2702188789844513,
      "learning_rate": 3.0180180180180183e-05,
      "loss": 0.0373,
      "step": 880
    },
    {
      "epoch": 4.141812042768711,
      "grad_norm": 0.24195368587970734,
      "learning_rate": 2.927927927927928e-05,
      "loss": 0.0369,
      "step": 920
    },
    {
      "epoch": 4.321890827236916,
      "grad_norm": 0.2964402437210083,
      "learning_rate": 2.8378378378378378e-05,
      "loss": 0.0324,
      "step": 960
    },
    {
      "epoch": 4.501969611705121,
      "grad_norm": 0.30053117871284485,
      "learning_rate": 2.7477477477477483e-05,
      "loss": 0.0282,
      "step": 1000
    },
    {
      "epoch": 4.682048396173326,
      "grad_norm": 0.31303390860557556,
      "learning_rate": 2.6576576576576577e-05,
      "loss": 0.0267,
      "step": 1040
    },
    {
      "epoch": 4.862127180641531,
      "grad_norm": 0.2905685007572174,
      "learning_rate": 2.5675675675675675e-05,
      "loss": 0.0302,
      "step": 1080
    },
    {
      "epoch": 5.042205965109735,
      "grad_norm": 0.22705398499965668,
      "learning_rate": 2.4774774774774777e-05,
      "loss": 0.0308,
      "step": 1120
    },
    {
      "epoch": 5.22228474957794,
      "grad_norm": 0.12304919958114624,
      "learning_rate": 2.3873873873873874e-05,
      "loss": 0.0172,
      "step": 1160
    },
    {
      "epoch": 5.402363534046145,
      "grad_norm": 0.265591025352478,
      "learning_rate": 2.2972972972972976e-05,
      "loss": 0.0235,
      "step": 1200
    },
    {
      "epoch": 5.58244231851435,
      "grad_norm": 0.3027079105377197,
      "learning_rate": 2.2072072072072073e-05,
      "loss": 0.0231,
      "step": 1240
    },
    {
      "epoch": 5.7625211029825545,
      "grad_norm": 0.29543060064315796,
      "learning_rate": 2.117117117117117e-05,
      "loss": 0.0235,
      "step": 1280
    },
    {
      "epoch": 5.9425998874507595,
      "grad_norm": 0.2505602240562439,
      "learning_rate": 2.0270270270270273e-05,
      "loss": 0.0212,
      "step": 1320
    },
    {
      "epoch": 6.1226786719189645,
      "grad_norm": 0.19057944416999817,
      "learning_rate": 1.936936936936937e-05,
      "loss": 0.0195,
      "step": 1360
    },
    {
      "epoch": 6.3027574563871696,
      "grad_norm": 0.240937277674675,
      "learning_rate": 1.846846846846847e-05,
      "loss": 0.0174,
      "step": 1400
    },
    {
      "epoch": 6.482836240855375,
      "grad_norm": 0.25285354256629944,
      "learning_rate": 1.756756756756757e-05,
      "loss": 0.0172,
      "step": 1440
    },
    {
      "epoch": 6.662915025323579,
      "grad_norm": 0.35455822944641113,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.0172,
      "step": 1480
    },
    {
      "epoch": 6.842993809791784,
      "grad_norm": 0.14479529857635498,
      "learning_rate": 1.5765765765765765e-05,
      "loss": 0.0179,
      "step": 1520
    },
    {
      "epoch": 7.023072594259989,
      "grad_norm": 0.2024831473827362,
      "learning_rate": 1.4864864864864867e-05,
      "loss": 0.0168,
      "step": 1560
    },
    {
      "epoch": 7.203151378728194,
      "grad_norm": 0.17621932923793793,
      "learning_rate": 1.3963963963963963e-05,
      "loss": 0.0127,
      "step": 1600
    },
    {
      "epoch": 7.383230163196399,
      "grad_norm": 0.1810392290353775,
      "learning_rate": 1.3063063063063064e-05,
      "loss": 0.015,
      "step": 1640
    },
    {
      "epoch": 7.563308947664603,
      "grad_norm": 0.2588270306587219,
      "learning_rate": 1.2162162162162164e-05,
      "loss": 0.0145,
      "step": 1680
    },
    {
      "epoch": 7.743387732132808,
      "grad_norm": 0.20072610676288605,
      "learning_rate": 1.1261261261261261e-05,
      "loss": 0.013,
      "step": 1720
    },
    {
      "epoch": 7.923466516601013,
      "grad_norm": 0.20741352438926697,
      "learning_rate": 1.0360360360360361e-05,
      "loss": 0.0107,
      "step": 1760
    },
    {
      "epoch": 8.103545301069218,
      "grad_norm": 0.10997072607278824,
      "learning_rate": 9.45945945945946e-06,
      "loss": 0.0138,
      "step": 1800
    },
    {
      "epoch": 8.283624085537422,
      "grad_norm": 0.1996031105518341,
      "learning_rate": 8.558558558558558e-06,
      "loss": 0.0093,
      "step": 1840
    },
    {
      "epoch": 8.463702870005628,
      "grad_norm": 0.19463427364826202,
      "learning_rate": 7.657657657657658e-06,
      "loss": 0.0087,
      "step": 1880
    },
    {
      "epoch": 8.643781654473832,
      "grad_norm": 0.13947124779224396,
      "learning_rate": 6.7567567567567575e-06,
      "loss": 0.0111,
      "step": 1920
    },
    {
      "epoch": 8.823860438942036,
      "grad_norm": 0.12221422046422958,
      "learning_rate": 5.855855855855856e-06,
      "loss": 0.0124,
      "step": 1960
    },
    {
      "epoch": 9.003939223410242,
      "grad_norm": 0.3783756494522095,
      "learning_rate": 4.954954954954955e-06,
      "loss": 0.0093,
      "step": 2000
    },
    {
      "epoch": 9.184018007878446,
      "grad_norm": 0.07258374243974686,
      "learning_rate": 4.0540540540540545e-06,
      "loss": 0.0095,
      "step": 2040
    },
    {
      "epoch": 9.364096792346652,
      "grad_norm": 0.17456740140914917,
      "learning_rate": 3.153153153153153e-06,
      "loss": 0.0097,
      "step": 2080
    },
    {
      "epoch": 9.544175576814856,
      "grad_norm": 0.15748119354248047,
      "learning_rate": 2.2522522522522524e-06,
      "loss": 0.0084,
      "step": 2120
    },
    {
      "epoch": 9.72425436128306,
      "grad_norm": 0.21072803437709808,
      "learning_rate": 1.3513513513513515e-06,
      "loss": 0.0084,
      "step": 2160
    },
    {
      "epoch": 9.904333145751266,
      "grad_norm": 0.20778457820415497,
      "learning_rate": 4.504504504504505e-07,
      "loss": 0.0067,
      "step": 2200
    }
  ],
  "logging_steps": 40,
  "max_steps": 2220,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 550,
  "total_flos": 9.109057559424e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}