{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2039775624681285,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002039775624681285,
      "eval_loss": 1.7698744535446167,
      "eval_runtime": 9.7023,
      "eval_samples_per_second": 85.134,
      "eval_steps_per_second": 10.719,
      "step": 1
    },
    {
      "epoch": 0.006119326874043855,
      "grad_norm": 0.1770610362291336,
      "learning_rate": 3e-05,
      "loss": 1.7347,
      "step": 3
    },
    {
      "epoch": 0.01223865374808771,
      "grad_norm": 0.17321984469890594,
      "learning_rate": 6e-05,
      "loss": 1.7032,
      "step": 6
    },
    {
      "epoch": 0.018357980622131564,
      "grad_norm": 0.1810854822397232,
      "learning_rate": 9e-05,
      "loss": 1.7703,
      "step": 9
    },
    {
      "epoch": 0.018357980622131564,
      "eval_loss": 1.7629197835922241,
      "eval_runtime": 9.4373,
      "eval_samples_per_second": 87.525,
      "eval_steps_per_second": 11.02,
      "step": 9
    },
    {
      "epoch": 0.02447730749617542,
      "grad_norm": 0.13758370280265808,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.8195,
      "step": 12
    },
    {
      "epoch": 0.030596634370219276,
      "grad_norm": 0.12051206082105637,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.7581,
      "step": 15
    },
    {
      "epoch": 0.03671596124426313,
      "grad_norm": 0.14768671989440918,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7982,
      "step": 18
    },
    {
      "epoch": 0.03671596124426313,
      "eval_loss": 1.7322971820831299,
      "eval_runtime": 9.5328,
      "eval_samples_per_second": 86.648,
      "eval_steps_per_second": 10.91,
      "step": 18
    },
    {
      "epoch": 0.04283528811830699,
      "grad_norm": 0.13068392872810364,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.6479,
      "step": 21
    },
    {
      "epoch": 0.04895461499235084,
      "grad_norm": 0.1342775821685791,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.7567,
      "step": 24
    },
    {
      "epoch": 0.05507394186639469,
      "grad_norm": 0.09749147295951843,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.6677,
      "step": 27
    },
    {
      "epoch": 0.05507394186639469,
      "eval_loss": 1.7079455852508545,
      "eval_runtime": 9.5159,
      "eval_samples_per_second": 86.802,
      "eval_steps_per_second": 10.929,
      "step": 27
    },
    {
      "epoch": 0.06119326874043855,
      "grad_norm": 0.10710040479898453,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.7579,
      "step": 30
    },
    {
      "epoch": 0.06731259561448241,
      "grad_norm": 0.11456683278083801,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.598,
      "step": 33
    },
    {
      "epoch": 0.07343192248852626,
      "grad_norm": 0.10145865380764008,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.7151,
      "step": 36
    },
    {
      "epoch": 0.07343192248852626,
      "eval_loss": 1.693877935409546,
      "eval_runtime": 9.5307,
      "eval_samples_per_second": 86.667,
      "eval_steps_per_second": 10.912,
      "step": 36
    },
    {
      "epoch": 0.07955124936257012,
      "grad_norm": 0.09318255633115768,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.7257,
      "step": 39
    },
    {
      "epoch": 0.08567057623661398,
      "grad_norm": 0.09956396371126175,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.6626,
      "step": 42
    },
    {
      "epoch": 0.09178990311065782,
      "grad_norm": 0.09471065551042557,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.7668,
      "step": 45
    },
    {
      "epoch": 0.09178990311065782,
      "eval_loss": 1.6852061748504639,
      "eval_runtime": 9.4793,
      "eval_samples_per_second": 87.138,
      "eval_steps_per_second": 10.971,
      "step": 45
    },
    {
      "epoch": 0.09790922998470168,
      "grad_norm": 0.08964243531227112,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.5625,
      "step": 48
    },
    {
      "epoch": 0.10402855685874554,
      "grad_norm": 0.09644579887390137,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.6178,
      "step": 51
    },
    {
      "epoch": 0.11014788373278939,
      "grad_norm": 0.08853770792484283,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.6741,
      "step": 54
    },
    {
      "epoch": 0.11014788373278939,
      "eval_loss": 1.6789332628250122,
      "eval_runtime": 9.4531,
      "eval_samples_per_second": 87.379,
      "eval_steps_per_second": 11.002,
      "step": 54
    },
    {
      "epoch": 0.11626721060683325,
      "grad_norm": 0.09715063124895096,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.752,
      "step": 57
    },
    {
      "epoch": 0.1223865374808771,
      "grad_norm": 0.10642886161804199,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.6847,
      "step": 60
    },
    {
      "epoch": 0.12850586435492095,
      "grad_norm": 0.0896935909986496,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.6174,
      "step": 63
    },
    {
      "epoch": 0.12850586435492095,
      "eval_loss": 1.674660563468933,
      "eval_runtime": 9.5416,
      "eval_samples_per_second": 86.569,
      "eval_steps_per_second": 10.9,
      "step": 63
    },
    {
      "epoch": 0.13462519122896482,
      "grad_norm": 0.10045938938856125,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.6777,
      "step": 66
    },
    {
      "epoch": 0.14074451810300867,
      "grad_norm": 0.09015397727489471,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.7356,
      "step": 69
    },
    {
      "epoch": 0.14686384497705252,
      "grad_norm": 0.0945475846529007,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.6918,
      "step": 72
    },
    {
      "epoch": 0.14686384497705252,
      "eval_loss": 1.6721640825271606,
      "eval_runtime": 9.4607,
      "eval_samples_per_second": 87.308,
      "eval_steps_per_second": 10.993,
      "step": 72
    },
    {
      "epoch": 0.1529831718510964,
      "grad_norm": 0.09467766433954239,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.6911,
      "step": 75
    },
    {
      "epoch": 0.15910249872514023,
      "grad_norm": 0.08118527382612228,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.7175,
      "step": 78
    },
    {
      "epoch": 0.16522182559918408,
      "grad_norm": 0.09201746433973312,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.6384,
      "step": 81
    },
    {
      "epoch": 0.16522182559918408,
      "eval_loss": 1.670763611793518,
      "eval_runtime": 9.4415,
      "eval_samples_per_second": 87.486,
      "eval_steps_per_second": 11.015,
      "step": 81
    },
    {
      "epoch": 0.17134115247322795,
      "grad_norm": 0.08330924808979034,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.6135,
      "step": 84
    },
    {
      "epoch": 0.1774604793472718,
      "grad_norm": 0.09003107994794846,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.6142,
      "step": 87
    },
    {
      "epoch": 0.18357980622131564,
      "grad_norm": 0.09455045312643051,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.7382,
      "step": 90
    },
    {
      "epoch": 0.18357980622131564,
      "eval_loss": 1.6701672077178955,
      "eval_runtime": 9.4785,
      "eval_samples_per_second": 87.145,
      "eval_steps_per_second": 10.972,
      "step": 90
    },
    {
      "epoch": 0.18969913309535952,
      "grad_norm": 0.10735976696014404,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.6611,
      "step": 93
    },
    {
      "epoch": 0.19581845996940336,
      "grad_norm": 0.09430377185344696,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.755,
      "step": 96
    },
    {
      "epoch": 0.2019377868434472,
      "grad_norm": 0.09521771967411041,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.6503,
      "step": 99
    },
    {
      "epoch": 0.2019377868434472,
      "eval_loss": 1.6700620651245117,
      "eval_runtime": 9.479,
      "eval_samples_per_second": 87.14,
      "eval_steps_per_second": 10.972,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2801079640129536.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}