{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.668918918918919,
  "eval_steps": 9,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006756756756756757,
      "eval_loss": 2.4069736003875732,
      "eval_runtime": 17.7545,
      "eval_samples_per_second": 14.081,
      "eval_steps_per_second": 1.802,
      "step": 1
    },
    {
      "epoch": 0.02027027027027027,
      "grad_norm": 1.0342730283737183,
      "learning_rate": 3e-05,
      "loss": 2.3391,
      "step": 3
    },
    {
      "epoch": 0.04054054054054054,
      "grad_norm": 1.2104450464248657,
      "learning_rate": 6e-05,
      "loss": 2.3851,
      "step": 6
    },
    {
      "epoch": 0.060810810810810814,
      "grad_norm": 1.101657509803772,
      "learning_rate": 9e-05,
      "loss": 2.2245,
      "step": 9
    },
    {
      "epoch": 0.060810810810810814,
      "eval_loss": 2.158346652984619,
      "eval_runtime": 18.0282,
      "eval_samples_per_second": 13.867,
      "eval_steps_per_second": 1.775,
      "step": 9
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 1.4548938274383545,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.1255,
      "step": 12
    },
    {
      "epoch": 0.10135135135135136,
      "grad_norm": 1.4602792263031006,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.9416,
      "step": 15
    },
    {
      "epoch": 0.12162162162162163,
      "grad_norm": 1.3606456518173218,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.0257,
      "step": 18
    },
    {
      "epoch": 0.12162162162162163,
      "eval_loss": 1.9933276176452637,
      "eval_runtime": 18.0468,
      "eval_samples_per_second": 13.853,
      "eval_steps_per_second": 1.773,
      "step": 18
    },
    {
      "epoch": 0.14189189189189189,
      "grad_norm": 1.1379156112670898,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.0445,
      "step": 21
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 1.226538062095642,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.9248,
      "step": 24
    },
    {
      "epoch": 0.18243243243243243,
      "grad_norm": 1.1492433547973633,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.0234,
      "step": 27
    },
    {
      "epoch": 0.18243243243243243,
      "eval_loss": 1.922350287437439,
      "eval_runtime": 18.0583,
      "eval_samples_per_second": 13.844,
      "eval_steps_per_second": 1.772,
      "step": 27
    },
    {
      "epoch": 0.20270270270270271,
      "grad_norm": 0.953130841255188,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.0631,
      "step": 30
    },
    {
      "epoch": 0.22297297297297297,
      "grad_norm": 1.0591418743133545,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.855,
      "step": 33
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 1.1333528757095337,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.9812,
      "step": 36
    },
    {
      "epoch": 0.24324324324324326,
      "eval_loss": 1.8779890537261963,
      "eval_runtime": 18.0565,
      "eval_samples_per_second": 13.845,
      "eval_steps_per_second": 1.772,
      "step": 36
    },
    {
      "epoch": 0.2635135135135135,
      "grad_norm": 0.9660253524780273,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.7361,
      "step": 39
    },
    {
      "epoch": 0.28378378378378377,
      "grad_norm": 1.0392206907272339,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.7901,
      "step": 42
    },
    {
      "epoch": 0.30405405405405406,
      "grad_norm": 1.1912034749984741,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.8843,
      "step": 45
    },
    {
      "epoch": 0.30405405405405406,
      "eval_loss": 1.848825454711914,
      "eval_runtime": 18.0415,
      "eval_samples_per_second": 13.857,
      "eval_steps_per_second": 1.774,
      "step": 45
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 1.3097021579742432,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.8724,
      "step": 48
    },
    {
      "epoch": 0.34459459459459457,
      "grad_norm": 1.1584711074829102,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.8167,
      "step": 51
    },
    {
      "epoch": 0.36486486486486486,
      "grad_norm": 1.2216107845306396,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.8643,
      "step": 54
    },
    {
      "epoch": 0.36486486486486486,
      "eval_loss": 1.8309001922607422,
      "eval_runtime": 18.0543,
      "eval_samples_per_second": 13.847,
      "eval_steps_per_second": 1.772,
      "step": 54
    },
    {
      "epoch": 0.38513513513513514,
      "grad_norm": 1.103145718574524,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.8524,
      "step": 57
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 1.1739338636398315,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.9149,
      "step": 60
    },
    {
      "epoch": 0.42567567567567566,
      "grad_norm": 1.1992526054382324,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.8706,
      "step": 63
    },
    {
      "epoch": 0.42567567567567566,
      "eval_loss": 1.8197158575057983,
      "eval_runtime": 18.0457,
      "eval_samples_per_second": 13.854,
      "eval_steps_per_second": 1.773,
      "step": 63
    },
    {
      "epoch": 0.44594594594594594,
      "grad_norm": 1.3138195276260376,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.8948,
      "step": 66
    },
    {
      "epoch": 0.46621621621621623,
      "grad_norm": 1.1699349880218506,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.8595,
      "step": 69
    },
    {
      "epoch": 0.4864864864864865,
      "grad_norm": 1.3647220134735107,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.6933,
      "step": 72
    },
    {
      "epoch": 0.4864864864864865,
      "eval_loss": 1.8112175464630127,
      "eval_runtime": 18.0498,
      "eval_samples_per_second": 13.851,
      "eval_steps_per_second": 1.773,
      "step": 72
    },
    {
      "epoch": 0.5067567567567568,
      "grad_norm": 1.242955207824707,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.8172,
      "step": 75
    },
    {
      "epoch": 0.527027027027027,
      "grad_norm": 1.2106515169143677,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.7981,
      "step": 78
    },
    {
      "epoch": 0.5472972972972973,
      "grad_norm": 1.4093782901763916,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.7838,
      "step": 81
    },
    {
      "epoch": 0.5472972972972973,
      "eval_loss": 1.80698823928833,
      "eval_runtime": 18.0458,
      "eval_samples_per_second": 13.854,
      "eval_steps_per_second": 1.773,
      "step": 81
    },
    {
      "epoch": 0.5675675675675675,
      "grad_norm": 1.143998146057129,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.7882,
      "step": 84
    },
    {
      "epoch": 0.5878378378378378,
      "grad_norm": 1.0916920900344849,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.8518,
      "step": 87
    },
    {
      "epoch": 0.6081081081081081,
      "grad_norm": 1.289839744567871,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.8249,
      "step": 90
    },
    {
      "epoch": 0.6081081081081081,
      "eval_loss": 1.8045200109481812,
      "eval_runtime": 18.054,
      "eval_samples_per_second": 13.847,
      "eval_steps_per_second": 1.772,
      "step": 90
    },
    {
      "epoch": 0.6283783783783784,
      "grad_norm": 1.1940500736236572,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.7712,
      "step": 93
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 1.31273353099823,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.8361,
      "step": 96
    },
    {
      "epoch": 0.668918918918919,
      "grad_norm": 1.3148573637008667,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.8606,
      "step": 99
    },
    {
      "epoch": 0.668918918918919,
      "eval_loss": 1.8047760725021362,
      "eval_runtime": 18.0616,
      "eval_samples_per_second": 13.842,
      "eval_steps_per_second": 1.772,
      "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.468936821449687e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}