{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03251239535072747,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003251239535072746,
      "eval_loss": 0.7989336848258972,
      "eval_runtime": 75.5758,
      "eval_samples_per_second": 68.54,
      "eval_steps_per_second": 8.574,
      "step": 1
    },
    {
      "epoch": 0.000975371860521824,
      "grad_norm": 0.19370755553245544,
      "learning_rate": 3e-05,
      "loss": 0.7761,
      "step": 3
    },
    {
      "epoch": 0.001950743721043648,
      "grad_norm": 0.22604067623615265,
      "learning_rate": 6e-05,
      "loss": 0.8021,
      "step": 6
    },
    {
      "epoch": 0.002926115581565472,
      "grad_norm": 0.23022867739200592,
      "learning_rate": 9e-05,
      "loss": 0.7489,
      "step": 9
    },
    {
      "epoch": 0.002926115581565472,
      "eval_loss": 0.7733925580978394,
      "eval_runtime": 75.6352,
      "eval_samples_per_second": 68.487,
      "eval_steps_per_second": 8.567,
      "step": 9
    },
    {
      "epoch": 0.003901487442087296,
      "grad_norm": 0.2029326856136322,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.7676,
      "step": 12
    },
    {
      "epoch": 0.00487685930260912,
      "grad_norm": 0.1627143770456314,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.6929,
      "step": 15
    },
    {
      "epoch": 0.005852231163130944,
      "grad_norm": 0.19533924758434296,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.6512,
      "step": 18
    },
    {
      "epoch": 0.005852231163130944,
      "eval_loss": 0.6337721943855286,
      "eval_runtime": 75.5657,
      "eval_samples_per_second": 68.55,
      "eval_steps_per_second": 8.575,
      "step": 18
    },
    {
      "epoch": 0.006827603023652768,
      "grad_norm": 0.16657300293445587,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.6146,
      "step": 21
    },
    {
      "epoch": 0.007802974884174592,
      "grad_norm": 0.13847649097442627,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.5419,
      "step": 24
    },
    {
      "epoch": 0.008778346744696415,
      "grad_norm": 0.12339890748262405,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.5284,
      "step": 27
    },
    {
      "epoch": 0.008778346744696415,
      "eval_loss": 0.5452246069908142,
      "eval_runtime": 75.4618,
      "eval_samples_per_second": 68.644,
      "eval_steps_per_second": 8.587,
      "step": 27
    },
    {
      "epoch": 0.00975371860521824,
      "grad_norm": 0.10368139296770096,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.5381,
      "step": 30
    },
    {
      "epoch": 0.010729090465740063,
      "grad_norm": 0.10946593433618546,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.5459,
      "step": 33
    },
    {
      "epoch": 0.011704462326261888,
      "grad_norm": 0.12600837647914886,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.5512,
      "step": 36
    },
    {
      "epoch": 0.011704462326261888,
      "eval_loss": 0.5043684244155884,
      "eval_runtime": 75.5557,
      "eval_samples_per_second": 68.559,
      "eval_steps_per_second": 8.576,
      "step": 36
    },
    {
      "epoch": 0.012679834186783711,
      "grad_norm": 0.0971435084939003,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.5055,
      "step": 39
    },
    {
      "epoch": 0.013655206047305536,
      "grad_norm": 0.10446028411388397,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.5166,
      "step": 42
    },
    {
      "epoch": 0.014630577907827359,
      "grad_norm": 0.0836402103304863,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.4551,
      "step": 45
    },
    {
      "epoch": 0.014630577907827359,
      "eval_loss": 0.48350176215171814,
      "eval_runtime": 75.4434,
      "eval_samples_per_second": 68.661,
      "eval_steps_per_second": 8.589,
      "step": 45
    },
    {
      "epoch": 0.015605949768349184,
      "grad_norm": 0.08709566295146942,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.4879,
      "step": 48
    },
    {
      "epoch": 0.016581321628871007,
      "grad_norm": 0.09738816320896149,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.4976,
      "step": 51
    },
    {
      "epoch": 0.01755669348939283,
      "grad_norm": 0.0888911709189415,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.4774,
      "step": 54
    },
    {
      "epoch": 0.01755669348939283,
      "eval_loss": 0.4760722815990448,
      "eval_runtime": 75.3804,
      "eval_samples_per_second": 68.718,
      "eval_steps_per_second": 8.596,
      "step": 54
    },
    {
      "epoch": 0.018532065349914657,
      "grad_norm": 0.09731058776378632,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.476,
      "step": 57
    },
    {
      "epoch": 0.01950743721043648,
      "grad_norm": 0.09557648748159409,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.4517,
      "step": 60
    },
    {
      "epoch": 0.020482809070958303,
      "grad_norm": 0.10155142098665237,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.4892,
      "step": 63
    },
    {
      "epoch": 0.020482809070958303,
      "eval_loss": 0.4730236530303955,
      "eval_runtime": 75.574,
      "eval_samples_per_second": 68.542,
      "eval_steps_per_second": 8.574,
      "step": 63
    },
    {
      "epoch": 0.021458180931480126,
      "grad_norm": 0.09069006890058517,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.5073,
      "step": 66
    },
    {
      "epoch": 0.02243355279200195,
      "grad_norm": 0.08972770720720291,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.4521,
      "step": 69
    },
    {
      "epoch": 0.023408924652523776,
      "grad_norm": 0.08725884556770325,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.4493,
      "step": 72
    },
    {
      "epoch": 0.023408924652523776,
      "eval_loss": 0.4715610146522522,
      "eval_runtime": 75.3522,
      "eval_samples_per_second": 68.744,
      "eval_steps_per_second": 8.6,
      "step": 72
    },
    {
      "epoch": 0.0243842965130456,
      "grad_norm": 0.0850292444229126,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.4419,
      "step": 75
    },
    {
      "epoch": 0.025359668373567422,
      "grad_norm": 0.07774844020605087,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.4579,
      "step": 78
    },
    {
      "epoch": 0.026335040234089245,
      "grad_norm": 0.09053909778594971,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.4457,
      "step": 81
    },
    {
      "epoch": 0.026335040234089245,
      "eval_loss": 0.47095027565956116,
      "eval_runtime": 75.5927,
      "eval_samples_per_second": 68.525,
      "eval_steps_per_second": 8.572,
      "step": 81
    },
    {
      "epoch": 0.02731041209461107,
      "grad_norm": 0.07739745080471039,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.4211,
      "step": 84
    },
    {
      "epoch": 0.028285783955132895,
      "grad_norm": 0.08248703926801682,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.4289,
      "step": 87
    },
    {
      "epoch": 0.029261155815654718,
      "grad_norm": 0.09834661334753036,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.5081,
      "step": 90
    },
    {
      "epoch": 0.029261155815654718,
      "eval_loss": 0.4705808162689209,
      "eval_runtime": 75.6328,
      "eval_samples_per_second": 68.489,
      "eval_steps_per_second": 8.568,
      "step": 90
    },
    {
      "epoch": 0.03023652767617654,
      "grad_norm": 0.07801888138055801,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.4643,
      "step": 93
    },
    {
      "epoch": 0.031211899536698368,
      "grad_norm": 0.09624099731445312,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.4155,
      "step": 96
    },
    {
      "epoch": 0.03218727139722019,
      "grad_norm": 0.09031011909246445,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.4894,
      "step": 99
    },
    {
      "epoch": 0.03218727139722019,
      "eval_loss": 0.4705558717250824,
      "eval_runtime": 75.4568,
      "eval_samples_per_second": 68.649,
      "eval_steps_per_second": 8.588,
      "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": 6356704690176000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}