{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015281757402101241,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015281757402101241,
      "eval_loss": 1.1498295068740845,
      "eval_runtime": 296.5009,
      "eval_samples_per_second": 37.17,
      "eval_steps_per_second": 4.648,
      "step": 1
    },
    {
      "epoch": 0.00045845272206303727,
      "grad_norm": 0.5009817481040955,
      "learning_rate": 3e-05,
      "loss": 1.0517,
      "step": 3
    },
    {
      "epoch": 0.0009169054441260745,
      "grad_norm": 0.5765618681907654,
      "learning_rate": 6e-05,
      "loss": 1.2558,
      "step": 6
    },
    {
      "epoch": 0.0013753581661891117,
      "grad_norm": 0.680789589881897,
      "learning_rate": 9e-05,
      "loss": 1.1772,
      "step": 9
    },
    {
      "epoch": 0.0013753581661891117,
      "eval_loss": 1.0687979459762573,
      "eval_runtime": 296.5136,
      "eval_samples_per_second": 37.169,
      "eval_steps_per_second": 4.647,
      "step": 9
    },
    {
      "epoch": 0.001833810888252149,
      "grad_norm": 0.6807825565338135,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.8785,
      "step": 12
    },
    {
      "epoch": 0.002292263610315186,
      "grad_norm": 0.6680711507797241,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.6678,
      "step": 15
    },
    {
      "epoch": 0.0027507163323782233,
      "grad_norm": 0.5782425999641418,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.6998,
      "step": 18
    },
    {
      "epoch": 0.0027507163323782233,
      "eval_loss": 0.45378875732421875,
      "eval_runtime": 297.1012,
      "eval_samples_per_second": 37.095,
      "eval_steps_per_second": 4.638,
      "step": 18
    },
    {
      "epoch": 0.003209169054441261,
      "grad_norm": 0.2907300889492035,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.3854,
      "step": 21
    },
    {
      "epoch": 0.003667621776504298,
      "grad_norm": 0.39028528332710266,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.4963,
      "step": 24
    },
    {
      "epoch": 0.004126074498567335,
      "grad_norm": 0.2929573059082031,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.2358,
      "step": 27
    },
    {
      "epoch": 0.004126074498567335,
      "eval_loss": 0.32671964168548584,
      "eval_runtime": 297.1526,
      "eval_samples_per_second": 37.089,
      "eval_steps_per_second": 4.637,
      "step": 27
    },
    {
      "epoch": 0.004584527220630372,
      "grad_norm": 0.43915438652038574,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.4901,
      "step": 30
    },
    {
      "epoch": 0.00504297994269341,
      "grad_norm": 0.25669264793395996,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.3356,
      "step": 33
    },
    {
      "epoch": 0.005501432664756447,
      "grad_norm": 0.24750342965126038,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.2031,
      "step": 36
    },
    {
      "epoch": 0.005501432664756447,
      "eval_loss": 0.3014591932296753,
      "eval_runtime": 297.1231,
      "eval_samples_per_second": 37.092,
      "eval_steps_per_second": 4.638,
      "step": 36
    },
    {
      "epoch": 0.005959885386819484,
      "grad_norm": 0.33709627389907837,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.3068,
      "step": 39
    },
    {
      "epoch": 0.006418338108882522,
      "grad_norm": 0.18148460984230042,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.1992,
      "step": 42
    },
    {
      "epoch": 0.006876790830945559,
      "grad_norm": 0.38474711775779724,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.4824,
      "step": 45
    },
    {
      "epoch": 0.006876790830945559,
      "eval_loss": 0.2919241786003113,
      "eval_runtime": 297.3015,
      "eval_samples_per_second": 37.07,
      "eval_steps_per_second": 4.635,
      "step": 45
    },
    {
      "epoch": 0.007335243553008596,
      "grad_norm": 0.12017693370580673,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.1679,
      "step": 48
    },
    {
      "epoch": 0.007793696275071633,
      "grad_norm": 0.22833120822906494,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.2791,
      "step": 51
    },
    {
      "epoch": 0.00825214899713467,
      "grad_norm": 0.12489762902259827,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.1671,
      "step": 54
    },
    {
      "epoch": 0.00825214899713467,
      "eval_loss": 0.28554975986480713,
      "eval_runtime": 296.7155,
      "eval_samples_per_second": 37.143,
      "eval_steps_per_second": 4.644,
      "step": 54
    },
    {
      "epoch": 0.008710601719197708,
      "grad_norm": 0.19015756249427795,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.3258,
      "step": 57
    },
    {
      "epoch": 0.009169054441260744,
      "grad_norm": 0.1945570856332779,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.3784,
      "step": 60
    },
    {
      "epoch": 0.009627507163323782,
      "grad_norm": 0.2393001914024353,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.3064,
      "step": 63
    },
    {
      "epoch": 0.009627507163323782,
      "eval_loss": 0.2829715311527252,
      "eval_runtime": 296.4782,
      "eval_samples_per_second": 37.173,
      "eval_steps_per_second": 4.648,
      "step": 63
    },
    {
      "epoch": 0.01008595988538682,
      "grad_norm": 0.2453099638223648,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.4036,
      "step": 66
    },
    {
      "epoch": 0.010544412607449857,
      "grad_norm": 0.2992512881755829,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.24,
      "step": 69
    },
    {
      "epoch": 0.011002865329512893,
      "grad_norm": 0.21949434280395508,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.3146,
      "step": 72
    },
    {
      "epoch": 0.011002865329512893,
      "eval_loss": 0.2810784876346588,
      "eval_runtime": 296.6441,
      "eval_samples_per_second": 37.152,
      "eval_steps_per_second": 4.645,
      "step": 72
    },
    {
      "epoch": 0.011461318051575931,
      "grad_norm": 0.21194490790367126,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.3362,
      "step": 75
    },
    {
      "epoch": 0.011919770773638969,
      "grad_norm": 0.25095176696777344,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.262,
      "step": 78
    },
    {
      "epoch": 0.012378223495702006,
      "grad_norm": 0.11870462447404861,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.1055,
      "step": 81
    },
    {
      "epoch": 0.012378223495702006,
      "eval_loss": 0.2801515460014343,
      "eval_runtime": 296.9407,
      "eval_samples_per_second": 37.115,
      "eval_steps_per_second": 4.641,
      "step": 81
    },
    {
      "epoch": 0.012836676217765044,
      "grad_norm": 0.16880249977111816,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.192,
      "step": 84
    },
    {
      "epoch": 0.01329512893982808,
      "grad_norm": 0.30556225776672363,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.2727,
      "step": 87
    },
    {
      "epoch": 0.013753581661891117,
      "grad_norm": 0.23559348285198212,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2933,
      "step": 90
    },
    {
      "epoch": 0.013753581661891117,
      "eval_loss": 0.2797732949256897,
      "eval_runtime": 296.9853,
      "eval_samples_per_second": 37.11,
      "eval_steps_per_second": 4.64,
      "step": 90
    },
    {
      "epoch": 0.014212034383954155,
      "grad_norm": 0.24415625631809235,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.3288,
      "step": 93
    },
    {
      "epoch": 0.014670487106017193,
      "grad_norm": 0.09298162907361984,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0904,
      "step": 96
    },
    {
      "epoch": 0.015128939828080229,
      "grad_norm": 0.007296608295291662,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.1468,
      "step": 99
    },
    {
      "epoch": 0.015128939828080229,
      "eval_loss": 0.2796213924884796,
      "eval_runtime": 296.5122,
      "eval_samples_per_second": 37.169,
      "eval_steps_per_second": 4.647,
      "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": 3.20235311726592e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}