{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8651162790697673,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018604651162790697,
      "eval_loss": 7.122097015380859,
      "eval_runtime": 1.8245,
      "eval_samples_per_second": 49.877,
      "eval_steps_per_second": 6.577,
      "step": 1
    },
    {
      "epoch": 0.05581395348837209,
      "grad_norm": 5.93759298324585,
      "learning_rate": 3e-05,
      "loss": 7.0049,
      "step": 3
    },
    {
      "epoch": 0.11162790697674418,
      "grad_norm": 3.5059802532196045,
      "learning_rate": 6e-05,
      "loss": 6.785,
      "step": 6
    },
    {
      "epoch": 0.16744186046511628,
      "grad_norm": 2.8853189945220947,
      "learning_rate": 9e-05,
      "loss": 6.2763,
      "step": 9
    },
    {
      "epoch": 0.16744186046511628,
      "eval_loss": 5.901803016662598,
      "eval_runtime": 1.4176,
      "eval_samples_per_second": 64.193,
      "eval_steps_per_second": 8.465,
      "step": 9
    },
    {
      "epoch": 0.22325581395348837,
      "grad_norm": 2.918773889541626,
      "learning_rate": 9.987820251299122e-05,
      "loss": 5.7888,
      "step": 12
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 2.4992666244506836,
      "learning_rate": 9.924038765061042e-05,
      "loss": 5.5229,
      "step": 15
    },
    {
      "epoch": 0.33488372093023255,
      "grad_norm": 2.410930633544922,
      "learning_rate": 9.806308479691595e-05,
      "loss": 5.2322,
      "step": 18
    },
    {
      "epoch": 0.33488372093023255,
      "eval_loss": 5.058493614196777,
      "eval_runtime": 1.4209,
      "eval_samples_per_second": 64.043,
      "eval_steps_per_second": 8.445,
      "step": 18
    },
    {
      "epoch": 0.39069767441860465,
      "grad_norm": 2.452528953552246,
      "learning_rate": 9.635919272833938e-05,
      "loss": 4.993,
      "step": 21
    },
    {
      "epoch": 0.44651162790697674,
      "grad_norm": 2.0651979446411133,
      "learning_rate": 9.414737964294636e-05,
      "loss": 4.8643,
      "step": 24
    },
    {
      "epoch": 0.5023255813953489,
      "grad_norm": 2.8087124824523926,
      "learning_rate": 9.145187862775209e-05,
      "loss": 4.6,
      "step": 27
    },
    {
      "epoch": 0.5023255813953489,
      "eval_loss": 4.6170830726623535,
      "eval_runtime": 1.4244,
      "eval_samples_per_second": 63.885,
      "eval_steps_per_second": 8.424,
      "step": 27
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 2.3394060134887695,
      "learning_rate": 8.83022221559489e-05,
      "loss": 4.4692,
      "step": 30
    },
    {
      "epoch": 0.6139534883720931,
      "grad_norm": 2.6000590324401855,
      "learning_rate": 8.473291852294987e-05,
      "loss": 4.3967,
      "step": 33
    },
    {
      "epoch": 0.6697674418604651,
      "grad_norm": 2.269150972366333,
      "learning_rate": 8.07830737662829e-05,
      "loss": 4.3017,
      "step": 36
    },
    {
      "epoch": 0.6697674418604651,
      "eval_loss": 4.316805362701416,
      "eval_runtime": 1.4232,
      "eval_samples_per_second": 63.942,
      "eval_steps_per_second": 8.432,
      "step": 36
    },
    {
      "epoch": 0.7255813953488373,
      "grad_norm": 2.6373918056488037,
      "learning_rate": 7.649596321166024e-05,
      "loss": 4.3059,
      "step": 39
    },
    {
      "epoch": 0.7813953488372093,
      "grad_norm": 2.009603977203369,
      "learning_rate": 7.191855733945387e-05,
      "loss": 4.2137,
      "step": 42
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 2.5424704551696777,
      "learning_rate": 6.710100716628344e-05,
      "loss": 4.0419,
      "step": 45
    },
    {
      "epoch": 0.8372093023255814,
      "eval_loss": 4.111220359802246,
      "eval_runtime": 1.427,
      "eval_samples_per_second": 63.768,
      "eval_steps_per_second": 8.409,
      "step": 45
    },
    {
      "epoch": 0.8930232558139535,
      "grad_norm": 2.416537284851074,
      "learning_rate": 6.209609477998338e-05,
      "loss": 3.8657,
      "step": 48
    },
    {
      "epoch": 0.9488372093023256,
      "grad_norm": 2.1381163597106934,
      "learning_rate": 5.695865504800327e-05,
      "loss": 3.9941,
      "step": 51
    },
    {
      "epoch": 1.0093023255813953,
      "grad_norm": 3.770850419998169,
      "learning_rate": 5.174497483512506e-05,
      "loss": 4.5154,
      "step": 54
    },
    {
      "epoch": 1.0093023255813953,
      "eval_loss": 3.986980438232422,
      "eval_runtime": 1.4232,
      "eval_samples_per_second": 63.942,
      "eval_steps_per_second": 8.432,
      "step": 54
    },
    {
      "epoch": 1.0651162790697675,
      "grad_norm": 2.297471523284912,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 3.7592,
      "step": 57
    },
    {
      "epoch": 1.1209302325581396,
      "grad_norm": 2.4820058345794678,
      "learning_rate": 4.131759111665349e-05,
      "loss": 3.8182,
      "step": 60
    },
    {
      "epoch": 1.1767441860465115,
      "grad_norm": 46.66299057006836,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 3.8323,
      "step": 63
    },
    {
      "epoch": 1.1767441860465115,
      "eval_loss": 3.9052999019622803,
      "eval_runtime": 1.4226,
      "eval_samples_per_second": 63.966,
      "eval_steps_per_second": 8.435,
      "step": 63
    },
    {
      "epoch": 1.2325581395348837,
      "grad_norm": 2.4314541816711426,
      "learning_rate": 3.12696703292044e-05,
      "loss": 3.8175,
      "step": 66
    },
    {
      "epoch": 1.2883720930232558,
      "grad_norm": 2.642011880874634,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 3.7243,
      "step": 69
    },
    {
      "epoch": 1.344186046511628,
      "grad_norm": 2.5912115573883057,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 3.5854,
      "step": 72
    },
    {
      "epoch": 1.344186046511628,
      "eval_loss": 3.826810836791992,
      "eval_runtime": 1.4278,
      "eval_samples_per_second": 63.734,
      "eval_steps_per_second": 8.405,
      "step": 72
    },
    {
      "epoch": 1.4,
      "grad_norm": 2.162818193435669,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 3.6049,
      "step": 75
    },
    {
      "epoch": 1.455813953488372,
      "grad_norm": 2.701357126235962,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 3.7687,
      "step": 78
    },
    {
      "epoch": 1.5116279069767442,
      "grad_norm": 2.41788387298584,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 3.8804,
      "step": 81
    },
    {
      "epoch": 1.5116279069767442,
      "eval_loss": 3.793916702270508,
      "eval_runtime": 1.4278,
      "eval_samples_per_second": 63.736,
      "eval_steps_per_second": 8.405,
      "step": 81
    },
    {
      "epoch": 1.5674418604651161,
      "grad_norm": 2.8578102588653564,
      "learning_rate": 7.597595192178702e-06,
      "loss": 3.5929,
      "step": 84
    },
    {
      "epoch": 1.6232558139534885,
      "grad_norm": 2.4142818450927734,
      "learning_rate": 5.060297685041659e-06,
      "loss": 3.7192,
      "step": 87
    },
    {
      "epoch": 1.6790697674418604,
      "grad_norm": 2.4720561504364014,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 3.6054,
      "step": 90
    },
    {
      "epoch": 1.6790697674418604,
      "eval_loss": 3.775722026824951,
      "eval_runtime": 1.4214,
      "eval_samples_per_second": 64.019,
      "eval_steps_per_second": 8.442,
      "step": 90
    },
    {
      "epoch": 1.7348837209302326,
      "grad_norm": 2.3214516639709473,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 3.6552,
      "step": 93
    },
    {
      "epoch": 1.7906976744186047,
      "grad_norm": 2.328660726547241,
      "learning_rate": 4.865965629214819e-07,
      "loss": 3.671,
      "step": 96
    },
    {
      "epoch": 1.8465116279069766,
      "grad_norm": 2.30373477935791,
      "learning_rate": 3.04586490452119e-08,
      "loss": 3.5648,
      "step": 99
    },
    {
      "epoch": 1.8465116279069766,
      "eval_loss": 3.7725934982299805,
      "eval_runtime": 1.4221,
      "eval_samples_per_second": 63.991,
      "eval_steps_per_second": 8.438,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 6658776367104000.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}