{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0533333333333332,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 9.902738571166992,
      "learning_rate": 0.0,
      "loss": 7.5683,
      "step": 1
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 8.882129669189453,
      "learning_rate": 4e-05,
      "loss": 7.3788,
      "step": 2
    },
    {
      "epoch": 0.05333333333333334,
      "grad_norm": 6.9227614402771,
      "learning_rate": 8e-05,
      "loss": 7.2323,
      "step": 3
    },
    {
      "epoch": 0.07111111111111111,
      "grad_norm": 3.930971384048462,
      "learning_rate": 0.00012,
      "loss": 7.0819,
      "step": 4
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 3.7796881198883057,
      "learning_rate": 0.00016,
      "loss": 6.7808,
      "step": 5
    },
    {
      "epoch": 0.10666666666666667,
      "grad_norm": 3.719074249267578,
      "learning_rate": 0.0002,
      "loss": 6.704,
      "step": 6
    },
    {
      "epoch": 0.12444444444444444,
      "grad_norm": 5.659056186676025,
      "learning_rate": 0.00019636363636363636,
      "loss": 6.5588,
      "step": 7
    },
    {
      "epoch": 0.14222222222222222,
      "grad_norm": 11.144302368164062,
      "learning_rate": 0.00019272727272727274,
      "loss": 6.4086,
      "step": 8
    },
    {
      "epoch": 0.16,
      "grad_norm": 4.9178338050842285,
      "learning_rate": 0.0001890909090909091,
      "loss": 6.2833,
      "step": 9
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 2.524080991744995,
      "learning_rate": 0.00018545454545454545,
      "loss": 6.2426,
      "step": 10
    },
    {
      "epoch": 0.19555555555555557,
      "grad_norm": 3.267975330352783,
      "learning_rate": 0.00018181818181818183,
      "loss": 6.2025,
      "step": 11
    },
    {
      "epoch": 0.21333333333333335,
      "grad_norm": 3.699554681777954,
      "learning_rate": 0.0001781818181818182,
      "loss": 6.1311,
      "step": 12
    },
    {
      "epoch": 0.2311111111111111,
      "grad_norm": 5.842496395111084,
      "learning_rate": 0.00017454545454545454,
      "loss": 6.106,
      "step": 13
    },
    {
      "epoch": 0.24888888888888888,
      "grad_norm": 4.9988532066345215,
      "learning_rate": 0.0001709090909090909,
      "loss": 6.1794,
      "step": 14
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 4.165736198425293,
      "learning_rate": 0.00016727272727272728,
      "loss": 6.1222,
      "step": 15
    },
    {
      "epoch": 0.28444444444444444,
      "grad_norm": 4.161974906921387,
      "learning_rate": 0.00016363636363636366,
      "loss": 6.0748,
      "step": 16
    },
    {
      "epoch": 0.3022222222222222,
      "grad_norm": 3.4932847023010254,
      "learning_rate": 0.00016,
      "loss": 5.9904,
      "step": 17
    },
    {
      "epoch": 0.32,
      "grad_norm": 4.147347927093506,
      "learning_rate": 0.00015636363636363637,
      "loss": 6.041,
      "step": 18
    },
    {
      "epoch": 0.3377777777777778,
      "grad_norm": 3.2812204360961914,
      "learning_rate": 0.00015272727272727275,
      "loss": 5.9663,
      "step": 19
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 3.3930680751800537,
      "learning_rate": 0.0001490909090909091,
      "loss": 5.9091,
      "step": 20
    },
    {
      "epoch": 0.37333333333333335,
      "grad_norm": 4.013797283172607,
      "learning_rate": 0.00014545454545454546,
      "loss": 5.931,
      "step": 21
    },
    {
      "epoch": 0.39111111111111113,
      "grad_norm": 2.85188364982605,
      "learning_rate": 0.00014181818181818184,
      "loss": 5.8464,
      "step": 22
    },
    {
      "epoch": 0.4088888888888889,
      "grad_norm": 2.7872464656829834,
      "learning_rate": 0.0001381818181818182,
      "loss": 5.943,
      "step": 23
    },
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 3.2645275592803955,
      "learning_rate": 0.00013454545454545455,
      "loss": 5.8657,
      "step": 24
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 2.8722269535064697,
      "learning_rate": 0.00013090909090909093,
      "loss": 5.7727,
      "step": 25
    },
    {
      "epoch": 0.4622222222222222,
      "grad_norm": 2.1603174209594727,
      "learning_rate": 0.00012727272727272728,
      "loss": 5.8712,
      "step": 26
    },
    {
      "epoch": 0.48,
      "grad_norm": 2.783595561981201,
      "learning_rate": 0.00012363636363636364,
      "loss": 5.9149,
      "step": 27
    },
    {
      "epoch": 0.49777777777777776,
      "grad_norm": 2.2030014991760254,
      "learning_rate": 0.00012,
      "loss": 5.8502,
      "step": 28
    },
    {
      "epoch": 0.5155555555555555,
      "grad_norm": 2.821263074874878,
      "learning_rate": 0.00011636363636363636,
      "loss": 5.8471,
      "step": 29
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 4.963853359222412,
      "learning_rate": 0.00011272727272727272,
      "loss": 5.9404,
      "step": 30
    },
    {
      "epoch": 0.5511111111111111,
      "grad_norm": 2.6349852085113525,
      "learning_rate": 0.00010909090909090909,
      "loss": 5.8419,
      "step": 31
    },
    {
      "epoch": 0.5688888888888889,
      "grad_norm": 2.6861917972564697,
      "learning_rate": 0.00010545454545454545,
      "loss": 5.7972,
      "step": 32
    },
    {
      "epoch": 0.5866666666666667,
      "grad_norm": 2.8622891902923584,
      "learning_rate": 0.00010181818181818181,
      "loss": 5.7338,
      "step": 33
    },
    {
      "epoch": 0.6044444444444445,
      "grad_norm": 2.2102324962615967,
      "learning_rate": 9.818181818181818e-05,
      "loss": 5.7475,
      "step": 34
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 2.9417433738708496,
      "learning_rate": 9.454545454545455e-05,
      "loss": 5.7562,
      "step": 35
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.533151388168335,
      "learning_rate": 9.090909090909092e-05,
      "loss": 5.7702,
      "step": 36
    },
    {
      "epoch": 0.6577777777777778,
      "grad_norm": 2.4525845050811768,
      "learning_rate": 8.727272727272727e-05,
      "loss": 5.7764,
      "step": 37
    },
    {
      "epoch": 0.6755555555555556,
      "grad_norm": 3.402923107147217,
      "learning_rate": 8.363636363636364e-05,
      "loss": 5.9145,
      "step": 38
    },
    {
      "epoch": 0.6933333333333334,
      "grad_norm": 3.261005163192749,
      "learning_rate": 8e-05,
      "loss": 5.7848,
      "step": 39
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 2.244154930114746,
      "learning_rate": 7.636363636363637e-05,
      "loss": 5.7873,
      "step": 40
    },
    {
      "epoch": 0.7288888888888889,
      "grad_norm": 3.457752227783203,
      "learning_rate": 7.272727272727273e-05,
      "loss": 5.8139,
      "step": 41
    },
    {
      "epoch": 0.7466666666666667,
      "grad_norm": 2.3376035690307617,
      "learning_rate": 6.90909090909091e-05,
      "loss": 5.7564,
      "step": 42
    },
    {
      "epoch": 0.7644444444444445,
      "grad_norm": 3.8495278358459473,
      "learning_rate": 6.545454545454546e-05,
      "loss": 5.6566,
      "step": 43
    },
    {
      "epoch": 0.7822222222222223,
      "grad_norm": 2.349485158920288,
      "learning_rate": 6.181818181818182e-05,
      "loss": 5.7529,
      "step": 44
    },
    {
      "epoch": 0.8,
      "grad_norm": 2.8913824558258057,
      "learning_rate": 5.818181818181818e-05,
      "loss": 5.706,
      "step": 45
    },
    {
      "epoch": 0.8177777777777778,
      "grad_norm": 3.932647705078125,
      "learning_rate": 5.4545454545454546e-05,
      "loss": 5.8259,
      "step": 46
    },
    {
      "epoch": 0.8355555555555556,
      "grad_norm": 2.2334136962890625,
      "learning_rate": 5.090909090909091e-05,
      "loss": 5.7211,
      "step": 47
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 1.9286762475967407,
      "learning_rate": 4.7272727272727275e-05,
      "loss": 5.6765,
      "step": 48
    },
    {
      "epoch": 0.8711111111111111,
      "grad_norm": 2.598808526992798,
      "learning_rate": 4.3636363636363636e-05,
      "loss": 5.7905,
      "step": 49
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 2.2895076274871826,
      "learning_rate": 4e-05,
      "loss": 5.6579,
      "step": 50
    },
    {
      "epoch": 0.9066666666666666,
      "grad_norm": 3.7514963150024414,
      "learning_rate": 3.6363636363636364e-05,
      "loss": 5.734,
      "step": 51
    },
    {
      "epoch": 0.9244444444444444,
      "grad_norm": 2.71718430519104,
      "learning_rate": 3.272727272727273e-05,
      "loss": 5.6998,
      "step": 52
    },
    {
      "epoch": 0.9422222222222222,
      "grad_norm": 1.9475185871124268,
      "learning_rate": 2.909090909090909e-05,
      "loss": 5.6739,
      "step": 53
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.6652722358703613,
      "learning_rate": 2.5454545454545454e-05,
      "loss": 5.8915,
      "step": 54
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 2.292740821838379,
      "learning_rate": 2.1818181818181818e-05,
      "loss": 5.7107,
      "step": 55
    },
    {
      "epoch": 0.9955555555555555,
      "grad_norm": 2.497856855392456,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 5.6296,
      "step": 56
    },
    {
      "epoch": 1.0,
      "grad_norm": 4.55602502822876,
      "learning_rate": 1.4545454545454545e-05,
      "loss": 5.5288,
      "step": 57
    },
    {
      "epoch": 1.0177777777777777,
      "grad_norm": 2.530329704284668,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 5.3935,
      "step": 58
    },
    {
      "epoch": 1.0355555555555556,
      "grad_norm": 2.5937700271606445,
      "learning_rate": 7.272727272727272e-06,
      "loss": 5.3327,
      "step": 59
    },
    {
      "epoch": 1.0533333333333332,
      "grad_norm": 2.1082897186279297,
      "learning_rate": 3.636363636363636e-06,
      "loss": 5.298,
      "step": 60
    }
  ],
  "logging_steps": 1,
  "max_steps": 60,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 401136498706944.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}