{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11235955056179775,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00149812734082397,
      "grad_norm": 33.35292434692383,
      "learning_rate": 1e-05,
      "loss": 8.4892,
      "step": 1
    },
    {
      "epoch": 0.00149812734082397,
      "eval_loss": 8.506402969360352,
      "eval_runtime": 5.0512,
      "eval_samples_per_second": 111.261,
      "eval_steps_per_second": 14.056,
      "step": 1
    },
    {
      "epoch": 0.00299625468164794,
      "grad_norm": 29.205915451049805,
      "learning_rate": 2e-05,
      "loss": 8.7652,
      "step": 2
    },
    {
      "epoch": 0.0044943820224719105,
      "grad_norm": 38.662696838378906,
      "learning_rate": 3e-05,
      "loss": 8.329,
      "step": 3
    },
    {
      "epoch": 0.00599250936329588,
      "grad_norm": 29.221637725830078,
      "learning_rate": 4e-05,
      "loss": 8.5478,
      "step": 4
    },
    {
      "epoch": 0.00749063670411985,
      "grad_norm": 31.94698143005371,
      "learning_rate": 5e-05,
      "loss": 8.2514,
      "step": 5
    },
    {
      "epoch": 0.008988764044943821,
      "grad_norm": 27.73323631286621,
      "learning_rate": 6e-05,
      "loss": 8.2959,
      "step": 6
    },
    {
      "epoch": 0.010486891385767791,
      "grad_norm": 24.731342315673828,
      "learning_rate": 7e-05,
      "loss": 8.153,
      "step": 7
    },
    {
      "epoch": 0.01198501872659176,
      "grad_norm": 24.460359573364258,
      "learning_rate": 8e-05,
      "loss": 8.1005,
      "step": 8
    },
    {
      "epoch": 0.01348314606741573,
      "grad_norm": 23.165380477905273,
      "learning_rate": 9e-05,
      "loss": 7.4285,
      "step": 9
    },
    {
      "epoch": 0.01348314606741573,
      "eval_loss": 7.255934238433838,
      "eval_runtime": 5.0553,
      "eval_samples_per_second": 111.171,
      "eval_steps_per_second": 14.045,
      "step": 9
    },
    {
      "epoch": 0.0149812734082397,
      "grad_norm": 18.089080810546875,
      "learning_rate": 0.0001,
      "loss": 7.751,
      "step": 10
    },
    {
      "epoch": 0.01647940074906367,
      "grad_norm": 16.641746520996094,
      "learning_rate": 9.99695413509548e-05,
      "loss": 7.235,
      "step": 11
    },
    {
      "epoch": 0.017977528089887642,
      "grad_norm": 14.398178100585938,
      "learning_rate": 9.987820251299122e-05,
      "loss": 6.8906,
      "step": 12
    },
    {
      "epoch": 0.01947565543071161,
      "grad_norm": 11.744943618774414,
      "learning_rate": 9.972609476841367e-05,
      "loss": 6.6012,
      "step": 13
    },
    {
      "epoch": 0.020973782771535582,
      "grad_norm": 10.035268783569336,
      "learning_rate": 9.951340343707852e-05,
      "loss": 6.7429,
      "step": 14
    },
    {
      "epoch": 0.02247191011235955,
      "grad_norm": 10.172917366027832,
      "learning_rate": 9.924038765061042e-05,
      "loss": 6.1403,
      "step": 15
    },
    {
      "epoch": 0.02397003745318352,
      "grad_norm": 9.985401153564453,
      "learning_rate": 9.890738003669029e-05,
      "loss": 5.924,
      "step": 16
    },
    {
      "epoch": 0.02546816479400749,
      "grad_norm": 8.237224578857422,
      "learning_rate": 9.851478631379982e-05,
      "loss": 6.4427,
      "step": 17
    },
    {
      "epoch": 0.02696629213483146,
      "grad_norm": 8.345848083496094,
      "learning_rate": 9.806308479691595e-05,
      "loss": 6.1714,
      "step": 18
    },
    {
      "epoch": 0.02696629213483146,
      "eval_loss": 6.026069164276123,
      "eval_runtime": 5.0492,
      "eval_samples_per_second": 111.304,
      "eval_steps_per_second": 14.062,
      "step": 18
    },
    {
      "epoch": 0.02846441947565543,
      "grad_norm": 6.646966457366943,
      "learning_rate": 9.755282581475769e-05,
      "loss": 6.3546,
      "step": 19
    },
    {
      "epoch": 0.0299625468164794,
      "grad_norm": 7.407896518707275,
      "learning_rate": 9.698463103929542e-05,
      "loss": 5.7212,
      "step": 20
    },
    {
      "epoch": 0.03146067415730337,
      "grad_norm": 6.867751598358154,
      "learning_rate": 9.635919272833938e-05,
      "loss": 5.8571,
      "step": 21
    },
    {
      "epoch": 0.03295880149812734,
      "grad_norm": 5.814306259155273,
      "learning_rate": 9.567727288213005e-05,
      "loss": 6.1518,
      "step": 22
    },
    {
      "epoch": 0.03445692883895131,
      "grad_norm": 6.592785835266113,
      "learning_rate": 9.493970231495835e-05,
      "loss": 6.6262,
      "step": 23
    },
    {
      "epoch": 0.035955056179775284,
      "grad_norm": 7.892642974853516,
      "learning_rate": 9.414737964294636e-05,
      "loss": 5.5888,
      "step": 24
    },
    {
      "epoch": 0.03745318352059925,
      "grad_norm": 5.857728958129883,
      "learning_rate": 9.330127018922194e-05,
      "loss": 5.7918,
      "step": 25
    },
    {
      "epoch": 0.03895131086142322,
      "grad_norm": 5.877769470214844,
      "learning_rate": 9.24024048078213e-05,
      "loss": 5.406,
      "step": 26
    },
    {
      "epoch": 0.04044943820224719,
      "grad_norm": 5.7603230476379395,
      "learning_rate": 9.145187862775209e-05,
      "loss": 5.5544,
      "step": 27
    },
    {
      "epoch": 0.04044943820224719,
      "eval_loss": 5.330251216888428,
      "eval_runtime": 5.1379,
      "eval_samples_per_second": 109.384,
      "eval_steps_per_second": 13.819,
      "step": 27
    },
    {
      "epoch": 0.041947565543071164,
      "grad_norm": 5.099091053009033,
      "learning_rate": 9.045084971874738e-05,
      "loss": 5.7185,
      "step": 28
    },
    {
      "epoch": 0.04344569288389513,
      "grad_norm": 4.921545505523682,
      "learning_rate": 8.940053768033609e-05,
      "loss": 5.081,
      "step": 29
    },
    {
      "epoch": 0.0449438202247191,
      "grad_norm": 4.545036315917969,
      "learning_rate": 8.83022221559489e-05,
      "loss": 5.3674,
      "step": 30
    },
    {
      "epoch": 0.04644194756554307,
      "grad_norm": 4.012330532073975,
      "learning_rate": 8.715724127386972e-05,
      "loss": 5.0857,
      "step": 31
    },
    {
      "epoch": 0.04794007490636704,
      "grad_norm": 4.733462810516357,
      "learning_rate": 8.596699001693255e-05,
      "loss": 5.599,
      "step": 32
    },
    {
      "epoch": 0.04943820224719101,
      "grad_norm": 4.145115375518799,
      "learning_rate": 8.473291852294987e-05,
      "loss": 4.7403,
      "step": 33
    },
    {
      "epoch": 0.05093632958801498,
      "grad_norm": 5.177260875701904,
      "learning_rate": 8.345653031794292e-05,
      "loss": 4.9125,
      "step": 34
    },
    {
      "epoch": 0.052434456928838954,
      "grad_norm": 4.307314872741699,
      "learning_rate": 8.213938048432697e-05,
      "loss": 4.8608,
      "step": 35
    },
    {
      "epoch": 0.05393258426966292,
      "grad_norm": 4.051609039306641,
      "learning_rate": 8.07830737662829e-05,
      "loss": 5.103,
      "step": 36
    },
    {
      "epoch": 0.05393258426966292,
      "eval_loss": 4.865622520446777,
      "eval_runtime": 5.0494,
      "eval_samples_per_second": 111.3,
      "eval_steps_per_second": 14.061,
      "step": 36
    },
    {
      "epoch": 0.05543071161048689,
      "grad_norm": 3.6555047035217285,
      "learning_rate": 7.938926261462366e-05,
      "loss": 5.346,
      "step": 37
    },
    {
      "epoch": 0.05692883895131086,
      "grad_norm": 3.7957916259765625,
      "learning_rate": 7.795964517353735e-05,
      "loss": 4.6881,
      "step": 38
    },
    {
      "epoch": 0.058426966292134834,
      "grad_norm": 3.4084856510162354,
      "learning_rate": 7.649596321166024e-05,
      "loss": 4.8244,
      "step": 39
    },
    {
      "epoch": 0.0599250936329588,
      "grad_norm": 3.9070608615875244,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.5502,
      "step": 40
    },
    {
      "epoch": 0.06142322097378277,
      "grad_norm": 3.6457884311676025,
      "learning_rate": 7.347357813929454e-05,
      "loss": 4.9674,
      "step": 41
    },
    {
      "epoch": 0.06292134831460675,
      "grad_norm": 3.537919759750366,
      "learning_rate": 7.191855733945387e-05,
      "loss": 4.5994,
      "step": 42
    },
    {
      "epoch": 0.06441947565543071,
      "grad_norm": 3.2818875312805176,
      "learning_rate": 7.033683215379002e-05,
      "loss": 4.24,
      "step": 43
    },
    {
      "epoch": 0.06591760299625468,
      "grad_norm": 3.0351362228393555,
      "learning_rate": 6.873032967079561e-05,
      "loss": 4.6635,
      "step": 44
    },
    {
      "epoch": 0.06741573033707865,
      "grad_norm": 2.9568066596984863,
      "learning_rate": 6.710100716628344e-05,
      "loss": 4.6542,
      "step": 45
    },
    {
      "epoch": 0.06741573033707865,
      "eval_loss": 4.533878326416016,
      "eval_runtime": 5.0476,
      "eval_samples_per_second": 111.34,
      "eval_steps_per_second": 14.066,
      "step": 45
    },
    {
      "epoch": 0.06891385767790262,
      "grad_norm": 2.7085890769958496,
      "learning_rate": 6.545084971874738e-05,
      "loss": 4.5054,
      "step": 46
    },
    {
      "epoch": 0.07041198501872659,
      "grad_norm": 3.3949663639068604,
      "learning_rate": 6.378186779084995e-05,
      "loss": 4.853,
      "step": 47
    },
    {
      "epoch": 0.07191011235955057,
      "grad_norm": 2.987119436264038,
      "learning_rate": 6.209609477998338e-05,
      "loss": 4.7567,
      "step": 48
    },
    {
      "epoch": 0.07340823970037454,
      "grad_norm": 2.469896078109741,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 4.2099,
      "step": 49
    },
    {
      "epoch": 0.0749063670411985,
      "grad_norm": 2.4648237228393555,
      "learning_rate": 5.868240888334653e-05,
      "loss": 4.3734,
      "step": 50
    },
    {
      "epoch": 0.07640449438202247,
      "grad_norm": 2.5853934288024902,
      "learning_rate": 5.695865504800327e-05,
      "loss": 4.313,
      "step": 51
    },
    {
      "epoch": 0.07790262172284644,
      "grad_norm": 2.9297568798065186,
      "learning_rate": 5.522642316338268e-05,
      "loss": 4.6197,
      "step": 52
    },
    {
      "epoch": 0.07940074906367041,
      "grad_norm": 2.545381546020508,
      "learning_rate": 5.348782368720626e-05,
      "loss": 4.0591,
      "step": 53
    },
    {
      "epoch": 0.08089887640449438,
      "grad_norm": 2.857722520828247,
      "learning_rate": 5.174497483512506e-05,
      "loss": 4.5878,
      "step": 54
    },
    {
      "epoch": 0.08089887640449438,
      "eval_loss": 4.307217597961426,
      "eval_runtime": 5.1062,
      "eval_samples_per_second": 110.061,
      "eval_steps_per_second": 13.905,
      "step": 54
    },
    {
      "epoch": 0.08239700374531835,
      "grad_norm": 2.407810688018799,
      "learning_rate": 5e-05,
      "loss": 4.3392,
      "step": 55
    },
    {
      "epoch": 0.08389513108614233,
      "grad_norm": 2.570552110671997,
      "learning_rate": 4.825502516487497e-05,
      "loss": 4.4584,
      "step": 56
    },
    {
      "epoch": 0.0853932584269663,
      "grad_norm": 2.6279847621917725,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 4.425,
      "step": 57
    },
    {
      "epoch": 0.08689138576779026,
      "grad_norm": 3.007448434829712,
      "learning_rate": 4.477357683661734e-05,
      "loss": 4.5935,
      "step": 58
    },
    {
      "epoch": 0.08838951310861423,
      "grad_norm": 2.377514123916626,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 3.9613,
      "step": 59
    },
    {
      "epoch": 0.0898876404494382,
      "grad_norm": 2.6137871742248535,
      "learning_rate": 4.131759111665349e-05,
      "loss": 4.1664,
      "step": 60
    },
    {
      "epoch": 0.09138576779026217,
      "grad_norm": 2.346526861190796,
      "learning_rate": 3.960441545911204e-05,
      "loss": 4.3429,
      "step": 61
    },
    {
      "epoch": 0.09288389513108614,
      "grad_norm": 2.3919084072113037,
      "learning_rate": 3.790390522001662e-05,
      "loss": 4.3198,
      "step": 62
    },
    {
      "epoch": 0.09438202247191012,
      "grad_norm": 2.6010396480560303,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 4.4285,
      "step": 63
    },
    {
      "epoch": 0.09438202247191012,
      "eval_loss": 4.148770809173584,
      "eval_runtime": 5.0464,
      "eval_samples_per_second": 111.367,
      "eval_steps_per_second": 14.07,
      "step": 63
    },
    {
      "epoch": 0.09588014981273409,
      "grad_norm": 2.1853432655334473,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 4.0948,
      "step": 64
    },
    {
      "epoch": 0.09737827715355805,
      "grad_norm": 2.2798073291778564,
      "learning_rate": 3.289899283371657e-05,
      "loss": 4.1717,
      "step": 65
    },
    {
      "epoch": 0.09887640449438202,
      "grad_norm": 2.386640787124634,
      "learning_rate": 3.12696703292044e-05,
      "loss": 3.9134,
      "step": 66
    },
    {
      "epoch": 0.10037453183520599,
      "grad_norm": 2.6383981704711914,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 4.3411,
      "step": 67
    },
    {
      "epoch": 0.10187265917602996,
      "grad_norm": 2.1975576877593994,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 4.1277,
      "step": 68
    },
    {
      "epoch": 0.10337078651685393,
      "grad_norm": 2.150082588195801,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 4.0219,
      "step": 69
    },
    {
      "epoch": 0.10486891385767791,
      "grad_norm": 2.762874126434326,
      "learning_rate": 2.500000000000001e-05,
      "loss": 4.2591,
      "step": 70
    },
    {
      "epoch": 0.10636704119850188,
      "grad_norm": 1.973354458808899,
      "learning_rate": 2.350403678833976e-05,
      "loss": 3.8811,
      "step": 71
    },
    {
      "epoch": 0.10786516853932585,
      "grad_norm": 2.2953357696533203,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 4.0632,
      "step": 72
    },
    {
      "epoch": 0.10786516853932585,
      "eval_loss": 4.0451812744140625,
      "eval_runtime": 5.0459,
      "eval_samples_per_second": 111.377,
      "eval_steps_per_second": 14.071,
      "step": 72
    },
    {
      "epoch": 0.10936329588014981,
      "grad_norm": 2.3707635402679443,
      "learning_rate": 2.061073738537635e-05,
      "loss": 4.1333,
      "step": 73
    },
    {
      "epoch": 0.11086142322097378,
      "grad_norm": 2.294806480407715,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 4.0764,
      "step": 74
    },
    {
      "epoch": 0.11235955056179775,
      "grad_norm": 2.1599864959716797,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 3.7799,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 20362140057600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}