{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.056338028169014,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014084507042253521,
      "grad_norm": 5.285252094268799,
      "learning_rate": 1e-05,
      "loss": 12.7199,
      "step": 1
    },
    {
      "epoch": 0.014084507042253521,
      "eval_loss": 6.275448799133301,
      "eval_runtime": 9.4464,
      "eval_samples_per_second": 6.352,
      "eval_steps_per_second": 0.847,
      "step": 1
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 5.595484733581543,
      "learning_rate": 2e-05,
      "loss": 11.4639,
      "step": 2
    },
    {
      "epoch": 0.04225352112676056,
      "grad_norm": 4.9379425048828125,
      "learning_rate": 3e-05,
      "loss": 12.1198,
      "step": 3
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 5.559077262878418,
      "learning_rate": 4e-05,
      "loss": 12.8959,
      "step": 4
    },
    {
      "epoch": 0.07042253521126761,
      "grad_norm": 6.555881023406982,
      "learning_rate": 5e-05,
      "loss": 11.8686,
      "step": 5
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": 7.449399948120117,
      "learning_rate": 6e-05,
      "loss": 12.5061,
      "step": 6
    },
    {
      "epoch": 0.09859154929577464,
      "grad_norm": 7.8671722412109375,
      "learning_rate": 7e-05,
      "loss": 12.7458,
      "step": 7
    },
    {
      "epoch": 0.11267605633802817,
      "grad_norm": 8.257889747619629,
      "learning_rate": 8e-05,
      "loss": 11.8244,
      "step": 8
    },
    {
      "epoch": 0.1267605633802817,
      "grad_norm": 8.127012252807617,
      "learning_rate": 9e-05,
      "loss": 9.5607,
      "step": 9
    },
    {
      "epoch": 0.1267605633802817,
      "eval_loss": 4.54133939743042,
      "eval_runtime": 9.448,
      "eval_samples_per_second": 6.351,
      "eval_steps_per_second": 0.847,
      "step": 9
    },
    {
      "epoch": 0.14084507042253522,
      "grad_norm": 8.534059524536133,
      "learning_rate": 0.0001,
      "loss": 9.4819,
      "step": 10
    },
    {
      "epoch": 0.15492957746478872,
      "grad_norm": 8.69261360168457,
      "learning_rate": 9.99695413509548e-05,
      "loss": 7.5689,
      "step": 11
    },
    {
      "epoch": 0.16901408450704225,
      "grad_norm": 9.661815643310547,
      "learning_rate": 9.987820251299122e-05,
      "loss": 7.8439,
      "step": 12
    },
    {
      "epoch": 0.18309859154929578,
      "grad_norm": 6.753230571746826,
      "learning_rate": 9.972609476841367e-05,
      "loss": 5.1035,
      "step": 13
    },
    {
      "epoch": 0.19718309859154928,
      "grad_norm": 6.40622091293335,
      "learning_rate": 9.951340343707852e-05,
      "loss": 4.4567,
      "step": 14
    },
    {
      "epoch": 0.2112676056338028,
      "grad_norm": 5.068661212921143,
      "learning_rate": 9.924038765061042e-05,
      "loss": 3.2579,
      "step": 15
    },
    {
      "epoch": 0.22535211267605634,
      "grad_norm": 6.61514949798584,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.616,
      "step": 16
    },
    {
      "epoch": 0.23943661971830985,
      "grad_norm": 8.611897468566895,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.2972,
      "step": 17
    },
    {
      "epoch": 0.2535211267605634,
      "grad_norm": 7.323372840881348,
      "learning_rate": 9.806308479691595e-05,
      "loss": 3.2693,
      "step": 18
    },
    {
      "epoch": 0.2535211267605634,
      "eval_loss": 0.8134925365447998,
      "eval_runtime": 9.445,
      "eval_samples_per_second": 6.353,
      "eval_steps_per_second": 0.847,
      "step": 18
    },
    {
      "epoch": 0.2676056338028169,
      "grad_norm": 7.8986287117004395,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.921,
      "step": 19
    },
    {
      "epoch": 0.28169014084507044,
      "grad_norm": 4.541922092437744,
      "learning_rate": 9.698463103929542e-05,
      "loss": 1.7129,
      "step": 20
    },
    {
      "epoch": 0.29577464788732394,
      "grad_norm": 5.23263692855835,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.5027,
      "step": 21
    },
    {
      "epoch": 0.30985915492957744,
      "grad_norm": 4.416317462921143,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.8677,
      "step": 22
    },
    {
      "epoch": 0.323943661971831,
      "grad_norm": 7.6834845542907715,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.7007,
      "step": 23
    },
    {
      "epoch": 0.3380281690140845,
      "grad_norm": 4.361001491546631,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.1304,
      "step": 24
    },
    {
      "epoch": 0.352112676056338,
      "grad_norm": 5.443579196929932,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.0861,
      "step": 25
    },
    {
      "epoch": 0.36619718309859156,
      "grad_norm": 6.655890464782715,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.2659,
      "step": 26
    },
    {
      "epoch": 0.38028169014084506,
      "grad_norm": 6.326033592224121,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.9785,
      "step": 27
    },
    {
      "epoch": 0.38028169014084506,
      "eval_loss": 0.3746188282966614,
      "eval_runtime": 9.4749,
      "eval_samples_per_second": 6.333,
      "eval_steps_per_second": 0.844,
      "step": 27
    },
    {
      "epoch": 0.39436619718309857,
      "grad_norm": 3.373551607131958,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.7874,
      "step": 28
    },
    {
      "epoch": 0.4084507042253521,
      "grad_norm": 2.853113889694214,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.6588,
      "step": 29
    },
    {
      "epoch": 0.4225352112676056,
      "grad_norm": 6.440278053283691,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.1987,
      "step": 30
    },
    {
      "epoch": 0.43661971830985913,
      "grad_norm": 3.5188775062561035,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.8453,
      "step": 31
    },
    {
      "epoch": 0.4507042253521127,
      "grad_norm": 2.3258731365203857,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.687,
      "step": 32
    },
    {
      "epoch": 0.4647887323943662,
      "grad_norm": 2.443490743637085,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.5889,
      "step": 33
    },
    {
      "epoch": 0.4788732394366197,
      "grad_norm": 2.5021681785583496,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.4796,
      "step": 34
    },
    {
      "epoch": 0.49295774647887325,
      "grad_norm": 1.7857712507247925,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.5177,
      "step": 35
    },
    {
      "epoch": 0.5070422535211268,
      "grad_norm": 2.7204785346984863,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.3911,
      "step": 36
    },
    {
      "epoch": 0.5070422535211268,
      "eval_loss": 0.29374733567237854,
      "eval_runtime": 9.4415,
      "eval_samples_per_second": 6.355,
      "eval_steps_per_second": 0.847,
      "step": 36
    },
    {
      "epoch": 0.5211267605633803,
      "grad_norm": 2.436917304992676,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.4892,
      "step": 37
    },
    {
      "epoch": 0.5352112676056338,
      "grad_norm": 2.354090452194214,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.4712,
      "step": 38
    },
    {
      "epoch": 0.5492957746478874,
      "grad_norm": 2.533153533935547,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.7417,
      "step": 39
    },
    {
      "epoch": 0.5633802816901409,
      "grad_norm": 3.5074594020843506,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.7935,
      "step": 40
    },
    {
      "epoch": 0.5774647887323944,
      "grad_norm": 4.164097309112549,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.8672,
      "step": 41
    },
    {
      "epoch": 0.5915492957746479,
      "grad_norm": 1.9988298416137695,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.5798,
      "step": 42
    },
    {
      "epoch": 0.6056338028169014,
      "grad_norm": 3.0973868370056152,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.5251,
      "step": 43
    },
    {
      "epoch": 0.6197183098591549,
      "grad_norm": 2.183314561843872,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.5634,
      "step": 44
    },
    {
      "epoch": 0.6338028169014085,
      "grad_norm": 2.6934773921966553,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.5318,
      "step": 45
    },
    {
      "epoch": 0.6338028169014085,
      "eval_loss": 0.27166080474853516,
      "eval_runtime": 9.4396,
      "eval_samples_per_second": 6.356,
      "eval_steps_per_second": 0.847,
      "step": 45
    },
    {
      "epoch": 0.647887323943662,
      "grad_norm": 1.339059829711914,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.2873,
      "step": 46
    },
    {
      "epoch": 0.6619718309859155,
      "grad_norm": 2.191518545150757,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.4224,
      "step": 47
    },
    {
      "epoch": 0.676056338028169,
      "grad_norm": 1.743062973022461,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.4417,
      "step": 48
    },
    {
      "epoch": 0.6901408450704225,
      "grad_norm": 4.4744486808776855,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.4353,
      "step": 49
    },
    {
      "epoch": 0.704225352112676,
      "grad_norm": 2.906970500946045,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.6858,
      "step": 50
    },
    {
      "epoch": 0.7183098591549296,
      "grad_norm": 2.466736316680908,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.7071,
      "step": 51
    },
    {
      "epoch": 0.7323943661971831,
      "grad_norm": 3.520155191421509,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.6728,
      "step": 52
    },
    {
      "epoch": 0.7464788732394366,
      "grad_norm": 2.4411091804504395,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.5243,
      "step": 53
    },
    {
      "epoch": 0.7605633802816901,
      "grad_norm": 3.1338558197021484,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.5815,
      "step": 54
    },
    {
      "epoch": 0.7605633802816901,
      "eval_loss": 0.2808348834514618,
      "eval_runtime": 9.4515,
      "eval_samples_per_second": 6.348,
      "eval_steps_per_second": 0.846,
      "step": 54
    },
    {
      "epoch": 0.7746478873239436,
      "grad_norm": 1.9054027795791626,
      "learning_rate": 5e-05,
      "loss": 0.2372,
      "step": 55
    },
    {
      "epoch": 0.7887323943661971,
      "grad_norm": 3.4146244525909424,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.4923,
      "step": 56
    },
    {
      "epoch": 0.8028169014084507,
      "grad_norm": 3.7887396812438965,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.617,
      "step": 57
    },
    {
      "epoch": 0.8169014084507042,
      "grad_norm": 2.911750078201294,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.7843,
      "step": 58
    },
    {
      "epoch": 0.8309859154929577,
      "grad_norm": 2.115206003189087,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.3456,
      "step": 59
    },
    {
      "epoch": 0.8450704225352113,
      "grad_norm": 2.2854878902435303,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.3661,
      "step": 60
    },
    {
      "epoch": 0.8591549295774648,
      "grad_norm": 2.277642011642456,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.3269,
      "step": 61
    },
    {
      "epoch": 0.8732394366197183,
      "grad_norm": 1.5300718545913696,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.419,
      "step": 62
    },
    {
      "epoch": 0.8873239436619719,
      "grad_norm": 1.847389578819275,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.3511,
      "step": 63
    },
    {
      "epoch": 0.8873239436619719,
      "eval_loss": 0.24202439188957214,
      "eval_runtime": 9.4451,
      "eval_samples_per_second": 6.353,
      "eval_steps_per_second": 0.847,
      "step": 63
    },
    {
      "epoch": 0.9014084507042254,
      "grad_norm": 3.6181552410125732,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.563,
      "step": 64
    },
    {
      "epoch": 0.9154929577464789,
      "grad_norm": 1.4496983289718628,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.3528,
      "step": 65
    },
    {
      "epoch": 0.9295774647887324,
      "grad_norm": 1.217552900314331,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.2035,
      "step": 66
    },
    {
      "epoch": 0.9436619718309859,
      "grad_norm": 2.433314800262451,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.4006,
      "step": 67
    },
    {
      "epoch": 0.9577464788732394,
      "grad_norm": 1.664299488067627,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.4371,
      "step": 68
    },
    {
      "epoch": 0.971830985915493,
      "grad_norm": 3.6762967109680176,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.5866,
      "step": 69
    },
    {
      "epoch": 0.9859154929577465,
      "grad_norm": 1.7839586734771729,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.3675,
      "step": 70
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.3271634578704834,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.2743,
      "step": 71
    },
    {
      "epoch": 1.0140845070422535,
      "grad_norm": 1.5560985803604126,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.3647,
      "step": 72
    },
    {
      "epoch": 1.0140845070422535,
      "eval_loss": 0.22708940505981445,
      "eval_runtime": 9.4393,
      "eval_samples_per_second": 6.356,
      "eval_steps_per_second": 0.848,
      "step": 72
    },
    {
      "epoch": 1.028169014084507,
      "grad_norm": 2.105374813079834,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.5075,
      "step": 73
    },
    {
      "epoch": 1.0422535211267605,
      "grad_norm": 2.403916358947754,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.7175,
      "step": 74
    },
    {
      "epoch": 1.056338028169014,
      "grad_norm": 2.558152675628662,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.2165,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 9.497940581154816e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}