{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5934065934065934,
  "eval_steps": 500,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 0.8349836468696594,
      "learning_rate": 0.0,
      "loss": 0.9434,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 0.8700987696647644,
      "learning_rate": 4e-05,
      "loss": 0.9905,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.9241365194320679,
      "learning_rate": 8e-05,
      "loss": 0.9438,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 0.9019892811775208,
      "learning_rate": 0.00012,
      "loss": 0.9216,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.8872910141944885,
      "learning_rate": 0.00016,
      "loss": 0.9374,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.5874530076980591,
      "learning_rate": 0.0002,
      "loss": 0.7673,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5062956809997559,
      "learning_rate": 0.00019955654101995565,
      "loss": 0.8011,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.5953829288482666,
      "learning_rate": 0.00019911308203991133,
      "loss": 0.8455,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.5616072416305542,
      "learning_rate": 0.00019866962305986697,
      "loss": 0.8265,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.49180087447166443,
      "learning_rate": 0.00019822616407982261,
      "loss": 0.8561,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.42030951380729675,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.8796,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.3004567325115204,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.8636,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.2698984444141388,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.718,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.25445133447647095,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.7235,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.22418756783008575,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.688,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.2096303105354309,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.7267,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.3029191195964813,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.7763,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.2644464075565338,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.7618,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.2536560893058777,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.7999,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.24718916416168213,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.752,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.2625150680541992,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.736,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.32164040207862854,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.7043,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3981449604034424,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.7057,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3817313015460968,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.7413,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.29256680607795715,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.693,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.27523350715637207,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.6474,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.23511967062950134,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.6519,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.2961374819278717,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.6426,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.2760772407054901,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.7388,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.2285313606262207,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.7756,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.2657061517238617,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.7275,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.22572828829288483,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.6793,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.26335304975509644,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.7131,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.25231942534446716,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.7715,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2437426745891571,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.7094,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.28558826446533203,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.6937,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.2915894687175751,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.7238,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.25342074036598206,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.7323,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.22744007408618927,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.703,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.25383231043815613,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.7093,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.2194337695837021,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.7367,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.32021859288215637,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.6652,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.2328304797410965,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.7016,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.24166613817214966,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.6717,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2733803391456604,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.6979,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.2689957320690155,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.6977,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.2698104977607727,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.723,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.25856417417526245,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.723,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.22988826036453247,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.7356,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.24859416484832764,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.6671,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.24891626834869385,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.6628,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.22740386426448822,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.6377,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.2636365294456482,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.6901,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2437390238046646,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.72,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.23658742010593414,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.7365,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.23923538625240326,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.706,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2877054512500763,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.7436,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.2839520573616028,
      "learning_rate": 0.000176940133037694,
      "loss": 0.6779,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.2308293879032135,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.6357,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.24402214586734772,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.7508,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.23816415667533875,
      "learning_rate": 0.000175609756097561,
      "loss": 0.7249,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.28321942687034607,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.7479,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.23680296540260315,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.6413,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.23129238188266754,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.6786,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.25140181183815,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.7167,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.27190810441970825,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.6267,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.23768772184848785,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.7397,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.2618238031864166,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.6987,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.24789907038211823,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.6223,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.2744330167770386,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.6964,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.23732465505599976,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.6524,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.2278261035680771,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.7437,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.24909941852092743,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.6955,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3007880449295044,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.625,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.2338089644908905,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.6843,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.27349653840065,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.6825,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.2793181836605072,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.6529,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.2612224221229553,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.6807,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.2740105986595154,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.6294,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.2226412147283554,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.6569,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.2254134714603424,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.6569,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.22373083233833313,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.6733,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.2485770583152771,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.6422,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.25764942169189453,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.6682,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.24047411978244781,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.7126,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.21252930164337158,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.7109,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.25431081652641296,
      "learning_rate": 0.000164079822616408,
      "loss": 0.6416,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.24909189343452454,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.6963,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.25534072518348694,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.7898,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.22847016155719757,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.6903,
      "step": 90
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.145108297405645e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}