{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.015539771612447514,
  "eval_steps": 50,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015696739002472236,
      "grad_norm": 0.4209878444671631,
      "learning_rate": 5e-05,
      "loss": 0.96,
      "step": 1
    },
    {
      "epoch": 0.00015696739002472236,
      "eval_loss": 1.059880018234253,
      "eval_runtime": 58.7176,
      "eval_samples_per_second": 45.693,
      "eval_steps_per_second": 22.855,
      "step": 1
    },
    {
      "epoch": 0.0003139347800494447,
      "grad_norm": 0.37363916635513306,
      "learning_rate": 0.0001,
      "loss": 0.7969,
      "step": 2
    },
    {
      "epoch": 0.0004709021700741671,
      "grad_norm": 0.31887054443359375,
      "learning_rate": 0.00015,
      "loss": 0.9958,
      "step": 3
    },
    {
      "epoch": 0.0006278695600988894,
      "grad_norm": 0.6505757570266724,
      "learning_rate": 0.0002,
      "loss": 1.4545,
      "step": 4
    },
    {
      "epoch": 0.0007848369501236119,
      "grad_norm": 0.338165819644928,
      "learning_rate": 0.00025,
      "loss": 0.8554,
      "step": 5
    },
    {
      "epoch": 0.0009418043401483342,
      "grad_norm": 0.6994407176971436,
      "learning_rate": 0.0003,
      "loss": 0.9343,
      "step": 6
    },
    {
      "epoch": 0.0010987717301730565,
      "grad_norm": 0.31736791133880615,
      "learning_rate": 0.00035,
      "loss": 0.7684,
      "step": 7
    },
    {
      "epoch": 0.0012557391201977789,
      "grad_norm": 0.42489951848983765,
      "learning_rate": 0.0004,
      "loss": 0.9331,
      "step": 8
    },
    {
      "epoch": 0.0014127065102225013,
      "grad_norm": 0.4670903980731964,
      "learning_rate": 0.00045000000000000004,
      "loss": 0.938,
      "step": 9
    },
    {
      "epoch": 0.0015696739002472237,
      "grad_norm": 0.6221330165863037,
      "learning_rate": 0.0005,
      "loss": 1.163,
      "step": 10
    },
    {
      "epoch": 0.001726641290271946,
      "grad_norm": 0.44136929512023926,
      "learning_rate": 0.0004998442655654946,
      "loss": 0.743,
      "step": 11
    },
    {
      "epoch": 0.0018836086802966683,
      "grad_norm": 0.4158223867416382,
      "learning_rate": 0.0004993772562876909,
      "loss": 0.7409,
      "step": 12
    },
    {
      "epoch": 0.0020405760703213907,
      "grad_norm": 0.6507619023323059,
      "learning_rate": 0.0004985995540019955,
      "loss": 0.7963,
      "step": 13
    },
    {
      "epoch": 0.002197543460346113,
      "grad_norm": 0.5717980861663818,
      "learning_rate": 0.0004975121276286136,
      "loss": 0.899,
      "step": 14
    },
    {
      "epoch": 0.0023545108503708356,
      "grad_norm": 0.6496816277503967,
      "learning_rate": 0.0004961163319653958,
      "loss": 0.9617,
      "step": 15
    },
    {
      "epoch": 0.0025114782403955578,
      "grad_norm": 0.4178118109703064,
      "learning_rate": 0.0004944139059999286,
      "loss": 0.6501,
      "step": 16
    },
    {
      "epoch": 0.00266844563042028,
      "grad_norm": 0.4809323251247406,
      "learning_rate": 0.000492406970742972,
      "loss": 1.1646,
      "step": 17
    },
    {
      "epoch": 0.0028254130204450026,
      "grad_norm": 0.34386783838272095,
      "learning_rate": 0.0004900980265859448,
      "loss": 0.6848,
      "step": 18
    },
    {
      "epoch": 0.002982380410469725,
      "grad_norm": 0.39839452505111694,
      "learning_rate": 0.0004874899501857477,
      "loss": 0.9252,
      "step": 19
    },
    {
      "epoch": 0.0031393478004944474,
      "grad_norm": 0.2926274836063385,
      "learning_rate": 0.00048458599088080736,
      "loss": 0.6852,
      "step": 20
    },
    {
      "epoch": 0.0032963151905191696,
      "grad_norm": 0.309630811214447,
      "learning_rate": 0.0004813897666428053,
      "loss": 0.7408,
      "step": 21
    },
    {
      "epoch": 0.003453282580543892,
      "grad_norm": 0.44346147775650024,
      "learning_rate": 0.00047790525956913543,
      "loss": 0.7721,
      "step": 22
    },
    {
      "epoch": 0.0036102499705686145,
      "grad_norm": 0.38101327419281006,
      "learning_rate": 0.0004741368109217071,
      "loss": 0.8934,
      "step": 23
    },
    {
      "epoch": 0.0037672173605933367,
      "grad_norm": 0.6885596513748169,
      "learning_rate": 0.00047008911571827283,
      "loss": 0.7099,
      "step": 24
    },
    {
      "epoch": 0.003924184750618059,
      "grad_norm": 0.4238623082637787,
      "learning_rate": 0.00046576721688302105,
      "loss": 0.6671,
      "step": 25
    },
    {
      "epoch": 0.0040811521406427815,
      "grad_norm": 0.4145318269729614,
      "learning_rate": 0.0004611764989637205,
      "loss": 0.907,
      "step": 26
    },
    {
      "epoch": 0.004238119530667504,
      "grad_norm": 0.47778183221817017,
      "learning_rate": 0.0004563226814232444,
      "loss": 0.9015,
      "step": 27
    },
    {
      "epoch": 0.004395086920692226,
      "grad_norm": 0.40440261363983154,
      "learning_rate": 0.0004512118115138315,
      "loss": 0.7177,
      "step": 28
    },
    {
      "epoch": 0.0045520543107169485,
      "grad_norm": 0.6247038841247559,
      "learning_rate": 0.0004458502567429631,
      "loss": 0.898,
      "step": 29
    },
    {
      "epoch": 0.004709021700741671,
      "grad_norm": 0.7316962480545044,
      "learning_rate": 0.00044024469694024196,
      "loss": 1.295,
      "step": 30
    },
    {
      "epoch": 0.004865989090766393,
      "grad_norm": 0.46687981486320496,
      "learning_rate": 0.00043440211593515554,
      "loss": 1.0014,
      "step": 31
    },
    {
      "epoch": 0.0050229564807911155,
      "grad_norm": 0.4061206877231598,
      "learning_rate": 0.0004283297928560951,
      "loss": 0.6779,
      "step": 32
    },
    {
      "epoch": 0.005179923870815838,
      "grad_norm": 0.4588050842285156,
      "learning_rate": 0.0004220352930614672,
      "loss": 0.8217,
      "step": 33
    },
    {
      "epoch": 0.00533689126084056,
      "grad_norm": 0.39541956782341003,
      "learning_rate": 0.00041552645871420013,
      "loss": 1.0593,
      "step": 34
    },
    {
      "epoch": 0.005493858650865283,
      "grad_norm": 0.32590246200561523,
      "learning_rate": 0.00040881139901138467,
      "loss": 0.5995,
      "step": 35
    },
    {
      "epoch": 0.005650826040890005,
      "grad_norm": 0.34778353571891785,
      "learning_rate": 0.00040189848008122475,
      "loss": 0.8404,
      "step": 36
    },
    {
      "epoch": 0.005807793430914728,
      "grad_norm": 0.43329522013664246,
      "learning_rate": 0.00039479631455988334,
      "loss": 0.714,
      "step": 37
    },
    {
      "epoch": 0.00596476082093945,
      "grad_norm": 0.48381856083869934,
      "learning_rate": 0.0003875137508612103,
      "loss": 0.939,
      "step": 38
    },
    {
      "epoch": 0.006121728210964172,
      "grad_norm": 0.8319804668426514,
      "learning_rate": 0.00038005986215272055,
      "loss": 0.9289,
      "step": 39
    },
    {
      "epoch": 0.006278695600988895,
      "grad_norm": 0.4785021245479584,
      "learning_rate": 0.0003724439350515571,
      "loss": 1.051,
      "step": 40
    },
    {
      "epoch": 0.006435662991013617,
      "grad_norm": 0.6576308608055115,
      "learning_rate": 0.0003646754580545226,
      "loss": 0.9983,
      "step": 41
    },
    {
      "epoch": 0.006592630381038339,
      "grad_norm": 0.4170599579811096,
      "learning_rate": 0.000356764109716594,
      "loss": 0.8185,
      "step": 42
    },
    {
      "epoch": 0.006749597771063062,
      "grad_norm": 0.4000290632247925,
      "learning_rate": 0.00034871974659264783,
      "loss": 0.8255,
      "step": 43
    },
    {
      "epoch": 0.006906565161087784,
      "grad_norm": 0.32657188177108765,
      "learning_rate": 0.0003405523909574206,
      "loss": 0.6339,
      "step": 44
    },
    {
      "epoch": 0.007063532551112506,
      "grad_norm": 0.41789180040359497,
      "learning_rate": 0.0003322722183190025,
      "loss": 0.8051,
      "step": 45
    },
    {
      "epoch": 0.007220499941137229,
      "grad_norm": 0.38286373019218445,
      "learning_rate": 0.0003238895447414211,
      "loss": 0.6807,
      "step": 46
    },
    {
      "epoch": 0.007377467331161951,
      "grad_norm": 0.3656023442745209,
      "learning_rate": 0.0003154148139921102,
      "loss": 0.6798,
      "step": 47
    },
    {
      "epoch": 0.007534434721186673,
      "grad_norm": 0.4634772837162018,
      "learning_rate": 0.00030685858453027663,
      "loss": 0.8384,
      "step": 48
    },
    {
      "epoch": 0.007691402111211396,
      "grad_norm": 0.3100186884403229,
      "learning_rate": 0.0002982315163523742,
      "loss": 0.7984,
      "step": 49
    },
    {
      "epoch": 0.007848369501236118,
      "grad_norm": 0.608703076839447,
      "learning_rate": 0.000289544357711076,
      "loss": 1.2016,
      "step": 50
    },
    {
      "epoch": 0.007848369501236118,
      "eval_loss": 0.898485004901886,
      "eval_runtime": 58.4598,
      "eval_samples_per_second": 45.895,
      "eval_steps_per_second": 22.956,
      "step": 50
    },
    {
      "epoch": 0.008005336891260841,
      "grad_norm": 0.3083370625972748,
      "learning_rate": 0.0002808079317242896,
      "loss": 0.6572,
      "step": 51
    },
    {
      "epoch": 0.008162304281285563,
      "grad_norm": 0.3935853838920593,
      "learning_rate": 0.0002720331228909005,
      "loss": 1.0255,
      "step": 52
    },
    {
      "epoch": 0.008319271671310285,
      "grad_norm": 0.5018428564071655,
      "learning_rate": 0.00026323086353004075,
      "loss": 0.7937,
      "step": 53
    },
    {
      "epoch": 0.008476239061335008,
      "grad_norm": 0.27589741349220276,
      "learning_rate": 0.0002544121201607822,
      "loss": 0.5505,
      "step": 54
    },
    {
      "epoch": 0.00863320645135973,
      "grad_norm": 0.47793063521385193,
      "learning_rate": 0.00024558787983921783,
      "loss": 0.7793,
      "step": 55
    },
    {
      "epoch": 0.008790173841384452,
      "grad_norm": 0.6015914082527161,
      "learning_rate": 0.0002367691364699592,
      "loss": 1.0549,
      "step": 56
    },
    {
      "epoch": 0.008947141231409175,
      "grad_norm": 0.42470067739486694,
      "learning_rate": 0.00022796687710909964,
      "loss": 1.1239,
      "step": 57
    },
    {
      "epoch": 0.009104108621433897,
      "grad_norm": 0.41093453764915466,
      "learning_rate": 0.00021919206827571036,
      "loss": 1.0407,
      "step": 58
    },
    {
      "epoch": 0.009261076011458619,
      "grad_norm": 0.41134944558143616,
      "learning_rate": 0.00021045564228892402,
      "loss": 0.6677,
      "step": 59
    },
    {
      "epoch": 0.009418043401483342,
      "grad_norm": 0.38528087735176086,
      "learning_rate": 0.00020176848364762578,
      "loss": 1.0211,
      "step": 60
    },
    {
      "epoch": 0.009575010791508064,
      "grad_norm": 0.38283631205558777,
      "learning_rate": 0.00019314141546972343,
      "loss": 0.8785,
      "step": 61
    },
    {
      "epoch": 0.009731978181532786,
      "grad_norm": 0.3168281316757202,
      "learning_rate": 0.00018458518600788986,
      "loss": 0.8723,
      "step": 62
    },
    {
      "epoch": 0.00988894557155751,
      "grad_norm": 0.32666337490081787,
      "learning_rate": 0.00017611045525857898,
      "loss": 0.9419,
      "step": 63
    },
    {
      "epoch": 0.010045912961582231,
      "grad_norm": 0.40057867765426636,
      "learning_rate": 0.0001677277816809975,
      "loss": 0.9665,
      "step": 64
    },
    {
      "epoch": 0.010202880351606953,
      "grad_norm": 0.46375736594200134,
      "learning_rate": 0.00015944760904257942,
      "loss": 0.9058,
      "step": 65
    },
    {
      "epoch": 0.010359847741631676,
      "grad_norm": 0.3828064203262329,
      "learning_rate": 0.0001512802534073522,
      "loss": 0.6986,
      "step": 66
    },
    {
      "epoch": 0.010516815131656398,
      "grad_norm": 0.38636311888694763,
      "learning_rate": 0.00014323589028340596,
      "loss": 0.817,
      "step": 67
    },
    {
      "epoch": 0.01067378252168112,
      "grad_norm": 0.41518744826316833,
      "learning_rate": 0.00013532454194547733,
      "loss": 0.6401,
      "step": 68
    },
    {
      "epoch": 0.010830749911705843,
      "grad_norm": 0.5281746983528137,
      "learning_rate": 0.00012755606494844294,
      "loss": 0.8537,
      "step": 69
    },
    {
      "epoch": 0.010987717301730565,
      "grad_norm": 0.41452756524086,
      "learning_rate": 0.00011994013784727947,
      "loss": 0.8924,
      "step": 70
    },
    {
      "epoch": 0.011144684691755289,
      "grad_norm": 0.45944878458976746,
      "learning_rate": 0.00011248624913878966,
      "loss": 0.7256,
      "step": 71
    },
    {
      "epoch": 0.01130165208178001,
      "grad_norm": 0.6275045275688171,
      "learning_rate": 0.0001052036854401166,
      "loss": 0.9691,
      "step": 72
    },
    {
      "epoch": 0.011458619471804732,
      "grad_norm": 0.5686112642288208,
      "learning_rate": 9.810151991877531e-05,
      "loss": 0.8182,
      "step": 73
    },
    {
      "epoch": 0.011615586861829456,
      "grad_norm": 0.3548356592655182,
      "learning_rate": 9.118860098861537e-05,
      "loss": 0.5956,
      "step": 74
    },
    {
      "epoch": 0.011772554251854177,
      "grad_norm": 0.4017604887485504,
      "learning_rate": 8.44735412857999e-05,
      "loss": 0.6562,
      "step": 75
    },
    {
      "epoch": 0.0119295216418789,
      "grad_norm": 0.3947277367115021,
      "learning_rate": 7.79647069385328e-05,
      "loss": 1.0559,
      "step": 76
    },
    {
      "epoch": 0.012086489031903623,
      "grad_norm": 0.320968896150589,
      "learning_rate": 7.167020714390501e-05,
      "loss": 0.547,
      "step": 77
    },
    {
      "epoch": 0.012243456421928344,
      "grad_norm": 0.3922961950302124,
      "learning_rate": 6.559788406484446e-05,
      "loss": 0.9905,
      "step": 78
    },
    {
      "epoch": 0.012400423811953066,
      "grad_norm": 0.41221266984939575,
      "learning_rate": 5.975530305975807e-05,
      "loss": 0.8861,
      "step": 79
    },
    {
      "epoch": 0.01255739120197779,
      "grad_norm": 0.3318183422088623,
      "learning_rate": 5.414974325703686e-05,
      "loss": 0.7566,
      "step": 80
    },
    {
      "epoch": 0.012714358592002512,
      "grad_norm": 0.4427206814289093,
      "learning_rate": 4.8788188486168616e-05,
      "loss": 0.7644,
      "step": 81
    },
    {
      "epoch": 0.012871325982027233,
      "grad_norm": 0.4162525236606598,
      "learning_rate": 4.367731857675569e-05,
      "loss": 0.6616,
      "step": 82
    },
    {
      "epoch": 0.013028293372051957,
      "grad_norm": 0.37238290905952454,
      "learning_rate": 3.882350103627952e-05,
      "loss": 0.8344,
      "step": 83
    },
    {
      "epoch": 0.013185260762076679,
      "grad_norm": 0.43004289269447327,
      "learning_rate": 3.423278311697897e-05,
      "loss": 0.6133,
      "step": 84
    },
    {
      "epoch": 0.0133422281521014,
      "grad_norm": 0.4774795472621918,
      "learning_rate": 2.9910884281727225e-05,
      "loss": 0.9229,
      "step": 85
    },
    {
      "epoch": 0.013499195542126124,
      "grad_norm": 0.4710048735141754,
      "learning_rate": 2.586318907829291e-05,
      "loss": 1.003,
      "step": 86
    },
    {
      "epoch": 0.013656162932150846,
      "grad_norm": 0.48064345121383667,
      "learning_rate": 2.209474043086457e-05,
      "loss": 0.6504,
      "step": 87
    },
    {
      "epoch": 0.013813130322175567,
      "grad_norm": 0.3248710632324219,
      "learning_rate": 1.861023335719475e-05,
      "loss": 0.7729,
      "step": 88
    },
    {
      "epoch": 0.01397009771220029,
      "grad_norm": 0.43739113211631775,
      "learning_rate": 1.5414009119192633e-05,
      "loss": 1.0168,
      "step": 89
    },
    {
      "epoch": 0.014127065102225013,
      "grad_norm": 0.26098549365997314,
      "learning_rate": 1.25100498142523e-05,
      "loss": 0.6323,
      "step": 90
    },
    {
      "epoch": 0.014284032492249734,
      "grad_norm": 0.44334644079208374,
      "learning_rate": 9.901973414055187e-06,
      "loss": 0.7762,
      "step": 91
    },
    {
      "epoch": 0.014440999882274458,
      "grad_norm": 0.42882293462753296,
      "learning_rate": 7.593029257027956e-06,
      "loss": 0.9357,
      "step": 92
    },
    {
      "epoch": 0.01459796727229918,
      "grad_norm": 0.3838594853878021,
      "learning_rate": 5.5860940000714015e-06,
      "loss": 0.7766,
      "step": 93
    },
    {
      "epoch": 0.014754934662323901,
      "grad_norm": 0.2918799817562103,
      "learning_rate": 3.8836680346041594e-06,
      "loss": 0.6025,
      "step": 94
    },
    {
      "epoch": 0.014911902052348625,
      "grad_norm": 0.3367508053779602,
      "learning_rate": 2.487872371386424e-06,
      "loss": 0.7892,
      "step": 95
    },
    {
      "epoch": 0.015068869442373347,
      "grad_norm": 0.3433071970939636,
      "learning_rate": 1.4004459980045125e-06,
      "loss": 0.5108,
      "step": 96
    },
    {
      "epoch": 0.01522583683239807,
      "grad_norm": 0.4132903516292572,
      "learning_rate": 6.22743712309054e-07,
      "loss": 0.8608,
      "step": 97
    },
    {
      "epoch": 0.015382804222422792,
      "grad_norm": 0.36693432927131653,
      "learning_rate": 1.557344345054501e-07,
      "loss": 0.7531,
      "step": 98
    },
    {
      "epoch": 0.015539771612447514,
      "grad_norm": 0.42726150155067444,
      "learning_rate": 0.0,
      "loss": 0.8528,
      "step": 99
    }
  ],
  "logging_steps": 1,
  "max_steps": 99,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 300,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4864473877708800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}