{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0033791279119378785,
  "eval_steps": 50,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.4132605171089684e-05,
      "grad_norm": 0.20423279702663422,
      "learning_rate": 5e-05,
      "loss": 3.2544,
      "step": 1
    },
    {
      "epoch": 3.4132605171089684e-05,
      "eval_loss": 3.076941728591919,
      "eval_runtime": 203.9843,
      "eval_samples_per_second": 60.475,
      "eval_steps_per_second": 30.238,
      "step": 1
    },
    {
      "epoch": 6.826521034217937e-05,
      "grad_norm": 0.19064632058143616,
      "learning_rate": 0.0001,
      "loss": 2.8993,
      "step": 2
    },
    {
      "epoch": 0.00010239781551326905,
      "grad_norm": 0.19087578356266022,
      "learning_rate": 0.00015,
      "loss": 2.8242,
      "step": 3
    },
    {
      "epoch": 0.00013653042068435874,
      "grad_norm": 0.18373772501945496,
      "learning_rate": 0.0002,
      "loss": 2.6837,
      "step": 4
    },
    {
      "epoch": 0.0001706630258554484,
      "grad_norm": 0.26902732253074646,
      "learning_rate": 0.00025,
      "loss": 3.3408,
      "step": 5
    },
    {
      "epoch": 0.0002047956310265381,
      "grad_norm": 0.24464839696884155,
      "learning_rate": 0.0003,
      "loss": 3.0973,
      "step": 6
    },
    {
      "epoch": 0.0002389282361976278,
      "grad_norm": 0.25614237785339355,
      "learning_rate": 0.00035,
      "loss": 2.9122,
      "step": 7
    },
    {
      "epoch": 0.00027306084136871747,
      "grad_norm": 0.29932963848114014,
      "learning_rate": 0.0004,
      "loss": 3.0787,
      "step": 8
    },
    {
      "epoch": 0.0003071934465398072,
      "grad_norm": 0.2929045855998993,
      "learning_rate": 0.00045000000000000004,
      "loss": 2.8395,
      "step": 9
    },
    {
      "epoch": 0.0003413260517108968,
      "grad_norm": 0.31398922204971313,
      "learning_rate": 0.0005,
      "loss": 2.9357,
      "step": 10
    },
    {
      "epoch": 0.00037545865688198653,
      "grad_norm": 0.3056373596191406,
      "learning_rate": 0.0004998442655654946,
      "loss": 2.6586,
      "step": 11
    },
    {
      "epoch": 0.0004095912620530762,
      "grad_norm": 0.261355996131897,
      "learning_rate": 0.0004993772562876909,
      "loss": 2.7995,
      "step": 12
    },
    {
      "epoch": 0.0004437238672241659,
      "grad_norm": 0.34815752506256104,
      "learning_rate": 0.0004985995540019955,
      "loss": 3.5264,
      "step": 13
    },
    {
      "epoch": 0.0004778564723952556,
      "grad_norm": 0.4225376844406128,
      "learning_rate": 0.0004975121276286136,
      "loss": 2.9188,
      "step": 14
    },
    {
      "epoch": 0.0005119890775663453,
      "grad_norm": 0.40409791469573975,
      "learning_rate": 0.0004961163319653958,
      "loss": 2.6648,
      "step": 15
    },
    {
      "epoch": 0.0005461216827374349,
      "grad_norm": 0.4268514811992645,
      "learning_rate": 0.0004944139059999286,
      "loss": 2.3858,
      "step": 16
    },
    {
      "epoch": 0.0005802542879085246,
      "grad_norm": 0.3788816034793854,
      "learning_rate": 0.000492406970742972,
      "loss": 2.5092,
      "step": 17
    },
    {
      "epoch": 0.0006143868930796144,
      "grad_norm": 0.5883328914642334,
      "learning_rate": 0.0004900980265859448,
      "loss": 3.279,
      "step": 18
    },
    {
      "epoch": 0.000648519498250704,
      "grad_norm": 0.3739059567451477,
      "learning_rate": 0.0004874899501857477,
      "loss": 2.6785,
      "step": 19
    },
    {
      "epoch": 0.0006826521034217937,
      "grad_norm": 0.32422783970832825,
      "learning_rate": 0.00048458599088080736,
      "loss": 2.4865,
      "step": 20
    },
    {
      "epoch": 0.0007167847085928833,
      "grad_norm": 0.28062283992767334,
      "learning_rate": 0.0004813897666428053,
      "loss": 3.0097,
      "step": 21
    },
    {
      "epoch": 0.0007509173137639731,
      "grad_norm": 0.3173668384552002,
      "learning_rate": 0.00047790525956913543,
      "loss": 2.8305,
      "step": 22
    },
    {
      "epoch": 0.0007850499189350627,
      "grad_norm": 0.34149301052093506,
      "learning_rate": 0.0004741368109217071,
      "loss": 2.3109,
      "step": 23
    },
    {
      "epoch": 0.0008191825241061524,
      "grad_norm": 0.3601361811161041,
      "learning_rate": 0.00047008911571827283,
      "loss": 2.6649,
      "step": 24
    },
    {
      "epoch": 0.0008533151292772421,
      "grad_norm": 0.34317097067832947,
      "learning_rate": 0.00046576721688302105,
      "loss": 2.5954,
      "step": 25
    },
    {
      "epoch": 0.0008874477344483318,
      "grad_norm": 0.32293665409088135,
      "learning_rate": 0.0004611764989637205,
      "loss": 2.5435,
      "step": 26
    },
    {
      "epoch": 0.0009215803396194214,
      "grad_norm": 0.35975202918052673,
      "learning_rate": 0.0004563226814232444,
      "loss": 2.9584,
      "step": 27
    },
    {
      "epoch": 0.0009557129447905112,
      "grad_norm": 0.2800445258617401,
      "learning_rate": 0.0004512118115138315,
      "loss": 2.4723,
      "step": 28
    },
    {
      "epoch": 0.0009898455499616008,
      "grad_norm": 0.3043380677700043,
      "learning_rate": 0.0004458502567429631,
      "loss": 2.6894,
      "step": 29
    },
    {
      "epoch": 0.0010239781551326906,
      "grad_norm": 0.31911131739616394,
      "learning_rate": 0.00044024469694024196,
      "loss": 2.6563,
      "step": 30
    },
    {
      "epoch": 0.0010581107603037801,
      "grad_norm": 0.309402734041214,
      "learning_rate": 0.00043440211593515554,
      "loss": 2.4612,
      "step": 31
    },
    {
      "epoch": 0.0010922433654748699,
      "grad_norm": 0.30311980843544006,
      "learning_rate": 0.0004283297928560951,
      "loss": 2.7588,
      "step": 32
    },
    {
      "epoch": 0.0011263759706459596,
      "grad_norm": 0.3477875292301178,
      "learning_rate": 0.0004220352930614672,
      "loss": 2.4841,
      "step": 33
    },
    {
      "epoch": 0.0011605085758170492,
      "grad_norm": 0.37769827246665955,
      "learning_rate": 0.00041552645871420013,
      "loss": 2.5664,
      "step": 34
    },
    {
      "epoch": 0.001194641180988139,
      "grad_norm": 0.32566434144973755,
      "learning_rate": 0.00040881139901138467,
      "loss": 2.4234,
      "step": 35
    },
    {
      "epoch": 0.0012287737861592287,
      "grad_norm": 0.38163110613822937,
      "learning_rate": 0.00040189848008122475,
      "loss": 2.5688,
      "step": 36
    },
    {
      "epoch": 0.0012629063913303182,
      "grad_norm": 0.3524303734302521,
      "learning_rate": 0.00039479631455988334,
      "loss": 2.752,
      "step": 37
    },
    {
      "epoch": 0.001297038996501408,
      "grad_norm": 0.3833262622356415,
      "learning_rate": 0.0003875137508612103,
      "loss": 2.635,
      "step": 38
    },
    {
      "epoch": 0.0013311716016724975,
      "grad_norm": 0.30518823862075806,
      "learning_rate": 0.00038005986215272055,
      "loss": 2.5431,
      "step": 39
    },
    {
      "epoch": 0.0013653042068435873,
      "grad_norm": 0.3856472671031952,
      "learning_rate": 0.0003724439350515571,
      "loss": 2.7964,
      "step": 40
    },
    {
      "epoch": 0.001399436812014677,
      "grad_norm": 0.339182585477829,
      "learning_rate": 0.0003646754580545226,
      "loss": 2.4652,
      "step": 41
    },
    {
      "epoch": 0.0014335694171857666,
      "grad_norm": 0.3530672490596771,
      "learning_rate": 0.000356764109716594,
      "loss": 2.8105,
      "step": 42
    },
    {
      "epoch": 0.0014677020223568564,
      "grad_norm": 0.35563480854034424,
      "learning_rate": 0.00034871974659264783,
      "loss": 3.1352,
      "step": 43
    },
    {
      "epoch": 0.0015018346275279461,
      "grad_norm": 0.3361399471759796,
      "learning_rate": 0.0003405523909574206,
      "loss": 2.6759,
      "step": 44
    },
    {
      "epoch": 0.0015359672326990357,
      "grad_norm": 0.3976024091243744,
      "learning_rate": 0.0003322722183190025,
      "loss": 2.9357,
      "step": 45
    },
    {
      "epoch": 0.0015700998378701254,
      "grad_norm": 0.4400416314601898,
      "learning_rate": 0.0003238895447414211,
      "loss": 3.0256,
      "step": 46
    },
    {
      "epoch": 0.0016042324430412152,
      "grad_norm": 0.2710314989089966,
      "learning_rate": 0.0003154148139921102,
      "loss": 2.3832,
      "step": 47
    },
    {
      "epoch": 0.0016383650482123047,
      "grad_norm": 0.34264132380485535,
      "learning_rate": 0.00030685858453027663,
      "loss": 2.8334,
      "step": 48
    },
    {
      "epoch": 0.0016724976533833945,
      "grad_norm": 0.3671528398990631,
      "learning_rate": 0.0002982315163523742,
      "loss": 2.7482,
      "step": 49
    },
    {
      "epoch": 0.0017066302585544842,
      "grad_norm": 0.2519057095050812,
      "learning_rate": 0.000289544357711076,
      "loss": 2.7811,
      "step": 50
    },
    {
      "epoch": 0.0017066302585544842,
      "eval_loss": 2.6318328380584717,
      "eval_runtime": 203.8827,
      "eval_samples_per_second": 60.505,
      "eval_steps_per_second": 30.253,
      "step": 50
    },
    {
      "epoch": 0.0017407628637255738,
      "grad_norm": 0.2467103898525238,
      "learning_rate": 0.0002808079317242896,
      "loss": 2.2711,
      "step": 51
    },
    {
      "epoch": 0.0017748954688966635,
      "grad_norm": 0.2773958742618561,
      "learning_rate": 0.0002720331228909005,
      "loss": 2.4991,
      "step": 52
    },
    {
      "epoch": 0.0018090280740677533,
      "grad_norm": 0.22879059612751007,
      "learning_rate": 0.00026323086353004075,
      "loss": 2.5932,
      "step": 53
    },
    {
      "epoch": 0.0018431606792388428,
      "grad_norm": 0.2841690480709076,
      "learning_rate": 0.0002544121201607822,
      "loss": 2.7066,
      "step": 54
    },
    {
      "epoch": 0.0018772932844099326,
      "grad_norm": 0.3463197648525238,
      "learning_rate": 0.00024558787983921783,
      "loss": 2.4738,
      "step": 55
    },
    {
      "epoch": 0.0019114258895810224,
      "grad_norm": 0.30249327421188354,
      "learning_rate": 0.0002367691364699592,
      "loss": 2.5275,
      "step": 56
    },
    {
      "epoch": 0.001945558494752112,
      "grad_norm": 0.3161616921424866,
      "learning_rate": 0.00022796687710909964,
      "loss": 2.45,
      "step": 57
    },
    {
      "epoch": 0.0019796910999232017,
      "grad_norm": 0.3322688937187195,
      "learning_rate": 0.00021919206827571036,
      "loss": 2.6401,
      "step": 58
    },
    {
      "epoch": 0.002013823705094291,
      "grad_norm": 0.32816797494888306,
      "learning_rate": 0.00021045564228892402,
      "loss": 2.3709,
      "step": 59
    },
    {
      "epoch": 0.002047956310265381,
      "grad_norm": 0.3372400999069214,
      "learning_rate": 0.00020176848364762578,
      "loss": 2.5829,
      "step": 60
    },
    {
      "epoch": 0.0020820889154364707,
      "grad_norm": 0.39470982551574707,
      "learning_rate": 0.00019314141546972343,
      "loss": 2.631,
      "step": 61
    },
    {
      "epoch": 0.0021162215206075603,
      "grad_norm": 0.4079892635345459,
      "learning_rate": 0.00018458518600788986,
      "loss": 2.5531,
      "step": 62
    },
    {
      "epoch": 0.0021503541257786502,
      "grad_norm": 0.3176794946193695,
      "learning_rate": 0.00017611045525857898,
      "loss": 2.4695,
      "step": 63
    },
    {
      "epoch": 0.0021844867309497398,
      "grad_norm": 0.29289788007736206,
      "learning_rate": 0.0001677277816809975,
      "loss": 2.7621,
      "step": 64
    },
    {
      "epoch": 0.0022186193361208293,
      "grad_norm": 0.3670552670955658,
      "learning_rate": 0.00015944760904257942,
      "loss": 2.4779,
      "step": 65
    },
    {
      "epoch": 0.0022527519412919193,
      "grad_norm": 0.31173592805862427,
      "learning_rate": 0.0001512802534073522,
      "loss": 2.5398,
      "step": 66
    },
    {
      "epoch": 0.002286884546463009,
      "grad_norm": 0.31395551562309265,
      "learning_rate": 0.00014323589028340596,
      "loss": 2.3511,
      "step": 67
    },
    {
      "epoch": 0.0023210171516340984,
      "grad_norm": 0.30225545167922974,
      "learning_rate": 0.00013532454194547733,
      "loss": 2.2839,
      "step": 68
    },
    {
      "epoch": 0.0023551497568051884,
      "grad_norm": 0.3490327298641205,
      "learning_rate": 0.00012755606494844294,
      "loss": 2.1876,
      "step": 69
    },
    {
      "epoch": 0.002389282361976278,
      "grad_norm": 0.265563040971756,
      "learning_rate": 0.00011994013784727947,
      "loss": 2.4273,
      "step": 70
    },
    {
      "epoch": 0.0024234149671473674,
      "grad_norm": 0.4211519956588745,
      "learning_rate": 0.00011248624913878966,
      "loss": 2.4147,
      "step": 71
    },
    {
      "epoch": 0.0024575475723184574,
      "grad_norm": 0.3521697223186493,
      "learning_rate": 0.0001052036854401166,
      "loss": 2.5654,
      "step": 72
    },
    {
      "epoch": 0.002491680177489547,
      "grad_norm": 0.28024736046791077,
      "learning_rate": 9.810151991877531e-05,
      "loss": 2.7851,
      "step": 73
    },
    {
      "epoch": 0.0025258127826606365,
      "grad_norm": 0.3537457287311554,
      "learning_rate": 9.118860098861537e-05,
      "loss": 2.7206,
      "step": 74
    },
    {
      "epoch": 0.0025599453878317265,
      "grad_norm": 0.38442355394363403,
      "learning_rate": 8.44735412857999e-05,
      "loss": 2.9931,
      "step": 75
    },
    {
      "epoch": 0.002594077993002816,
      "grad_norm": 0.2771991193294525,
      "learning_rate": 7.79647069385328e-05,
      "loss": 2.366,
      "step": 76
    },
    {
      "epoch": 0.0026282105981739056,
      "grad_norm": 0.30113691091537476,
      "learning_rate": 7.167020714390501e-05,
      "loss": 2.7356,
      "step": 77
    },
    {
      "epoch": 0.002662343203344995,
      "grad_norm": 0.3958965241909027,
      "learning_rate": 6.559788406484446e-05,
      "loss": 2.3764,
      "step": 78
    },
    {
      "epoch": 0.002696475808516085,
      "grad_norm": 0.2729441523551941,
      "learning_rate": 5.975530305975807e-05,
      "loss": 2.4155,
      "step": 79
    },
    {
      "epoch": 0.0027306084136871746,
      "grad_norm": 0.4083710312843323,
      "learning_rate": 5.414974325703686e-05,
      "loss": 2.7141,
      "step": 80
    },
    {
      "epoch": 0.002764741018858264,
      "grad_norm": 0.2846662700176239,
      "learning_rate": 4.8788188486168616e-05,
      "loss": 2.2121,
      "step": 81
    },
    {
      "epoch": 0.002798873624029354,
      "grad_norm": 0.28273066878318787,
      "learning_rate": 4.367731857675569e-05,
      "loss": 2.5148,
      "step": 82
    },
    {
      "epoch": 0.0028330062292004437,
      "grad_norm": 0.23538333177566528,
      "learning_rate": 3.882350103627952e-05,
      "loss": 2.4308,
      "step": 83
    },
    {
      "epoch": 0.002867138834371533,
      "grad_norm": 0.3415232002735138,
      "learning_rate": 3.423278311697897e-05,
      "loss": 2.8553,
      "step": 84
    },
    {
      "epoch": 0.002901271439542623,
      "grad_norm": 0.2868449091911316,
      "learning_rate": 2.9910884281727225e-05,
      "loss": 2.7417,
      "step": 85
    },
    {
      "epoch": 0.0029354040447137127,
      "grad_norm": 0.32795730233192444,
      "learning_rate": 2.586318907829291e-05,
      "loss": 2.5102,
      "step": 86
    },
    {
      "epoch": 0.0029695366498848023,
      "grad_norm": 0.2663126289844513,
      "learning_rate": 2.209474043086457e-05,
      "loss": 2.5792,
      "step": 87
    },
    {
      "epoch": 0.0030036692550558922,
      "grad_norm": 0.4900624454021454,
      "learning_rate": 1.861023335719475e-05,
      "loss": 3.2786,
      "step": 88
    },
    {
      "epoch": 0.003037801860226982,
      "grad_norm": 0.3926824927330017,
      "learning_rate": 1.5414009119192633e-05,
      "loss": 2.5358,
      "step": 89
    },
    {
      "epoch": 0.0030719344653980713,
      "grad_norm": 0.32311323285102844,
      "learning_rate": 1.25100498142523e-05,
      "loss": 2.7474,
      "step": 90
    },
    {
      "epoch": 0.0031060670705691613,
      "grad_norm": 0.3624803423881531,
      "learning_rate": 9.901973414055187e-06,
      "loss": 2.6785,
      "step": 91
    },
    {
      "epoch": 0.003140199675740251,
      "grad_norm": 0.31824859976768494,
      "learning_rate": 7.593029257027956e-06,
      "loss": 2.175,
      "step": 92
    },
    {
      "epoch": 0.0031743322809113404,
      "grad_norm": 0.4055838882923126,
      "learning_rate": 5.5860940000714015e-06,
      "loss": 2.7394,
      "step": 93
    },
    {
      "epoch": 0.0032084648860824304,
      "grad_norm": 0.3027328848838806,
      "learning_rate": 3.8836680346041594e-06,
      "loss": 2.8705,
      "step": 94
    },
    {
      "epoch": 0.00324259749125352,
      "grad_norm": 0.2983163595199585,
      "learning_rate": 2.487872371386424e-06,
      "loss": 2.5091,
      "step": 95
    },
    {
      "epoch": 0.0032767300964246095,
      "grad_norm": 0.38754749298095703,
      "learning_rate": 1.4004459980045125e-06,
      "loss": 2.9323,
      "step": 96
    },
    {
      "epoch": 0.0033108627015956994,
      "grad_norm": 0.33583030104637146,
      "learning_rate": 6.22743712309054e-07,
      "loss": 2.6292,
      "step": 97
    },
    {
      "epoch": 0.003344995306766789,
      "grad_norm": 0.37954822182655334,
      "learning_rate": 1.557344345054501e-07,
      "loss": 2.7452,
      "step": 98
    },
    {
      "epoch": 0.0033791279119378785,
      "grad_norm": 0.2241569459438324,
      "learning_rate": 0.0,
      "loss": 2.5134,
      "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": 4169798900514816.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}