{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13027618551328818,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013027618551328818,
      "grad_norm": 14.949752807617188,
      "learning_rate": 4.0625e-06,
      "loss": 1.3439,
      "step": 1
    },
    {
      "epoch": 0.0026055237102657635,
      "grad_norm": 15.725403785705566,
      "learning_rate": 8.125e-06,
      "loss": 1.3354,
      "step": 2
    },
    {
      "epoch": 0.0039082855653986455,
      "grad_norm": 12.41278076171875,
      "learning_rate": 1.2187499999999998e-05,
      "loss": 1.3017,
      "step": 3
    },
    {
      "epoch": 0.005211047420531527,
      "grad_norm": 6.782334327697754,
      "learning_rate": 1.625e-05,
      "loss": 1.2634,
      "step": 4
    },
    {
      "epoch": 0.006513809275664409,
      "grad_norm": 3.730219841003418,
      "learning_rate": 2.03125e-05,
      "loss": 1.1704,
      "step": 5
    },
    {
      "epoch": 0.007816571130797291,
      "grad_norm": 2.547757863998413,
      "learning_rate": 2.4374999999999996e-05,
      "loss": 1.165,
      "step": 6
    },
    {
      "epoch": 0.009119332985930172,
      "grad_norm": 2.4353976249694824,
      "learning_rate": 2.8437499999999997e-05,
      "loss": 1.1567,
      "step": 7
    },
    {
      "epoch": 0.010422094841063054,
      "grad_norm": 2.218895673751831,
      "learning_rate": 3.25e-05,
      "loss": 1.0846,
      "step": 8
    },
    {
      "epoch": 0.011724856696195935,
      "grad_norm": 1.7433233261108398,
      "learning_rate": 3.6562499999999994e-05,
      "loss": 0.9816,
      "step": 9
    },
    {
      "epoch": 0.013027618551328817,
      "grad_norm": 1.6148579120635986,
      "learning_rate": 4.0625e-05,
      "loss": 1.0869,
      "step": 10
    },
    {
      "epoch": 0.0143303804064617,
      "grad_norm": 1.5065230131149292,
      "learning_rate": 4.4687499999999995e-05,
      "loss": 0.9625,
      "step": 11
    },
    {
      "epoch": 0.015633142261594582,
      "grad_norm": 1.4786823987960815,
      "learning_rate": 4.874999999999999e-05,
      "loss": 1.0489,
      "step": 12
    },
    {
      "epoch": 0.016935904116727463,
      "grad_norm": 1.2991230487823486,
      "learning_rate": 5.2812499999999996e-05,
      "loss": 0.9935,
      "step": 13
    },
    {
      "epoch": 0.018238665971860343,
      "grad_norm": 1.3199464082717896,
      "learning_rate": 5.687499999999999e-05,
      "loss": 1.0188,
      "step": 14
    },
    {
      "epoch": 0.019541427826993224,
      "grad_norm": 1.2793257236480713,
      "learning_rate": 6.09375e-05,
      "loss": 1.0265,
      "step": 15
    },
    {
      "epoch": 0.020844189682126108,
      "grad_norm": 1.2210655212402344,
      "learning_rate": 6.5e-05,
      "loss": 0.9019,
      "step": 16
    },
    {
      "epoch": 0.02214695153725899,
      "grad_norm": 1.3837445974349976,
      "learning_rate": 6.499971563731688e-05,
      "loss": 0.9487,
      "step": 17
    },
    {
      "epoch": 0.02344971339239187,
      "grad_norm": 1.2946529388427734,
      "learning_rate": 6.499886255424368e-05,
      "loss": 1.0031,
      "step": 18
    },
    {
      "epoch": 0.024752475247524754,
      "grad_norm": 1.3142110109329224,
      "learning_rate": 6.499744076570868e-05,
      "loss": 0.9941,
      "step": 19
    },
    {
      "epoch": 0.026055237102657634,
      "grad_norm": 1.8206599950790405,
      "learning_rate": 6.499545029659211e-05,
      "loss": 0.9767,
      "step": 20
    },
    {
      "epoch": 0.027357998957790515,
      "grad_norm": 1.2736281156539917,
      "learning_rate": 6.499289118172568e-05,
      "loss": 0.9194,
      "step": 21
    },
    {
      "epoch": 0.0286607608129234,
      "grad_norm": 1.8105640411376953,
      "learning_rate": 6.498976346589196e-05,
      "loss": 0.9853,
      "step": 22
    },
    {
      "epoch": 0.02996352266805628,
      "grad_norm": 1.4621827602386475,
      "learning_rate": 6.49860672038236e-05,
      "loss": 0.9896,
      "step": 23
    },
    {
      "epoch": 0.031266284523189164,
      "grad_norm": 1.212299108505249,
      "learning_rate": 6.498180246020238e-05,
      "loss": 0.9684,
      "step": 24
    },
    {
      "epoch": 0.032569046378322045,
      "grad_norm": 1.2274290323257446,
      "learning_rate": 6.49769693096581e-05,
      "loss": 0.9831,
      "step": 25
    },
    {
      "epoch": 0.033871808233454925,
      "grad_norm": 1.2909352779388428,
      "learning_rate": 6.49715678367672e-05,
      "loss": 0.9971,
      "step": 26
    },
    {
      "epoch": 0.035174570088587806,
      "grad_norm": 1.2330715656280518,
      "learning_rate": 6.49655981360514e-05,
      "loss": 0.9923,
      "step": 27
    },
    {
      "epoch": 0.03647733194372069,
      "grad_norm": 1.2433793544769287,
      "learning_rate": 6.495906031197591e-05,
      "loss": 0.9121,
      "step": 28
    },
    {
      "epoch": 0.03778009379885357,
      "grad_norm": 1.2374027967453003,
      "learning_rate": 6.49519544789477e-05,
      "loss": 0.9224,
      "step": 29
    },
    {
      "epoch": 0.03908285565398645,
      "grad_norm": 1.2204357385635376,
      "learning_rate": 6.494428076131346e-05,
      "loss": 0.919,
      "step": 30
    },
    {
      "epoch": 0.040385617509119336,
      "grad_norm": 1.1927292346954346,
      "learning_rate": 6.493603929335744e-05,
      "loss": 0.9589,
      "step": 31
    },
    {
      "epoch": 0.041688379364252216,
      "grad_norm": 1.1353641748428345,
      "learning_rate": 6.492723021929908e-05,
      "loss": 0.8869,
      "step": 32
    },
    {
      "epoch": 0.0429911412193851,
      "grad_norm": 1.212263822555542,
      "learning_rate": 6.49178536932905e-05,
      "loss": 0.8934,
      "step": 33
    },
    {
      "epoch": 0.04429390307451798,
      "grad_norm": 1.0893241167068481,
      "learning_rate": 6.49079098794138e-05,
      "loss": 0.8718,
      "step": 34
    },
    {
      "epoch": 0.04559666492965086,
      "grad_norm": 1.1801607608795166,
      "learning_rate": 6.489739895167818e-05,
      "loss": 0.9774,
      "step": 35
    },
    {
      "epoch": 0.04689942678478374,
      "grad_norm": 1.1302330493927002,
      "learning_rate": 6.488632109401691e-05,
      "loss": 0.9584,
      "step": 36
    },
    {
      "epoch": 0.04820218863991663,
      "grad_norm": 1.1432682275772095,
      "learning_rate": 6.487467650028411e-05,
      "loss": 0.9452,
      "step": 37
    },
    {
      "epoch": 0.04950495049504951,
      "grad_norm": 1.1399481296539307,
      "learning_rate": 6.486246537425133e-05,
      "loss": 0.9017,
      "step": 38
    },
    {
      "epoch": 0.05080771235018239,
      "grad_norm": 1.0911235809326172,
      "learning_rate": 6.484968792960403e-05,
      "loss": 0.9036,
      "step": 39
    },
    {
      "epoch": 0.05211047420531527,
      "grad_norm": 1.071078896522522,
      "learning_rate": 6.48363443899378e-05,
      "loss": 0.9273,
      "step": 40
    },
    {
      "epoch": 0.05341323606044815,
      "grad_norm": 1.053589105606079,
      "learning_rate": 6.482243498875449e-05,
      "loss": 0.8847,
      "step": 41
    },
    {
      "epoch": 0.05471599791558103,
      "grad_norm": 1.109771490097046,
      "learning_rate": 6.480795996945806e-05,
      "loss": 0.9364,
      "step": 42
    },
    {
      "epoch": 0.05601875977071391,
      "grad_norm": 1.1093286275863647,
      "learning_rate": 6.479291958535037e-05,
      "loss": 0.9088,
      "step": 43
    },
    {
      "epoch": 0.0573215216258468,
      "grad_norm": 1.0716255903244019,
      "learning_rate": 6.477731409962675e-05,
      "loss": 0.8885,
      "step": 44
    },
    {
      "epoch": 0.05862428348097968,
      "grad_norm": 1.1552095413208008,
      "learning_rate": 6.476114378537138e-05,
      "loss": 0.9736,
      "step": 45
    },
    {
      "epoch": 0.05992704533611256,
      "grad_norm": 1.1647394895553589,
      "learning_rate": 6.474440892555249e-05,
      "loss": 0.9138,
      "step": 46
    },
    {
      "epoch": 0.06122980719124544,
      "grad_norm": 1.1463412046432495,
      "learning_rate": 6.472710981301745e-05,
      "loss": 0.9204,
      "step": 47
    },
    {
      "epoch": 0.06253256904637833,
      "grad_norm": 1.175421118736267,
      "learning_rate": 6.470924675048762e-05,
      "loss": 0.9119,
      "step": 48
    },
    {
      "epoch": 0.06383533090151121,
      "grad_norm": 1.9249529838562012,
      "learning_rate": 6.469082005055304e-05,
      "loss": 0.8639,
      "step": 49
    },
    {
      "epoch": 0.06513809275664409,
      "grad_norm": 1.1802655458450317,
      "learning_rate": 6.467183003566701e-05,
      "loss": 0.9352,
      "step": 50
    },
    {
      "epoch": 0.06644085461177697,
      "grad_norm": 1.1035569906234741,
      "learning_rate": 6.465227703814038e-05,
      "loss": 0.9342,
      "step": 51
    },
    {
      "epoch": 0.06774361646690985,
      "grad_norm": 1.1226942539215088,
      "learning_rate": 6.463216140013581e-05,
      "loss": 0.8948,
      "step": 52
    },
    {
      "epoch": 0.06904637832204273,
      "grad_norm": 1.1143085956573486,
      "learning_rate": 6.46114834736617e-05,
      "loss": 0.9577,
      "step": 53
    },
    {
      "epoch": 0.07034914017717561,
      "grad_norm": 1.1214665174484253,
      "learning_rate": 6.459024362056608e-05,
      "loss": 0.9106,
      "step": 54
    },
    {
      "epoch": 0.07165190203230849,
      "grad_norm": 1.1105942726135254,
      "learning_rate": 6.45684422125303e-05,
      "loss": 0.8706,
      "step": 55
    },
    {
      "epoch": 0.07295466388744137,
      "grad_norm": 1.0562191009521484,
      "learning_rate": 6.454607963106247e-05,
      "loss": 0.8278,
      "step": 56
    },
    {
      "epoch": 0.07425742574257425,
      "grad_norm": 1.1298907995224,
      "learning_rate": 6.452315626749081e-05,
      "loss": 0.8883,
      "step": 57
    },
    {
      "epoch": 0.07556018759770713,
      "grad_norm": 1.133426547050476,
      "learning_rate": 6.449967252295682e-05,
      "loss": 0.8868,
      "step": 58
    },
    {
      "epoch": 0.07686294945284002,
      "grad_norm": 1.09175443649292,
      "learning_rate": 6.447562880840822e-05,
      "loss": 0.8486,
      "step": 59
    },
    {
      "epoch": 0.0781657113079729,
      "grad_norm": 1.1153368949890137,
      "learning_rate": 6.44510255445918e-05,
      "loss": 0.9278,
      "step": 60
    },
    {
      "epoch": 0.07946847316310579,
      "grad_norm": 1.102013349533081,
      "learning_rate": 6.442586316204601e-05,
      "loss": 0.8362,
      "step": 61
    },
    {
      "epoch": 0.08077123501823867,
      "grad_norm": 1.1041877269744873,
      "learning_rate": 6.44001421010935e-05,
      "loss": 0.8746,
      "step": 62
    },
    {
      "epoch": 0.08207399687337155,
      "grad_norm": 1.075576901435852,
      "learning_rate": 6.437386281183331e-05,
      "loss": 0.8567,
      "step": 63
    },
    {
      "epoch": 0.08337675872850443,
      "grad_norm": 1.1472443342208862,
      "learning_rate": 6.43470257541331e-05,
      "loss": 0.9023,
      "step": 64
    },
    {
      "epoch": 0.08467952058363731,
      "grad_norm": 1.1024972200393677,
      "learning_rate": 6.431963139762104e-05,
      "loss": 0.8982,
      "step": 65
    },
    {
      "epoch": 0.0859822824387702,
      "grad_norm": 1.1128768920898438,
      "learning_rate": 6.42916802216776e-05,
      "loss": 0.883,
      "step": 66
    },
    {
      "epoch": 0.08728504429390307,
      "grad_norm": 1.058384895324707,
      "learning_rate": 6.426317271542717e-05,
      "loss": 0.8428,
      "step": 67
    },
    {
      "epoch": 0.08858780614903596,
      "grad_norm": 1.0728991031646729,
      "learning_rate": 6.423410937772951e-05,
      "loss": 0.8553,
      "step": 68
    },
    {
      "epoch": 0.08989056800416884,
      "grad_norm": 1.0956963300704956,
      "learning_rate": 6.4204490717171e-05,
      "loss": 0.8894,
      "step": 69
    },
    {
      "epoch": 0.09119332985930172,
      "grad_norm": 1.0787287950515747,
      "learning_rate": 6.417431725205575e-05,
      "loss": 0.9086,
      "step": 70
    },
    {
      "epoch": 0.0924960917144346,
      "grad_norm": 1.1435580253601074,
      "learning_rate": 6.414358951039651e-05,
      "loss": 0.9074,
      "step": 71
    },
    {
      "epoch": 0.09379885356956748,
      "grad_norm": 1.0396053791046143,
      "learning_rate": 6.41123080299055e-05,
      "loss": 0.8553,
      "step": 72
    },
    {
      "epoch": 0.09510161542470036,
      "grad_norm": 1.0929105281829834,
      "learning_rate": 6.40804733579849e-05,
      "loss": 0.8504,
      "step": 73
    },
    {
      "epoch": 0.09640437727983325,
      "grad_norm": 1.1395248174667358,
      "learning_rate": 6.404808605171734e-05,
      "loss": 0.9222,
      "step": 74
    },
    {
      "epoch": 0.09770713913496613,
      "grad_norm": 1.0281647443771362,
      "learning_rate": 6.401514667785613e-05,
      "loss": 0.868,
      "step": 75
    },
    {
      "epoch": 0.09900990099009901,
      "grad_norm": 1.0565054416656494,
      "learning_rate": 6.398165581281536e-05,
      "loss": 0.8302,
      "step": 76
    },
    {
      "epoch": 0.1003126628452319,
      "grad_norm": 1.0529290437698364,
      "learning_rate": 6.394761404265977e-05,
      "loss": 0.8669,
      "step": 77
    },
    {
      "epoch": 0.10161542470036478,
      "grad_norm": 1.0579882860183716,
      "learning_rate": 6.391302196309452e-05,
      "loss": 0.9204,
      "step": 78
    },
    {
      "epoch": 0.10291818655549766,
      "grad_norm": 1.0531302690505981,
      "learning_rate": 6.387788017945482e-05,
      "loss": 0.9202,
      "step": 79
    },
    {
      "epoch": 0.10422094841063054,
      "grad_norm": 1.0358260869979858,
      "learning_rate": 6.384218930669521e-05,
      "loss": 0.8647,
      "step": 80
    },
    {
      "epoch": 0.10552371026576342,
      "grad_norm": 1.0599216222763062,
      "learning_rate": 6.380594996937895e-05,
      "loss": 0.9093,
      "step": 81
    },
    {
      "epoch": 0.1068264721208963,
      "grad_norm": 1.2026344537734985,
      "learning_rate": 6.376916280166696e-05,
      "loss": 0.8731,
      "step": 82
    },
    {
      "epoch": 0.10812923397602918,
      "grad_norm": 1.1054397821426392,
      "learning_rate": 6.373182844730677e-05,
      "loss": 0.8835,
      "step": 83
    },
    {
      "epoch": 0.10943199583116206,
      "grad_norm": 1.030562162399292,
      "learning_rate": 6.369394755962129e-05,
      "loss": 0.8432,
      "step": 84
    },
    {
      "epoch": 0.11073475768629494,
      "grad_norm": 1.0522128343582153,
      "learning_rate": 6.365552080149737e-05,
      "loss": 0.8598,
      "step": 85
    },
    {
      "epoch": 0.11203751954142782,
      "grad_norm": 1.0692416429519653,
      "learning_rate": 6.361654884537413e-05,
      "loss": 0.8812,
      "step": 86
    },
    {
      "epoch": 0.1133402813965607,
      "grad_norm": 1.1009373664855957,
      "learning_rate": 6.357703237323127e-05,
      "loss": 0.8635,
      "step": 87
    },
    {
      "epoch": 0.1146430432516936,
      "grad_norm": 1.1628373861312866,
      "learning_rate": 6.353697207657708e-05,
      "loss": 0.8907,
      "step": 88
    },
    {
      "epoch": 0.11594580510682648,
      "grad_norm": 1.1273458003997803,
      "learning_rate": 6.349636865643642e-05,
      "loss": 0.8445,
      "step": 89
    },
    {
      "epoch": 0.11724856696195936,
      "grad_norm": 1.0971312522888184,
      "learning_rate": 6.345522282333835e-05,
      "loss": 0.8543,
      "step": 90
    },
    {
      "epoch": 0.11855132881709224,
      "grad_norm": 1.0826351642608643,
      "learning_rate": 6.341353529730374e-05,
      "loss": 0.8605,
      "step": 91
    },
    {
      "epoch": 0.11985409067222512,
      "grad_norm": 1.0686413049697876,
      "learning_rate": 6.337130680783273e-05,
      "loss": 0.8814,
      "step": 92
    },
    {
      "epoch": 0.121156852527358,
      "grad_norm": 1.21683931350708,
      "learning_rate": 6.332853809389189e-05,
      "loss": 0.8979,
      "step": 93
    },
    {
      "epoch": 0.12245961438249088,
      "grad_norm": 1.0884461402893066,
      "learning_rate": 6.328522990390126e-05,
      "loss": 0.8577,
      "step": 94
    },
    {
      "epoch": 0.12376237623762376,
      "grad_norm": 1.047310709953308,
      "learning_rate": 6.324138299572135e-05,
      "loss": 0.8174,
      "step": 95
    },
    {
      "epoch": 0.12506513809275666,
      "grad_norm": 1.087296485900879,
      "learning_rate": 6.319699813663982e-05,
      "loss": 0.8566,
      "step": 96
    },
    {
      "epoch": 0.12636789994788952,
      "grad_norm": 1.070327639579773,
      "learning_rate": 6.315207610335808e-05,
      "loss": 0.8615,
      "step": 97
    },
    {
      "epoch": 0.12767066180302242,
      "grad_norm": 1.0299792289733887,
      "learning_rate": 6.310661768197764e-05,
      "loss": 0.866,
      "step": 98
    },
    {
      "epoch": 0.12897342365815528,
      "grad_norm": 1.1011384725570679,
      "learning_rate": 6.306062366798642e-05,
      "loss": 0.8775,
      "step": 99
    },
    {
      "epoch": 0.13027618551328818,
      "grad_norm": 1.0193467140197754,
      "learning_rate": 6.301409486624481e-05,
      "loss": 0.8243,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 767,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.5374903328099533e+17,
  "train_batch_size": 6,
  "trial_name": null,
  "trial_params": null
}