{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.032797638570022956,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00032797638570022957,
      "grad_norm": 3.994058609008789,
      "learning_rate": 0.00019805941782534764,
      "loss": 2.1587,
      "step": 1
    },
    {
      "epoch": 0.0006559527714004591,
      "grad_norm": 3.933835983276367,
      "learning_rate": 0.00019605881764529358,
      "loss": 2.0517,
      "step": 2
    },
    {
      "epoch": 0.0009839291571006887,
      "grad_norm": 2.435616970062256,
      "learning_rate": 0.00019405821746523957,
      "loss": 1.6092,
      "step": 3
    },
    {
      "epoch": 0.0013119055428009183,
      "grad_norm": 2.745454788208008,
      "learning_rate": 0.00019205761728518557,
      "loss": 1.4157,
      "step": 4
    },
    {
      "epoch": 0.0016398819285011479,
      "grad_norm": 1.7035468816757202,
      "learning_rate": 0.00019005701710513156,
      "loss": 1.0786,
      "step": 5
    },
    {
      "epoch": 0.0019678583142013774,
      "grad_norm": 2.8651487827301025,
      "learning_rate": 0.00018805641692507753,
      "loss": 1.0119,
      "step": 6
    },
    {
      "epoch": 0.0022958346999016072,
      "grad_norm": 3.744490146636963,
      "learning_rate": 0.00018605581674502352,
      "loss": 0.9555,
      "step": 7
    },
    {
      "epoch": 0.0026238110856018366,
      "grad_norm": 1.1622904539108276,
      "learning_rate": 0.00018405521656496952,
      "loss": 0.8364,
      "step": 8
    },
    {
      "epoch": 0.0029517874713020664,
      "grad_norm": 8.87141227722168,
      "learning_rate": 0.00018205461638491548,
      "loss": 0.7568,
      "step": 9
    },
    {
      "epoch": 0.0032797638570022957,
      "grad_norm": 1.4474456310272217,
      "learning_rate": 0.00018005401620486148,
      "loss": 0.7653,
      "step": 10
    },
    {
      "epoch": 0.0036077402427025255,
      "grad_norm": 1.3203747272491455,
      "learning_rate": 0.00017805341602480744,
      "loss": 0.643,
      "step": 11
    },
    {
      "epoch": 0.003935716628402755,
      "grad_norm": 1.6685700416564941,
      "learning_rate": 0.00017605281584475344,
      "loss": 0.6993,
      "step": 12
    },
    {
      "epoch": 0.004263693014102984,
      "grad_norm": 1.86400306224823,
      "learning_rate": 0.00017405221566469943,
      "loss": 0.6262,
      "step": 13
    },
    {
      "epoch": 0.0045916693998032145,
      "grad_norm": 1.2344428300857544,
      "learning_rate": 0.00017205161548464542,
      "loss": 0.6256,
      "step": 14
    },
    {
      "epoch": 0.004919645785503444,
      "grad_norm": 1.351318359375,
      "learning_rate": 0.00017005101530459136,
      "loss": 0.6516,
      "step": 15
    },
    {
      "epoch": 0.005247622171203673,
      "grad_norm": 1.4530205726623535,
      "learning_rate": 0.00016805041512453736,
      "loss": 0.6692,
      "step": 16
    },
    {
      "epoch": 0.0055755985569039025,
      "grad_norm": 1.2419607639312744,
      "learning_rate": 0.00016604981494448335,
      "loss": 0.6294,
      "step": 17
    },
    {
      "epoch": 0.005903574942604133,
      "grad_norm": 1.0507097244262695,
      "learning_rate": 0.00016404921476442935,
      "loss": 0.5902,
      "step": 18
    },
    {
      "epoch": 0.006231551328304362,
      "grad_norm": 0.8393335938453674,
      "learning_rate": 0.0001620486145843753,
      "loss": 0.604,
      "step": 19
    },
    {
      "epoch": 0.0065595277140045915,
      "grad_norm": 0.9332450032234192,
      "learning_rate": 0.0001600480144043213,
      "loss": 0.5327,
      "step": 20
    },
    {
      "epoch": 0.006887504099704822,
      "grad_norm": 1.0808994770050049,
      "learning_rate": 0.0001580474142242673,
      "loss": 0.596,
      "step": 21
    },
    {
      "epoch": 0.007215480485405051,
      "grad_norm": 0.8101345896720886,
      "learning_rate": 0.00015604681404421327,
      "loss": 0.5003,
      "step": 22
    },
    {
      "epoch": 0.00754345687110528,
      "grad_norm": 1.1937756538391113,
      "learning_rate": 0.00015404621386415926,
      "loss": 0.5872,
      "step": 23
    },
    {
      "epoch": 0.00787143325680551,
      "grad_norm": 0.9010137915611267,
      "learning_rate": 0.00015204561368410523,
      "loss": 0.5776,
      "step": 24
    },
    {
      "epoch": 0.008199409642505739,
      "grad_norm": 0.7353044152259827,
      "learning_rate": 0.00015004501350405122,
      "loss": 0.5487,
      "step": 25
    },
    {
      "epoch": 0.008527386028205968,
      "grad_norm": 1.011644721031189,
      "learning_rate": 0.00014804441332399721,
      "loss": 0.583,
      "step": 26
    },
    {
      "epoch": 0.0088553624139062,
      "grad_norm": 0.9079630970954895,
      "learning_rate": 0.0001460438131439432,
      "loss": 0.5559,
      "step": 27
    },
    {
      "epoch": 0.009183338799606429,
      "grad_norm": 0.607328474521637,
      "learning_rate": 0.00014404321296388918,
      "loss": 0.6093,
      "step": 28
    },
    {
      "epoch": 0.009511315185306658,
      "grad_norm": 0.8753256797790527,
      "learning_rate": 0.00014204261278383514,
      "loss": 0.5146,
      "step": 29
    },
    {
      "epoch": 0.009839291571006888,
      "grad_norm": 0.7783370614051819,
      "learning_rate": 0.00014004201260378114,
      "loss": 0.4971,
      "step": 30
    },
    {
      "epoch": 0.010167267956707117,
      "grad_norm": 0.5913918018341064,
      "learning_rate": 0.00013804141242372713,
      "loss": 0.5077,
      "step": 31
    },
    {
      "epoch": 0.010495244342407346,
      "grad_norm": 0.817452609539032,
      "learning_rate": 0.00013604081224367312,
      "loss": 0.5969,
      "step": 32
    },
    {
      "epoch": 0.010823220728107576,
      "grad_norm": 0.8791104555130005,
      "learning_rate": 0.0001340402120636191,
      "loss": 0.5425,
      "step": 33
    },
    {
      "epoch": 0.011151197113807805,
      "grad_norm": 0.6707533001899719,
      "learning_rate": 0.00013203961188356508,
      "loss": 0.5647,
      "step": 34
    },
    {
      "epoch": 0.011479173499508036,
      "grad_norm": 0.8518595099449158,
      "learning_rate": 0.00013003901170351108,
      "loss": 0.529,
      "step": 35
    },
    {
      "epoch": 0.011807149885208265,
      "grad_norm": 0.8530653715133667,
      "learning_rate": 0.00012803841152345704,
      "loss": 0.4994,
      "step": 36
    },
    {
      "epoch": 0.012135126270908495,
      "grad_norm": 0.5490475296974182,
      "learning_rate": 0.000126037811343403,
      "loss": 0.5335,
      "step": 37
    },
    {
      "epoch": 0.012463102656608724,
      "grad_norm": 0.6268607974052429,
      "learning_rate": 0.000124037211163349,
      "loss": 0.5691,
      "step": 38
    },
    {
      "epoch": 0.012791079042308954,
      "grad_norm": 0.7266058325767517,
      "learning_rate": 0.000122036610983295,
      "loss": 0.5389,
      "step": 39
    },
    {
      "epoch": 0.013119055428009183,
      "grad_norm": 0.6403557062149048,
      "learning_rate": 0.00012003601080324098,
      "loss": 0.5405,
      "step": 40
    },
    {
      "epoch": 0.013447031813709412,
      "grad_norm": 0.5774125456809998,
      "learning_rate": 0.00011803541062318697,
      "loss": 0.5031,
      "step": 41
    },
    {
      "epoch": 0.013775008199409643,
      "grad_norm": 0.7147932052612305,
      "learning_rate": 0.00011603481044313295,
      "loss": 0.5353,
      "step": 42
    },
    {
      "epoch": 0.014102984585109873,
      "grad_norm": 0.5923655033111572,
      "learning_rate": 0.00011403421026307892,
      "loss": 0.5532,
      "step": 43
    },
    {
      "epoch": 0.014430960970810102,
      "grad_norm": 0.6512230634689331,
      "learning_rate": 0.00011203361008302491,
      "loss": 0.5585,
      "step": 44
    },
    {
      "epoch": 0.014758937356510331,
      "grad_norm": 0.5685781240463257,
      "learning_rate": 0.0001100330099029709,
      "loss": 0.5231,
      "step": 45
    },
    {
      "epoch": 0.01508691374221056,
      "grad_norm": 0.5105693936347961,
      "learning_rate": 0.00010803240972291689,
      "loss": 0.5082,
      "step": 46
    },
    {
      "epoch": 0.01541489012791079,
      "grad_norm": 0.5665640234947205,
      "learning_rate": 0.00010603180954286287,
      "loss": 0.551,
      "step": 47
    },
    {
      "epoch": 0.01574286651361102,
      "grad_norm": 0.49588409066200256,
      "learning_rate": 0.00010403120936280886,
      "loss": 0.4706,
      "step": 48
    },
    {
      "epoch": 0.01607084289931125,
      "grad_norm": 0.6303009986877441,
      "learning_rate": 0.00010203060918275482,
      "loss": 0.6035,
      "step": 49
    },
    {
      "epoch": 0.016398819285011478,
      "grad_norm": 0.5468104481697083,
      "learning_rate": 0.00010003000900270081,
      "loss": 0.5344,
      "step": 50
    },
    {
      "epoch": 0.016726795670711708,
      "grad_norm": 0.5305197834968567,
      "learning_rate": 9.802940882264679e-05,
      "loss": 0.4671,
      "step": 51
    },
    {
      "epoch": 0.017054772056411937,
      "grad_norm": 0.6518839597702026,
      "learning_rate": 9.602880864259278e-05,
      "loss": 0.5079,
      "step": 52
    },
    {
      "epoch": 0.017382748442112166,
      "grad_norm": 0.6107843518257141,
      "learning_rate": 9.402820846253876e-05,
      "loss": 0.5327,
      "step": 53
    },
    {
      "epoch": 0.0177107248278124,
      "grad_norm": 0.550966739654541,
      "learning_rate": 9.202760828248476e-05,
      "loss": 0.5254,
      "step": 54
    },
    {
      "epoch": 0.01803870121351263,
      "grad_norm": 0.5233923196792603,
      "learning_rate": 9.002700810243074e-05,
      "loss": 0.5566,
      "step": 55
    },
    {
      "epoch": 0.018366677599212858,
      "grad_norm": 0.44530218839645386,
      "learning_rate": 8.802640792237672e-05,
      "loss": 0.5025,
      "step": 56
    },
    {
      "epoch": 0.018694653984913087,
      "grad_norm": 0.6728590130805969,
      "learning_rate": 8.602580774232271e-05,
      "loss": 0.5202,
      "step": 57
    },
    {
      "epoch": 0.019022630370613317,
      "grad_norm": 0.5043520927429199,
      "learning_rate": 8.402520756226868e-05,
      "loss": 0.5248,
      "step": 58
    },
    {
      "epoch": 0.019350606756313546,
      "grad_norm": 0.48946598172187805,
      "learning_rate": 8.202460738221467e-05,
      "loss": 0.5131,
      "step": 59
    },
    {
      "epoch": 0.019678583142013775,
      "grad_norm": 0.5078890323638916,
      "learning_rate": 8.002400720216065e-05,
      "loss": 0.5142,
      "step": 60
    },
    {
      "epoch": 0.020006559527714005,
      "grad_norm": 0.48533907532691956,
      "learning_rate": 7.802340702210663e-05,
      "loss": 0.5045,
      "step": 61
    },
    {
      "epoch": 0.020334535913414234,
      "grad_norm": 0.5382115840911865,
      "learning_rate": 7.602280684205261e-05,
      "loss": 0.5858,
      "step": 62
    },
    {
      "epoch": 0.020662512299114463,
      "grad_norm": 0.5158064961433411,
      "learning_rate": 7.402220666199861e-05,
      "loss": 0.525,
      "step": 63
    },
    {
      "epoch": 0.020990488684814693,
      "grad_norm": 0.5392168164253235,
      "learning_rate": 7.202160648194459e-05,
      "loss": 0.5439,
      "step": 64
    },
    {
      "epoch": 0.021318465070514922,
      "grad_norm": 0.5060271620750427,
      "learning_rate": 7.002100630189057e-05,
      "loss": 0.5141,
      "step": 65
    },
    {
      "epoch": 0.02164644145621515,
      "grad_norm": 0.5331196188926697,
      "learning_rate": 6.802040612183656e-05,
      "loss": 0.522,
      "step": 66
    },
    {
      "epoch": 0.02197441784191538,
      "grad_norm": 0.49599310755729675,
      "learning_rate": 6.601980594178254e-05,
      "loss": 0.5154,
      "step": 67
    },
    {
      "epoch": 0.02230239422761561,
      "grad_norm": 0.5665214657783508,
      "learning_rate": 6.401920576172852e-05,
      "loss": 0.5761,
      "step": 68
    },
    {
      "epoch": 0.022630370613315843,
      "grad_norm": 0.5102436542510986,
      "learning_rate": 6.20186055816745e-05,
      "loss": 0.5483,
      "step": 69
    },
    {
      "epoch": 0.022958346999016072,
      "grad_norm": 0.512220025062561,
      "learning_rate": 6.001800540162049e-05,
      "loss": 0.5357,
      "step": 70
    },
    {
      "epoch": 0.0232863233847163,
      "grad_norm": 0.5633516311645508,
      "learning_rate": 5.801740522156648e-05,
      "loss": 0.5605,
      "step": 71
    },
    {
      "epoch": 0.02361429977041653,
      "grad_norm": 0.4963136315345764,
      "learning_rate": 5.601680504151246e-05,
      "loss": 0.5617,
      "step": 72
    },
    {
      "epoch": 0.02394227615611676,
      "grad_norm": 0.6808409690856934,
      "learning_rate": 5.4016204861458444e-05,
      "loss": 0.5357,
      "step": 73
    },
    {
      "epoch": 0.02427025254181699,
      "grad_norm": 0.5417987704277039,
      "learning_rate": 5.201560468140443e-05,
      "loss": 0.5375,
      "step": 74
    },
    {
      "epoch": 0.02459822892751722,
      "grad_norm": 0.5455000996589661,
      "learning_rate": 5.0015004501350405e-05,
      "loss": 0.5362,
      "step": 75
    },
    {
      "epoch": 0.02492620531321745,
      "grad_norm": 0.49334102869033813,
      "learning_rate": 4.801440432129639e-05,
      "loss": 0.5081,
      "step": 76
    },
    {
      "epoch": 0.025254181698917678,
      "grad_norm": 0.4684203863143921,
      "learning_rate": 4.601380414124238e-05,
      "loss": 0.5061,
      "step": 77
    },
    {
      "epoch": 0.025582158084617907,
      "grad_norm": 0.5156847834587097,
      "learning_rate": 4.401320396118836e-05,
      "loss": 0.5231,
      "step": 78
    },
    {
      "epoch": 0.025910134470318136,
      "grad_norm": 0.5413920283317566,
      "learning_rate": 4.201260378113434e-05,
      "loss": 0.5849,
      "step": 79
    },
    {
      "epoch": 0.026238110856018366,
      "grad_norm": 0.5093967914581299,
      "learning_rate": 4.0012003601080326e-05,
      "loss": 0.497,
      "step": 80
    },
    {
      "epoch": 0.026566087241718595,
      "grad_norm": 0.46262067556381226,
      "learning_rate": 3.801140342102631e-05,
      "loss": 0.5364,
      "step": 81
    },
    {
      "epoch": 0.026894063627418825,
      "grad_norm": 0.6614812612533569,
      "learning_rate": 3.6010803240972294e-05,
      "loss": 0.4989,
      "step": 82
    },
    {
      "epoch": 0.027222040013119054,
      "grad_norm": 0.4883507788181305,
      "learning_rate": 3.401020306091828e-05,
      "loss": 0.5443,
      "step": 83
    },
    {
      "epoch": 0.027550016398819287,
      "grad_norm": 0.5155258774757385,
      "learning_rate": 3.200960288086426e-05,
      "loss": 0.5346,
      "step": 84
    },
    {
      "epoch": 0.027877992784519516,
      "grad_norm": 0.46190178394317627,
      "learning_rate": 3.0009002700810245e-05,
      "loss": 0.5019,
      "step": 85
    },
    {
      "epoch": 0.028205969170219745,
      "grad_norm": 0.6695094108581543,
      "learning_rate": 2.800840252075623e-05,
      "loss": 0.523,
      "step": 86
    },
    {
      "epoch": 0.028533945555919975,
      "grad_norm": 0.4700133204460144,
      "learning_rate": 2.6007802340702216e-05,
      "loss": 0.5288,
      "step": 87
    },
    {
      "epoch": 0.028861921941620204,
      "grad_norm": 0.5050464272499084,
      "learning_rate": 2.4007202160648196e-05,
      "loss": 0.4874,
      "step": 88
    },
    {
      "epoch": 0.029189898327320433,
      "grad_norm": 0.5086123943328857,
      "learning_rate": 2.200660198059418e-05,
      "loss": 0.557,
      "step": 89
    },
    {
      "epoch": 0.029517874713020663,
      "grad_norm": 0.48082900047302246,
      "learning_rate": 2.0006001800540163e-05,
      "loss": 0.5176,
      "step": 90
    },
    {
      "epoch": 0.029845851098720892,
      "grad_norm": 0.4965345561504364,
      "learning_rate": 1.8005401620486147e-05,
      "loss": 0.5113,
      "step": 91
    },
    {
      "epoch": 0.03017382748442112,
      "grad_norm": 0.49173784255981445,
      "learning_rate": 1.600480144043213e-05,
      "loss": 0.491,
      "step": 92
    },
    {
      "epoch": 0.03050180387012135,
      "grad_norm": 0.502700924873352,
      "learning_rate": 1.4004201260378114e-05,
      "loss": 0.522,
      "step": 93
    },
    {
      "epoch": 0.03082978025582158,
      "grad_norm": 0.5490285158157349,
      "learning_rate": 1.2003601080324098e-05,
      "loss": 0.4995,
      "step": 94
    },
    {
      "epoch": 0.03115775664152181,
      "grad_norm": 0.48369327187538147,
      "learning_rate": 1.0003000900270082e-05,
      "loss": 0.5166,
      "step": 95
    },
    {
      "epoch": 0.03148573302722204,
      "grad_norm": 0.6655266880989075,
      "learning_rate": 8.002400720216065e-06,
      "loss": 0.5704,
      "step": 96
    },
    {
      "epoch": 0.03181370941292227,
      "grad_norm": 0.4279884994029999,
      "learning_rate": 6.001800540162049e-06,
      "loss": 0.4882,
      "step": 97
    },
    {
      "epoch": 0.0321416857986225,
      "grad_norm": 0.5384986400604248,
      "learning_rate": 4.001200360108033e-06,
      "loss": 0.5809,
      "step": 98
    },
    {
      "epoch": 0.03246966218432273,
      "grad_norm": 0.4719259738922119,
      "learning_rate": 2.0006001800540163e-06,
      "loss": 0.5762,
      "step": 99
    },
    {
      "epoch": 0.032797638570022956,
      "grad_norm": 0.5332183241844177,
      "learning_rate": 0.0,
      "loss": 0.4694,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.686572160719258e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}