{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.050793650793650794,
  "eval_steps": 25,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005079365079365079,
      "grad_norm": 6.519351482391357,
      "learning_rate": 2e-05,
      "loss": 3.2267,
      "step": 1
    },
    {
      "epoch": 0.0005079365079365079,
      "eval_loss": 3.624514102935791,
      "eval_runtime": 204.3923,
      "eval_samples_per_second": 4.056,
      "eval_steps_per_second": 2.03,
      "step": 1
    },
    {
      "epoch": 0.0010158730158730158,
      "grad_norm": 5.146887302398682,
      "learning_rate": 4e-05,
      "loss": 3.3216,
      "step": 2
    },
    {
      "epoch": 0.0015238095238095239,
      "grad_norm": 5.531928062438965,
      "learning_rate": 6e-05,
      "loss": 3.0883,
      "step": 3
    },
    {
      "epoch": 0.0020317460317460317,
      "grad_norm": 5.524338245391846,
      "learning_rate": 8e-05,
      "loss": 3.7995,
      "step": 4
    },
    {
      "epoch": 0.0025396825396825397,
      "grad_norm": 13.655096054077148,
      "learning_rate": 0.0001,
      "loss": 3.1211,
      "step": 5
    },
    {
      "epoch": 0.0030476190476190477,
      "grad_norm": 4.864871501922607,
      "learning_rate": 0.00012,
      "loss": 3.0722,
      "step": 6
    },
    {
      "epoch": 0.0035555555555555557,
      "grad_norm": 3.7362592220306396,
      "learning_rate": 0.00014,
      "loss": 3.1339,
      "step": 7
    },
    {
      "epoch": 0.004063492063492063,
      "grad_norm": 3.1778581142425537,
      "learning_rate": 0.00016,
      "loss": 1.9299,
      "step": 8
    },
    {
      "epoch": 0.004571428571428572,
      "grad_norm": 1.8088997602462769,
      "learning_rate": 0.00018,
      "loss": 1.8856,
      "step": 9
    },
    {
      "epoch": 0.005079365079365079,
      "grad_norm": 1.6604986190795898,
      "learning_rate": 0.0002,
      "loss": 1.6712,
      "step": 10
    },
    {
      "epoch": 0.005587301587301587,
      "grad_norm": 0.8797962069511414,
      "learning_rate": 0.0001999390827019096,
      "loss": 1.8232,
      "step": 11
    },
    {
      "epoch": 0.006095238095238095,
      "grad_norm": 0.8502254486083984,
      "learning_rate": 0.00019975640502598244,
      "loss": 1.82,
      "step": 12
    },
    {
      "epoch": 0.006603174603174603,
      "grad_norm": 1.8626749515533447,
      "learning_rate": 0.00019945218953682734,
      "loss": 1.4507,
      "step": 13
    },
    {
      "epoch": 0.0071111111111111115,
      "grad_norm": 0.8453308939933777,
      "learning_rate": 0.00019902680687415705,
      "loss": 1.5455,
      "step": 14
    },
    {
      "epoch": 0.007619047619047619,
      "grad_norm": 0.7060232162475586,
      "learning_rate": 0.00019848077530122083,
      "loss": 1.9394,
      "step": 15
    },
    {
      "epoch": 0.008126984126984127,
      "grad_norm": 0.6864155530929565,
      "learning_rate": 0.00019781476007338058,
      "loss": 1.3181,
      "step": 16
    },
    {
      "epoch": 0.008634920634920634,
      "grad_norm": 0.5969262719154358,
      "learning_rate": 0.00019702957262759965,
      "loss": 1.4341,
      "step": 17
    },
    {
      "epoch": 0.009142857142857144,
      "grad_norm": 0.31484541296958923,
      "learning_rate": 0.0001961261695938319,
      "loss": 1.4729,
      "step": 18
    },
    {
      "epoch": 0.009650793650793651,
      "grad_norm": 0.46714216470718384,
      "learning_rate": 0.00019510565162951537,
      "loss": 2.0658,
      "step": 19
    },
    {
      "epoch": 0.010158730158730159,
      "grad_norm": 0.44908955693244934,
      "learning_rate": 0.00019396926207859084,
      "loss": 1.3463,
      "step": 20
    },
    {
      "epoch": 0.010666666666666666,
      "grad_norm": 0.6508448719978333,
      "learning_rate": 0.00019271838545667876,
      "loss": 1.3049,
      "step": 21
    },
    {
      "epoch": 0.011174603174603174,
      "grad_norm": 0.5306481719017029,
      "learning_rate": 0.0001913545457642601,
      "loss": 1.34,
      "step": 22
    },
    {
      "epoch": 0.011682539682539683,
      "grad_norm": 0.5218005776405334,
      "learning_rate": 0.0001898794046299167,
      "loss": 1.4621,
      "step": 23
    },
    {
      "epoch": 0.01219047619047619,
      "grad_norm": 0.4745350480079651,
      "learning_rate": 0.00018829475928589271,
      "loss": 1.5099,
      "step": 24
    },
    {
      "epoch": 0.012698412698412698,
      "grad_norm": 0.6343680620193481,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.1358,
      "step": 25
    },
    {
      "epoch": 0.012698412698412698,
      "eval_loss": 1.5563476085662842,
      "eval_runtime": 206.0859,
      "eval_samples_per_second": 4.023,
      "eval_steps_per_second": 2.014,
      "step": 25
    },
    {
      "epoch": 0.013206349206349206,
      "grad_norm": 0.3028874695301056,
      "learning_rate": 0.0001848048096156426,
      "loss": 1.6123,
      "step": 26
    },
    {
      "epoch": 0.013714285714285714,
      "grad_norm": 0.5397087335586548,
      "learning_rate": 0.00018290375725550417,
      "loss": 1.6102,
      "step": 27
    },
    {
      "epoch": 0.014222222222222223,
      "grad_norm": 0.28948265314102173,
      "learning_rate": 0.00018090169943749476,
      "loss": 1.3875,
      "step": 28
    },
    {
      "epoch": 0.01473015873015873,
      "grad_norm": 0.41503822803497314,
      "learning_rate": 0.00017880107536067218,
      "loss": 1.5284,
      "step": 29
    },
    {
      "epoch": 0.015238095238095238,
      "grad_norm": 0.6742813587188721,
      "learning_rate": 0.0001766044443118978,
      "loss": 1.3041,
      "step": 30
    },
    {
      "epoch": 0.015746031746031747,
      "grad_norm": 0.35028955340385437,
      "learning_rate": 0.00017431448254773944,
      "loss": 1.5403,
      "step": 31
    },
    {
      "epoch": 0.016253968253968253,
      "grad_norm": 0.39901459217071533,
      "learning_rate": 0.0001719339800338651,
      "loss": 1.1394,
      "step": 32
    },
    {
      "epoch": 0.016761904761904763,
      "grad_norm": 0.9433032274246216,
      "learning_rate": 0.00016946583704589973,
      "loss": 2.1009,
      "step": 33
    },
    {
      "epoch": 0.01726984126984127,
      "grad_norm": 0.2524099051952362,
      "learning_rate": 0.00016691306063588583,
      "loss": 1.1299,
      "step": 34
    },
    {
      "epoch": 0.017777777777777778,
      "grad_norm": 0.548650324344635,
      "learning_rate": 0.00016427876096865394,
      "loss": 1.3585,
      "step": 35
    },
    {
      "epoch": 0.018285714285714287,
      "grad_norm": 0.6572702527046204,
      "learning_rate": 0.0001615661475325658,
      "loss": 1.2422,
      "step": 36
    },
    {
      "epoch": 0.018793650793650793,
      "grad_norm": 0.4808460772037506,
      "learning_rate": 0.00015877852522924732,
      "loss": 1.6923,
      "step": 37
    },
    {
      "epoch": 0.019301587301587302,
      "grad_norm": 0.4411121904850006,
      "learning_rate": 0.0001559192903470747,
      "loss": 1.2018,
      "step": 38
    },
    {
      "epoch": 0.019809523809523808,
      "grad_norm": 0.6042914986610413,
      "learning_rate": 0.0001529919264233205,
      "loss": 1.5242,
      "step": 39
    },
    {
      "epoch": 0.020317460317460317,
      "grad_norm": 0.4709426462650299,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.6164,
      "step": 40
    },
    {
      "epoch": 0.020825396825396827,
      "grad_norm": 0.307210236787796,
      "learning_rate": 0.00014694715627858908,
      "loss": 1.642,
      "step": 41
    },
    {
      "epoch": 0.021333333333333333,
      "grad_norm": 0.3629468083381653,
      "learning_rate": 0.00014383711467890774,
      "loss": 1.3277,
      "step": 42
    },
    {
      "epoch": 0.021841269841269842,
      "grad_norm": 0.47343459725379944,
      "learning_rate": 0.00014067366430758004,
      "loss": 1.3657,
      "step": 43
    },
    {
      "epoch": 0.022349206349206348,
      "grad_norm": 0.5083032250404358,
      "learning_rate": 0.00013746065934159123,
      "loss": 1.7898,
      "step": 44
    },
    {
      "epoch": 0.022857142857142857,
      "grad_norm": 0.34503334760665894,
      "learning_rate": 0.00013420201433256689,
      "loss": 1.4534,
      "step": 45
    },
    {
      "epoch": 0.023365079365079366,
      "grad_norm": 0.513176679611206,
      "learning_rate": 0.00013090169943749476,
      "loss": 2.0591,
      "step": 46
    },
    {
      "epoch": 0.023873015873015872,
      "grad_norm": 0.6394305229187012,
      "learning_rate": 0.0001275637355816999,
      "loss": 1.4114,
      "step": 47
    },
    {
      "epoch": 0.02438095238095238,
      "grad_norm": 0.3904706537723541,
      "learning_rate": 0.00012419218955996676,
      "loss": 1.468,
      "step": 48
    },
    {
      "epoch": 0.024888888888888887,
      "grad_norm": 0.33670979738235474,
      "learning_rate": 0.00012079116908177593,
      "loss": 1.4328,
      "step": 49
    },
    {
      "epoch": 0.025396825396825397,
      "grad_norm": 0.31365063786506653,
      "learning_rate": 0.00011736481776669306,
      "loss": 1.2578,
      "step": 50
    },
    {
      "epoch": 0.025396825396825397,
      "eval_loss": 1.503420352935791,
      "eval_runtime": 206.1156,
      "eval_samples_per_second": 4.022,
      "eval_steps_per_second": 2.013,
      "step": 50
    },
    {
      "epoch": 0.025904761904761906,
      "grad_norm": 0.33596453070640564,
      "learning_rate": 0.00011391731009600654,
      "loss": 1.5421,
      "step": 51
    },
    {
      "epoch": 0.026412698412698412,
      "grad_norm": 0.2696133852005005,
      "learning_rate": 0.00011045284632676536,
      "loss": 1.3148,
      "step": 52
    },
    {
      "epoch": 0.02692063492063492,
      "grad_norm": 0.5372976660728455,
      "learning_rate": 0.00010697564737441252,
      "loss": 1.64,
      "step": 53
    },
    {
      "epoch": 0.027428571428571427,
      "grad_norm": 0.6545993089675903,
      "learning_rate": 0.00010348994967025012,
      "loss": 1.2776,
      "step": 54
    },
    {
      "epoch": 0.027936507936507936,
      "grad_norm": 0.2829376757144928,
      "learning_rate": 0.0001,
      "loss": 1.2245,
      "step": 55
    },
    {
      "epoch": 0.028444444444444446,
      "grad_norm": 0.3656099736690521,
      "learning_rate": 9.651005032974994e-05,
      "loss": 1.4617,
      "step": 56
    },
    {
      "epoch": 0.02895238095238095,
      "grad_norm": 0.3836618959903717,
      "learning_rate": 9.302435262558747e-05,
      "loss": 1.2219,
      "step": 57
    },
    {
      "epoch": 0.02946031746031746,
      "grad_norm": 0.30446094274520874,
      "learning_rate": 8.954715367323468e-05,
      "loss": 1.5095,
      "step": 58
    },
    {
      "epoch": 0.029968253968253967,
      "grad_norm": 0.4856981635093689,
      "learning_rate": 8.608268990399349e-05,
      "loss": 1.5771,
      "step": 59
    },
    {
      "epoch": 0.030476190476190476,
      "grad_norm": 0.45834746956825256,
      "learning_rate": 8.263518223330697e-05,
      "loss": 1.3313,
      "step": 60
    },
    {
      "epoch": 0.030984126984126985,
      "grad_norm": 0.3143262267112732,
      "learning_rate": 7.920883091822408e-05,
      "loss": 1.1435,
      "step": 61
    },
    {
      "epoch": 0.031492063492063495,
      "grad_norm": 0.40068405866622925,
      "learning_rate": 7.580781044003324e-05,
      "loss": 1.6526,
      "step": 62
    },
    {
      "epoch": 0.032,
      "grad_norm": 0.2322355955839157,
      "learning_rate": 7.243626441830009e-05,
      "loss": 1.2496,
      "step": 63
    },
    {
      "epoch": 0.032507936507936507,
      "grad_norm": 0.44400423765182495,
      "learning_rate": 6.909830056250527e-05,
      "loss": 1.3121,
      "step": 64
    },
    {
      "epoch": 0.03301587301587302,
      "grad_norm": 0.46300458908081055,
      "learning_rate": 6.579798566743314e-05,
      "loss": 1.5739,
      "step": 65
    },
    {
      "epoch": 0.033523809523809525,
      "grad_norm": 0.27108630537986755,
      "learning_rate": 6.25393406584088e-05,
      "loss": 0.9874,
      "step": 66
    },
    {
      "epoch": 0.03403174603174603,
      "grad_norm": 0.23532073199748993,
      "learning_rate": 5.9326335692419995e-05,
      "loss": 1.2079,
      "step": 67
    },
    {
      "epoch": 0.03453968253968254,
      "grad_norm": 0.4134567379951477,
      "learning_rate": 5.616288532109225e-05,
      "loss": 1.5086,
      "step": 68
    },
    {
      "epoch": 0.03504761904761905,
      "grad_norm": 0.3667893707752228,
      "learning_rate": 5.305284372141095e-05,
      "loss": 1.5459,
      "step": 69
    },
    {
      "epoch": 0.035555555555555556,
      "grad_norm": 0.5127963423728943,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.4526,
      "step": 70
    },
    {
      "epoch": 0.03606349206349206,
      "grad_norm": 0.23248711228370667,
      "learning_rate": 4.700807357667952e-05,
      "loss": 1.7219,
      "step": 71
    },
    {
      "epoch": 0.036571428571428574,
      "grad_norm": 0.36493247747421265,
      "learning_rate": 4.4080709652925336e-05,
      "loss": 1.2866,
      "step": 72
    },
    {
      "epoch": 0.03707936507936508,
      "grad_norm": 0.3120146691799164,
      "learning_rate": 4.12214747707527e-05,
      "loss": 1.7468,
      "step": 73
    },
    {
      "epoch": 0.037587301587301586,
      "grad_norm": 0.2617102265357971,
      "learning_rate": 3.843385246743417e-05,
      "loss": 1.3033,
      "step": 74
    },
    {
      "epoch": 0.0380952380952381,
      "grad_norm": 0.37346601486206055,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 1.3576,
      "step": 75
    },
    {
      "epoch": 0.0380952380952381,
      "eval_loss": 1.4916026592254639,
      "eval_runtime": 206.1501,
      "eval_samples_per_second": 4.021,
      "eval_steps_per_second": 2.013,
      "step": 75
    },
    {
      "epoch": 0.038603174603174605,
      "grad_norm": 0.28713932633399963,
      "learning_rate": 3.308693936411421e-05,
      "loss": 1.5865,
      "step": 76
    },
    {
      "epoch": 0.03911111111111111,
      "grad_norm": 0.26906633377075195,
      "learning_rate": 3.053416295410026e-05,
      "loss": 1.1854,
      "step": 77
    },
    {
      "epoch": 0.039619047619047616,
      "grad_norm": 0.4078941345214844,
      "learning_rate": 2.8066019966134904e-05,
      "loss": 1.2432,
      "step": 78
    },
    {
      "epoch": 0.04012698412698413,
      "grad_norm": 0.32490774989128113,
      "learning_rate": 2.5685517452260567e-05,
      "loss": 1.4465,
      "step": 79
    },
    {
      "epoch": 0.040634920634920635,
      "grad_norm": 0.30676373839378357,
      "learning_rate": 2.339555568810221e-05,
      "loss": 1.4783,
      "step": 80
    },
    {
      "epoch": 0.04114285714285714,
      "grad_norm": 0.3845832943916321,
      "learning_rate": 2.119892463932781e-05,
      "loss": 1.3254,
      "step": 81
    },
    {
      "epoch": 0.041650793650793654,
      "grad_norm": 0.41841885447502136,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 1.756,
      "step": 82
    },
    {
      "epoch": 0.04215873015873016,
      "grad_norm": 0.26209527254104614,
      "learning_rate": 1.7096242744495837e-05,
      "loss": 1.1009,
      "step": 83
    },
    {
      "epoch": 0.042666666666666665,
      "grad_norm": 0.4069371819496155,
      "learning_rate": 1.5195190384357404e-05,
      "loss": 1.3217,
      "step": 84
    },
    {
      "epoch": 0.04317460317460318,
      "grad_norm": 0.29204556345939636,
      "learning_rate": 1.339745962155613e-05,
      "loss": 1.437,
      "step": 85
    },
    {
      "epoch": 0.043682539682539684,
      "grad_norm": 0.36702778935432434,
      "learning_rate": 1.1705240714107302e-05,
      "loss": 1.2403,
      "step": 86
    },
    {
      "epoch": 0.04419047619047619,
      "grad_norm": 0.2762695252895355,
      "learning_rate": 1.0120595370083318e-05,
      "loss": 1.2892,
      "step": 87
    },
    {
      "epoch": 0.044698412698412696,
      "grad_norm": 0.30418360233306885,
      "learning_rate": 8.645454235739903e-06,
      "loss": 1.4427,
      "step": 88
    },
    {
      "epoch": 0.04520634920634921,
      "grad_norm": 0.30312514305114746,
      "learning_rate": 7.281614543321269e-06,
      "loss": 1.4674,
      "step": 89
    },
    {
      "epoch": 0.045714285714285714,
      "grad_norm": 0.36299508810043335,
      "learning_rate": 6.030737921409169e-06,
      "loss": 1.2849,
      "step": 90
    },
    {
      "epoch": 0.04622222222222222,
      "grad_norm": 0.3190608024597168,
      "learning_rate": 4.8943483704846475e-06,
      "loss": 1.3682,
      "step": 91
    },
    {
      "epoch": 0.04673015873015873,
      "grad_norm": 0.27337679266929626,
      "learning_rate": 3.873830406168111e-06,
      "loss": 1.2428,
      "step": 92
    },
    {
      "epoch": 0.04723809523809524,
      "grad_norm": 0.3793995976448059,
      "learning_rate": 2.970427372400353e-06,
      "loss": 1.9111,
      "step": 93
    },
    {
      "epoch": 0.047746031746031745,
      "grad_norm": 0.3148786723613739,
      "learning_rate": 2.1852399266194314e-06,
      "loss": 1.2274,
      "step": 94
    },
    {
      "epoch": 0.04825396825396826,
      "grad_norm": 0.487860769033432,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 1.401,
      "step": 95
    },
    {
      "epoch": 0.04876190476190476,
      "grad_norm": 0.2578515410423279,
      "learning_rate": 9.731931258429638e-07,
      "loss": 1.0545,
      "step": 96
    },
    {
      "epoch": 0.04926984126984127,
      "grad_norm": 0.30165234208106995,
      "learning_rate": 5.478104631726711e-07,
      "loss": 1.0555,
      "step": 97
    },
    {
      "epoch": 0.049777777777777775,
      "grad_norm": 0.27550289034843445,
      "learning_rate": 2.4359497401758024e-07,
      "loss": 1.542,
      "step": 98
    },
    {
      "epoch": 0.05028571428571429,
      "grad_norm": 0.21497561037540436,
      "learning_rate": 6.09172980904238e-08,
      "loss": 1.19,
      "step": 99
    },
    {
      "epoch": 0.050793650793650794,
      "grad_norm": 0.5045850872993469,
      "learning_rate": 0.0,
      "loss": 1.5234,
      "step": 100
    },
    {
      "epoch": 0.050793650793650794,
      "eval_loss": 1.4889129400253296,
      "eval_runtime": 206.2008,
      "eval_samples_per_second": 4.02,
      "eval_steps_per_second": 2.013,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.318461275897856e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}