{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.18066847335140018,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018066847335140017,
      "grad_norm": 2.8401210755443786,
      "learning_rate": 0.0,
      "loss": 0.8251,
      "step": 1
    },
    {
      "epoch": 0.0036133694670280035,
      "grad_norm": 2.884596771811998,
      "learning_rate": 1.7857142857142857e-06,
      "loss": 0.8284,
      "step": 2
    },
    {
      "epoch": 0.005420054200542005,
      "grad_norm": 2.885426730353446,
      "learning_rate": 3.5714285714285714e-06,
      "loss": 0.8426,
      "step": 3
    },
    {
      "epoch": 0.007226738934056007,
      "grad_norm": 2.651910724864975,
      "learning_rate": 5.357142857142857e-06,
      "loss": 0.8329,
      "step": 4
    },
    {
      "epoch": 0.009033423667570008,
      "grad_norm": 2.138099539200911,
      "learning_rate": 7.142857142857143e-06,
      "loss": 0.8087,
      "step": 5
    },
    {
      "epoch": 0.01084010840108401,
      "grad_norm": 1.5516804515831568,
      "learning_rate": 8.92857142857143e-06,
      "loss": 0.7878,
      "step": 6
    },
    {
      "epoch": 0.012646793134598013,
      "grad_norm": 1.3537216088647457,
      "learning_rate": 1.0714285714285714e-05,
      "loss": 0.76,
      "step": 7
    },
    {
      "epoch": 0.014453477868112014,
      "grad_norm": 2.2798033166818095,
      "learning_rate": 1.25e-05,
      "loss": 0.7502,
      "step": 8
    },
    {
      "epoch": 0.016260162601626018,
      "grad_norm": 2.4280919600136315,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.7449,
      "step": 9
    },
    {
      "epoch": 0.018066847335140017,
      "grad_norm": 1.931081683969551,
      "learning_rate": 1.6071428571428572e-05,
      "loss": 0.7271,
      "step": 10
    },
    {
      "epoch": 0.01987353206865402,
      "grad_norm": 2.033957326273334,
      "learning_rate": 1.785714285714286e-05,
      "loss": 0.7224,
      "step": 11
    },
    {
      "epoch": 0.02168021680216802,
      "grad_norm": 1.7440303482576578,
      "learning_rate": 1.9642857142857145e-05,
      "loss": 0.7373,
      "step": 12
    },
    {
      "epoch": 0.023486901535682024,
      "grad_norm": 1.1423427090231095,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.7033,
      "step": 13
    },
    {
      "epoch": 0.025293586269196026,
      "grad_norm": 0.9350758811837806,
      "learning_rate": 2.3214285714285715e-05,
      "loss": 0.6886,
      "step": 14
    },
    {
      "epoch": 0.02710027100271003,
      "grad_norm": 0.9041529205527444,
      "learning_rate": 2.5e-05,
      "loss": 0.6858,
      "step": 15
    },
    {
      "epoch": 0.028906955736224028,
      "grad_norm": 0.7774159470583337,
      "learning_rate": 2.6785714285714288e-05,
      "loss": 0.676,
      "step": 16
    },
    {
      "epoch": 0.03071364046973803,
      "grad_norm": 0.6642849851627606,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.6816,
      "step": 17
    },
    {
      "epoch": 0.032520325203252036,
      "grad_norm": 0.6696862181877565,
      "learning_rate": 3.0357142857142857e-05,
      "loss": 0.6727,
      "step": 18
    },
    {
      "epoch": 0.03432700993676603,
      "grad_norm": 0.6199596133483118,
      "learning_rate": 3.2142857142857144e-05,
      "loss": 0.6678,
      "step": 19
    },
    {
      "epoch": 0.036133694670280034,
      "grad_norm": 0.5724104094717255,
      "learning_rate": 3.392857142857143e-05,
      "loss": 0.6448,
      "step": 20
    },
    {
      "epoch": 0.037940379403794036,
      "grad_norm": 0.5762214978597714,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.6506,
      "step": 21
    },
    {
      "epoch": 0.03974706413730804,
      "grad_norm": 0.5444644294356963,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.6413,
      "step": 22
    },
    {
      "epoch": 0.04155374887082204,
      "grad_norm": 0.4801008888914334,
      "learning_rate": 3.928571428571429e-05,
      "loss": 0.6425,
      "step": 23
    },
    {
      "epoch": 0.04336043360433604,
      "grad_norm": 0.4780671650041637,
      "learning_rate": 4.107142857142857e-05,
      "loss": 0.6489,
      "step": 24
    },
    {
      "epoch": 0.045167118337850046,
      "grad_norm": 0.5145358853730851,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.6306,
      "step": 25
    },
    {
      "epoch": 0.04697380307136405,
      "grad_norm": 0.4229563893889767,
      "learning_rate": 4.464285714285715e-05,
      "loss": 0.6453,
      "step": 26
    },
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 0.4021332182222708,
      "learning_rate": 4.642857142857143e-05,
      "loss": 0.6251,
      "step": 27
    },
    {
      "epoch": 0.05058717253839205,
      "grad_norm": 0.48615223659558016,
      "learning_rate": 4.8214285714285716e-05,
      "loss": 0.6272,
      "step": 28
    },
    {
      "epoch": 0.052393857271906055,
      "grad_norm": 0.46304419453924084,
      "learning_rate": 5e-05,
      "loss": 0.6385,
      "step": 29
    },
    {
      "epoch": 0.05420054200542006,
      "grad_norm": 0.4055914485047887,
      "learning_rate": 4.999955240022902e-05,
      "loss": 0.6406,
      "step": 30
    },
    {
      "epoch": 0.05600722673893405,
      "grad_norm": 0.4320919468210144,
      "learning_rate": 4.999820961694372e-05,
      "loss": 0.6303,
      "step": 31
    },
    {
      "epoch": 0.057813911472448055,
      "grad_norm": 0.4042983593828653,
      "learning_rate": 4.999597169822646e-05,
      "loss": 0.6186,
      "step": 32
    },
    {
      "epoch": 0.05962059620596206,
      "grad_norm": 0.4310835292518631,
      "learning_rate": 4.9992838724212585e-05,
      "loss": 0.6287,
      "step": 33
    },
    {
      "epoch": 0.06142728093947606,
      "grad_norm": 0.412271814827728,
      "learning_rate": 4.9988810807087584e-05,
      "loss": 0.6165,
      "step": 34
    },
    {
      "epoch": 0.06323396567299007,
      "grad_norm": 0.40598837987994935,
      "learning_rate": 4.998388809108303e-05,
      "loss": 0.622,
      "step": 35
    },
    {
      "epoch": 0.06504065040650407,
      "grad_norm": 0.4223908220324365,
      "learning_rate": 4.997807075247146e-05,
      "loss": 0.6189,
      "step": 36
    },
    {
      "epoch": 0.06684733514001806,
      "grad_norm": 0.38197899028265064,
      "learning_rate": 4.997135899956001e-05,
      "loss": 0.623,
      "step": 37
    },
    {
      "epoch": 0.06865401987353206,
      "grad_norm": 0.3885330150920031,
      "learning_rate": 4.9963753072683025e-05,
      "loss": 0.6164,
      "step": 38
    },
    {
      "epoch": 0.07046070460704607,
      "grad_norm": 0.41115019726029983,
      "learning_rate": 4.9955253244193375e-05,
      "loss": 0.6182,
      "step": 39
    },
    {
      "epoch": 0.07226738934056007,
      "grad_norm": 0.3495037257115665,
      "learning_rate": 4.994585981845278e-05,
      "loss": 0.6072,
      "step": 40
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.3973831198418077,
      "learning_rate": 4.9935573131820854e-05,
      "loss": 0.6137,
      "step": 41
    },
    {
      "epoch": 0.07588075880758807,
      "grad_norm": 0.3339390206679997,
      "learning_rate": 4.9924393552643075e-05,
      "loss": 0.6064,
      "step": 42
    },
    {
      "epoch": 0.07768744354110207,
      "grad_norm": 0.3384678373992373,
      "learning_rate": 4.991232148123761e-05,
      "loss": 0.606,
      "step": 43
    },
    {
      "epoch": 0.07949412827461608,
      "grad_norm": 0.3764492630812678,
      "learning_rate": 4.989935734988098e-05,
      "loss": 0.601,
      "step": 44
    },
    {
      "epoch": 0.08130081300813008,
      "grad_norm": 0.35707353533847597,
      "learning_rate": 4.988550162279255e-05,
      "loss": 0.6097,
      "step": 45
    },
    {
      "epoch": 0.08310749774164408,
      "grad_norm": 0.34040533355863656,
      "learning_rate": 4.987075479611796e-05,
      "loss": 0.6094,
      "step": 46
    },
    {
      "epoch": 0.08491418247515808,
      "grad_norm": 0.34496537693497575,
      "learning_rate": 4.985511739791129e-05,
      "loss": 0.6129,
      "step": 47
    },
    {
      "epoch": 0.08672086720867209,
      "grad_norm": 0.3655410266089117,
      "learning_rate": 4.983858998811622e-05,
      "loss": 0.5994,
      "step": 48
    },
    {
      "epoch": 0.08852755194218609,
      "grad_norm": 0.32151319632227454,
      "learning_rate": 4.9821173158545936e-05,
      "loss": 0.607,
      "step": 49
    },
    {
      "epoch": 0.09033423667570009,
      "grad_norm": 0.3573869377855791,
      "learning_rate": 4.980286753286195e-05,
      "loss": 0.6067,
      "step": 50
    },
    {
      "epoch": 0.0921409214092141,
      "grad_norm": 0.3601371463623409,
      "learning_rate": 4.978367376655177e-05,
      "loss": 0.5965,
      "step": 51
    },
    {
      "epoch": 0.0939476061427281,
      "grad_norm": 0.3288839599265164,
      "learning_rate": 4.976359254690543e-05,
      "loss": 0.6128,
      "step": 52
    },
    {
      "epoch": 0.0957542908762421,
      "grad_norm": 0.3899144366212297,
      "learning_rate": 4.974262459299087e-05,
      "loss": 0.5992,
      "step": 53
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.31373036051997816,
      "learning_rate": 4.972077065562821e-05,
      "loss": 0.5894,
      "step": 54
    },
    {
      "epoch": 0.0993676603432701,
      "grad_norm": 0.3317064945312652,
      "learning_rate": 4.969803151736284e-05,
      "loss": 0.6046,
      "step": 55
    },
    {
      "epoch": 0.1011743450767841,
      "grad_norm": 0.4008096818415782,
      "learning_rate": 4.9674407992437394e-05,
      "loss": 0.6091,
      "step": 56
    },
    {
      "epoch": 0.10298102981029811,
      "grad_norm": 0.32205121061079506,
      "learning_rate": 4.964990092676263e-05,
      "loss": 0.5936,
      "step": 57
    },
    {
      "epoch": 0.10478771454381211,
      "grad_norm": 0.3834592472356572,
      "learning_rate": 4.962451119788709e-05,
      "loss": 0.6035,
      "step": 58
    },
    {
      "epoch": 0.10659439927732611,
      "grad_norm": 0.4364607834229955,
      "learning_rate": 4.959823971496574e-05,
      "loss": 0.5895,
      "step": 59
    },
    {
      "epoch": 0.10840108401084012,
      "grad_norm": 0.39798614932188364,
      "learning_rate": 4.957108741872736e-05,
      "loss": 0.5903,
      "step": 60
    },
    {
      "epoch": 0.1102077687443541,
      "grad_norm": 0.4078983073259993,
      "learning_rate": 4.954305528144085e-05,
      "loss": 0.594,
      "step": 61
    },
    {
      "epoch": 0.1120144534778681,
      "grad_norm": 0.5064139886264023,
      "learning_rate": 4.9514144306880506e-05,
      "loss": 0.5989,
      "step": 62
    },
    {
      "epoch": 0.11382113821138211,
      "grad_norm": 0.3049367414530056,
      "learning_rate": 4.9484355530289944e-05,
      "loss": 0.5982,
      "step": 63
    },
    {
      "epoch": 0.11562782294489611,
      "grad_norm": 0.45932591541254997,
      "learning_rate": 4.9453690018345144e-05,
      "loss": 0.598,
      "step": 64
    },
    {
      "epoch": 0.11743450767841011,
      "grad_norm": 0.34088884376991047,
      "learning_rate": 4.9422148869116194e-05,
      "loss": 0.5914,
      "step": 65
    },
    {
      "epoch": 0.11924119241192412,
      "grad_norm": 0.4408196994719187,
      "learning_rate": 4.938973321202799e-05,
      "loss": 0.5943,
      "step": 66
    },
    {
      "epoch": 0.12104787714543812,
      "grad_norm": 0.4034840944061305,
      "learning_rate": 4.935644420781978e-05,
      "loss": 0.5852,
      "step": 67
    },
    {
      "epoch": 0.12285456187895212,
      "grad_norm": 0.3532258693927161,
      "learning_rate": 4.932228304850363e-05,
      "loss": 0.6003,
      "step": 68
    },
    {
      "epoch": 0.12466124661246612,
      "grad_norm": 0.4041417285254443,
      "learning_rate": 4.928725095732169e-05,
      "loss": 0.6019,
      "step": 69
    },
    {
      "epoch": 0.12646793134598014,
      "grad_norm": 0.338119605860217,
      "learning_rate": 4.925134918870245e-05,
      "loss": 0.6056,
      "step": 70
    },
    {
      "epoch": 0.12827461607949414,
      "grad_norm": 0.2924641177682486,
      "learning_rate": 4.9214579028215776e-05,
      "loss": 0.5784,
      "step": 71
    },
    {
      "epoch": 0.13008130081300814,
      "grad_norm": 0.37576892630911196,
      "learning_rate": 4.917694179252692e-05,
      "loss": 0.5966,
      "step": 72
    },
    {
      "epoch": 0.13188798554652212,
      "grad_norm": 0.3066908816324021,
      "learning_rate": 4.91384388293493e-05,
      "loss": 0.5944,
      "step": 73
    },
    {
      "epoch": 0.13369467028003612,
      "grad_norm": 0.3296017371410444,
      "learning_rate": 4.909907151739633e-05,
      "loss": 0.5863,
      "step": 74
    },
    {
      "epoch": 0.13550135501355012,
      "grad_norm": 0.3510646842800697,
      "learning_rate": 4.9058841266332e-05,
      "loss": 0.5854,
      "step": 75
    },
    {
      "epoch": 0.13730803974706413,
      "grad_norm": 0.33050013383675975,
      "learning_rate": 4.90177495167204e-05,
      "loss": 0.5816,
      "step": 76
    },
    {
      "epoch": 0.13911472448057813,
      "grad_norm": 0.336545072709173,
      "learning_rate": 4.897579773997415e-05,
      "loss": 0.5768,
      "step": 77
    },
    {
      "epoch": 0.14092140921409213,
      "grad_norm": 0.3401542906091868,
      "learning_rate": 4.893298743830168e-05,
      "loss": 0.5877,
      "step": 78
    },
    {
      "epoch": 0.14272809394760613,
      "grad_norm": 0.30833272476392615,
      "learning_rate": 4.888932014465352e-05,
      "loss": 0.5949,
      "step": 79
    },
    {
      "epoch": 0.14453477868112014,
      "grad_norm": 0.40829913126640544,
      "learning_rate": 4.88447974226673e-05,
      "loss": 0.6045,
      "step": 80
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 0.3247095550760803,
      "learning_rate": 4.879942086661184e-05,
      "loss": 0.5901,
      "step": 81
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.40484730371305205,
      "learning_rate": 4.875319210133004e-05,
      "loss": 0.5825,
      "step": 82
    },
    {
      "epoch": 0.14995483288166214,
      "grad_norm": 0.37019522474324174,
      "learning_rate": 4.870611278218066e-05,
      "loss": 0.5918,
      "step": 83
    },
    {
      "epoch": 0.15176151761517614,
      "grad_norm": 0.3654744041300334,
      "learning_rate": 4.865818459497911e-05,
      "loss": 0.5865,
      "step": 84
    },
    {
      "epoch": 0.15356820234869015,
      "grad_norm": 0.3001653084612634,
      "learning_rate": 4.860940925593703e-05,
      "loss": 0.5889,
      "step": 85
    },
    {
      "epoch": 0.15537488708220415,
      "grad_norm": 0.3463142769052332,
      "learning_rate": 4.8559788511600876e-05,
      "loss": 0.5881,
      "step": 86
    },
    {
      "epoch": 0.15718157181571815,
      "grad_norm": 0.3221292284344934,
      "learning_rate": 4.850932413878934e-05,
      "loss": 0.5901,
      "step": 87
    },
    {
      "epoch": 0.15898825654923215,
      "grad_norm": 0.33253415770699135,
      "learning_rate": 4.8458017944529776e-05,
      "loss": 0.5952,
      "step": 88
    },
    {
      "epoch": 0.16079494128274616,
      "grad_norm": 0.37021022779245716,
      "learning_rate": 4.8405871765993433e-05,
      "loss": 0.5928,
      "step": 89
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 0.3197338147243217,
      "learning_rate": 4.8352887470429726e-05,
      "loss": 0.5837,
      "step": 90
    },
    {
      "epoch": 0.16440831074977416,
      "grad_norm": 0.35706780201968874,
      "learning_rate": 4.8299066955099335e-05,
      "loss": 0.5811,
      "step": 91
    },
    {
      "epoch": 0.16621499548328816,
      "grad_norm": 0.3730971582648582,
      "learning_rate": 4.8244412147206284e-05,
      "loss": 0.586,
      "step": 92
    },
    {
      "epoch": 0.16802168021680217,
      "grad_norm": 0.33467520904104064,
      "learning_rate": 4.8188925003828945e-05,
      "loss": 0.5919,
      "step": 93
    },
    {
      "epoch": 0.16982836495031617,
      "grad_norm": 0.41181901183464464,
      "learning_rate": 4.813260751184992e-05,
      "loss": 0.5922,
      "step": 94
    },
    {
      "epoch": 0.17163504968383017,
      "grad_norm": 0.31057237794043846,
      "learning_rate": 4.807546168788494e-05,
      "loss": 0.5835,
      "step": 95
    },
    {
      "epoch": 0.17344173441734417,
      "grad_norm": 0.4045185112342142,
      "learning_rate": 4.8017489578210604e-05,
      "loss": 0.5839,
      "step": 96
    },
    {
      "epoch": 0.17524841915085818,
      "grad_norm": 0.342091450071029,
      "learning_rate": 4.7958693258691167e-05,
      "loss": 0.5891,
      "step": 97
    },
    {
      "epoch": 0.17705510388437218,
      "grad_norm": 0.32193383766669476,
      "learning_rate": 4.7899074834704165e-05,
      "loss": 0.5814,
      "step": 98
    },
    {
      "epoch": 0.17886178861788618,
      "grad_norm": 0.33881983844597735,
      "learning_rate": 4.783863644106502e-05,
      "loss": 0.5951,
      "step": 99
    },
    {
      "epoch": 0.18066847335140018,
      "grad_norm": 0.3141049036238513,
      "learning_rate": 4.7777380241950645e-05,
      "loss": 0.5672,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 553,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 115440686923776.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}