{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03965551772481474,
  "eval_steps": 50,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004005607850991388,
      "grad_norm": 2.4344990253448486,
      "learning_rate": 5e-05,
      "loss": 3.1012,
      "step": 1
    },
    {
      "epoch": 0.0004005607850991388,
      "eval_loss": 3.0820372104644775,
      "eval_runtime": 28.6956,
      "eval_samples_per_second": 36.661,
      "eval_steps_per_second": 18.33,
      "step": 1
    },
    {
      "epoch": 0.0008011215701982776,
      "grad_norm": 1.7689874172210693,
      "learning_rate": 0.0001,
      "loss": 2.9772,
      "step": 2
    },
    {
      "epoch": 0.0012016823552974164,
      "grad_norm": 2.805964708328247,
      "learning_rate": 0.00015,
      "loss": 3.4926,
      "step": 3
    },
    {
      "epoch": 0.0016022431403965552,
      "grad_norm": 2.956672430038452,
      "learning_rate": 0.0002,
      "loss": 3.6622,
      "step": 4
    },
    {
      "epoch": 0.002002803925495694,
      "grad_norm": 2.5529518127441406,
      "learning_rate": 0.00025,
      "loss": 2.9273,
      "step": 5
    },
    {
      "epoch": 0.002403364710594833,
      "grad_norm": 1.831852912902832,
      "learning_rate": 0.0003,
      "loss": 2.5788,
      "step": 6
    },
    {
      "epoch": 0.0028039254956939716,
      "grad_norm": 1.6226868629455566,
      "learning_rate": 0.00035,
      "loss": 2.5177,
      "step": 7
    },
    {
      "epoch": 0.0032044862807931104,
      "grad_norm": 2.354496955871582,
      "learning_rate": 0.0004,
      "loss": 2.5655,
      "step": 8
    },
    {
      "epoch": 0.0036050470658922492,
      "grad_norm": 2.2879300117492676,
      "learning_rate": 0.00045000000000000004,
      "loss": 2.5502,
      "step": 9
    },
    {
      "epoch": 0.004005607850991388,
      "grad_norm": 2.574815034866333,
      "learning_rate": 0.0005,
      "loss": 2.2454,
      "step": 10
    },
    {
      "epoch": 0.004406168636090527,
      "grad_norm": 1.6621110439300537,
      "learning_rate": 0.0004998442655654946,
      "loss": 1.8034,
      "step": 11
    },
    {
      "epoch": 0.004806729421189666,
      "grad_norm": 1.984192132949829,
      "learning_rate": 0.0004993772562876909,
      "loss": 2.6323,
      "step": 12
    },
    {
      "epoch": 0.0052072902062888045,
      "grad_norm": 2.288874864578247,
      "learning_rate": 0.0004985995540019955,
      "loss": 1.9088,
      "step": 13
    },
    {
      "epoch": 0.005607850991387943,
      "grad_norm": 1.5363634824752808,
      "learning_rate": 0.0004975121276286136,
      "loss": 2.0859,
      "step": 14
    },
    {
      "epoch": 0.006008411776487082,
      "grad_norm": 1.1328516006469727,
      "learning_rate": 0.0004961163319653958,
      "loss": 1.9693,
      "step": 15
    },
    {
      "epoch": 0.006408972561586221,
      "grad_norm": 1.3997936248779297,
      "learning_rate": 0.0004944139059999286,
      "loss": 1.9882,
      "step": 16
    },
    {
      "epoch": 0.00680953334668536,
      "grad_norm": 1.317238688468933,
      "learning_rate": 0.000492406970742972,
      "loss": 1.9312,
      "step": 17
    },
    {
      "epoch": 0.0072100941317844985,
      "grad_norm": 1.458006501197815,
      "learning_rate": 0.0004900980265859448,
      "loss": 2.4625,
      "step": 18
    },
    {
      "epoch": 0.007610654916883637,
      "grad_norm": 0.970038115978241,
      "learning_rate": 0.0004874899501857477,
      "loss": 2.2326,
      "step": 19
    },
    {
      "epoch": 0.008011215701982776,
      "grad_norm": 1.6142843961715698,
      "learning_rate": 0.00048458599088080736,
      "loss": 1.9539,
      "step": 20
    },
    {
      "epoch": 0.008411776487081914,
      "grad_norm": 1.353042483329773,
      "learning_rate": 0.0004813897666428053,
      "loss": 2.335,
      "step": 21
    },
    {
      "epoch": 0.008812337272181054,
      "grad_norm": 1.423920750617981,
      "learning_rate": 0.00047790525956913543,
      "loss": 1.7413,
      "step": 22
    },
    {
      "epoch": 0.009212898057280192,
      "grad_norm": 1.5239485502243042,
      "learning_rate": 0.0004741368109217071,
      "loss": 2.2131,
      "step": 23
    },
    {
      "epoch": 0.009613458842379331,
      "grad_norm": 1.8239572048187256,
      "learning_rate": 0.00047008911571827283,
      "loss": 1.7396,
      "step": 24
    },
    {
      "epoch": 0.01001401962747847,
      "grad_norm": 1.0884772539138794,
      "learning_rate": 0.00046576721688302105,
      "loss": 2.2057,
      "step": 25
    },
    {
      "epoch": 0.010414580412577609,
      "grad_norm": 1.4631233215332031,
      "learning_rate": 0.0004611764989637205,
      "loss": 1.9047,
      "step": 26
    },
    {
      "epoch": 0.010815141197676747,
      "grad_norm": 1.1582131385803223,
      "learning_rate": 0.0004563226814232444,
      "loss": 2.5048,
      "step": 27
    },
    {
      "epoch": 0.011215701982775887,
      "grad_norm": 1.416812777519226,
      "learning_rate": 0.0004512118115138315,
      "loss": 1.8986,
      "step": 28
    },
    {
      "epoch": 0.011616262767875024,
      "grad_norm": 1.1690479516983032,
      "learning_rate": 0.0004458502567429631,
      "loss": 2.1514,
      "step": 29
    },
    {
      "epoch": 0.012016823552974164,
      "grad_norm": 1.16459059715271,
      "learning_rate": 0.00044024469694024196,
      "loss": 1.8639,
      "step": 30
    },
    {
      "epoch": 0.012417384338073302,
      "grad_norm": 1.056779384613037,
      "learning_rate": 0.00043440211593515554,
      "loss": 1.9256,
      "step": 31
    },
    {
      "epoch": 0.012817945123172442,
      "grad_norm": 1.5517312288284302,
      "learning_rate": 0.0004283297928560951,
      "loss": 1.9297,
      "step": 32
    },
    {
      "epoch": 0.01321850590827158,
      "grad_norm": 1.3826098442077637,
      "learning_rate": 0.0004220352930614672,
      "loss": 2.282,
      "step": 33
    },
    {
      "epoch": 0.01361906669337072,
      "grad_norm": 1.194398283958435,
      "learning_rate": 0.00041552645871420013,
      "loss": 2.2492,
      "step": 34
    },
    {
      "epoch": 0.014019627478469857,
      "grad_norm": 1.8520417213439941,
      "learning_rate": 0.00040881139901138467,
      "loss": 2.4,
      "step": 35
    },
    {
      "epoch": 0.014420188263568997,
      "grad_norm": 1.278959035873413,
      "learning_rate": 0.00040189848008122475,
      "loss": 2.1325,
      "step": 36
    },
    {
      "epoch": 0.014820749048668135,
      "grad_norm": 1.786801815032959,
      "learning_rate": 0.00039479631455988334,
      "loss": 2.0348,
      "step": 37
    },
    {
      "epoch": 0.015221309833767275,
      "grad_norm": 1.3184572458267212,
      "learning_rate": 0.0003875137508612103,
      "loss": 2.0454,
      "step": 38
    },
    {
      "epoch": 0.015621870618866412,
      "grad_norm": 1.1530405282974243,
      "learning_rate": 0.00038005986215272055,
      "loss": 2.2434,
      "step": 39
    },
    {
      "epoch": 0.016022431403965552,
      "grad_norm": 1.4723411798477173,
      "learning_rate": 0.0003724439350515571,
      "loss": 1.8833,
      "step": 40
    },
    {
      "epoch": 0.016422992189064692,
      "grad_norm": 1.6857566833496094,
      "learning_rate": 0.0003646754580545226,
      "loss": 2.2384,
      "step": 41
    },
    {
      "epoch": 0.016823552974163828,
      "grad_norm": 1.2251979112625122,
      "learning_rate": 0.000356764109716594,
      "loss": 2.5669,
      "step": 42
    },
    {
      "epoch": 0.017224113759262968,
      "grad_norm": 1.5817160606384277,
      "learning_rate": 0.00034871974659264783,
      "loss": 2.5998,
      "step": 43
    },
    {
      "epoch": 0.017624674544362107,
      "grad_norm": 1.326270580291748,
      "learning_rate": 0.0003405523909574206,
      "loss": 2.2238,
      "step": 44
    },
    {
      "epoch": 0.018025235329461247,
      "grad_norm": 0.9494209885597229,
      "learning_rate": 0.0003322722183190025,
      "loss": 2.0566,
      "step": 45
    },
    {
      "epoch": 0.018425796114560383,
      "grad_norm": 1.1728250980377197,
      "learning_rate": 0.0003238895447414211,
      "loss": 1.697,
      "step": 46
    },
    {
      "epoch": 0.018826356899659523,
      "grad_norm": 1.5986175537109375,
      "learning_rate": 0.0003154148139921102,
      "loss": 1.7549,
      "step": 47
    },
    {
      "epoch": 0.019226917684758663,
      "grad_norm": 1.1737697124481201,
      "learning_rate": 0.00030685858453027663,
      "loss": 1.7618,
      "step": 48
    },
    {
      "epoch": 0.019627478469857802,
      "grad_norm": 1.0616875886917114,
      "learning_rate": 0.0002982315163523742,
      "loss": 2.3967,
      "step": 49
    },
    {
      "epoch": 0.02002803925495694,
      "grad_norm": 1.4347580671310425,
      "learning_rate": 0.000289544357711076,
      "loss": 1.7634,
      "step": 50
    },
    {
      "epoch": 0.02002803925495694,
      "eval_loss": 2.012052536010742,
      "eval_runtime": 28.5887,
      "eval_samples_per_second": 36.798,
      "eval_steps_per_second": 18.399,
      "step": 50
    },
    {
      "epoch": 0.020428600040056078,
      "grad_norm": 1.5467963218688965,
      "learning_rate": 0.0002808079317242896,
      "loss": 2.0926,
      "step": 51
    },
    {
      "epoch": 0.020829160825155218,
      "grad_norm": 1.1608525514602661,
      "learning_rate": 0.0002720331228909005,
      "loss": 1.9368,
      "step": 52
    },
    {
      "epoch": 0.021229721610254357,
      "grad_norm": 1.5125212669372559,
      "learning_rate": 0.00026323086353004075,
      "loss": 2.2591,
      "step": 53
    },
    {
      "epoch": 0.021630282395353494,
      "grad_norm": 1.141327142715454,
      "learning_rate": 0.0002544121201607822,
      "loss": 1.8238,
      "step": 54
    },
    {
      "epoch": 0.022030843180452633,
      "grad_norm": 1.1864770650863647,
      "learning_rate": 0.00024558787983921783,
      "loss": 1.9923,
      "step": 55
    },
    {
      "epoch": 0.022431403965551773,
      "grad_norm": 1.2866952419281006,
      "learning_rate": 0.0002367691364699592,
      "loss": 1.9187,
      "step": 56
    },
    {
      "epoch": 0.022831964750650913,
      "grad_norm": 1.362595558166504,
      "learning_rate": 0.00022796687710909964,
      "loss": 2.0923,
      "step": 57
    },
    {
      "epoch": 0.02323252553575005,
      "grad_norm": 1.3138153553009033,
      "learning_rate": 0.00021919206827571036,
      "loss": 2.0055,
      "step": 58
    },
    {
      "epoch": 0.02363308632084919,
      "grad_norm": 1.1482343673706055,
      "learning_rate": 0.00021045564228892402,
      "loss": 1.9882,
      "step": 59
    },
    {
      "epoch": 0.024033647105948328,
      "grad_norm": 1.2140475511550903,
      "learning_rate": 0.00020176848364762578,
      "loss": 1.725,
      "step": 60
    },
    {
      "epoch": 0.024434207891047468,
      "grad_norm": 1.5149836540222168,
      "learning_rate": 0.00019314141546972343,
      "loss": 2.1587,
      "step": 61
    },
    {
      "epoch": 0.024834768676146604,
      "grad_norm": 1.5307202339172363,
      "learning_rate": 0.00018458518600788986,
      "loss": 2.1868,
      "step": 62
    },
    {
      "epoch": 0.025235329461245744,
      "grad_norm": 1.1949517726898193,
      "learning_rate": 0.00017611045525857898,
      "loss": 2.0899,
      "step": 63
    },
    {
      "epoch": 0.025635890246344883,
      "grad_norm": 1.2019050121307373,
      "learning_rate": 0.0001677277816809975,
      "loss": 1.7959,
      "step": 64
    },
    {
      "epoch": 0.026036451031444023,
      "grad_norm": 1.137641429901123,
      "learning_rate": 0.00015944760904257942,
      "loss": 1.9071,
      "step": 65
    },
    {
      "epoch": 0.02643701181654316,
      "grad_norm": 1.4122196435928345,
      "learning_rate": 0.0001512802534073522,
      "loss": 1.9875,
      "step": 66
    },
    {
      "epoch": 0.0268375726016423,
      "grad_norm": 1.3938771486282349,
      "learning_rate": 0.00014323589028340596,
      "loss": 1.9302,
      "step": 67
    },
    {
      "epoch": 0.02723813338674144,
      "grad_norm": 1.1219323873519897,
      "learning_rate": 0.00013532454194547733,
      "loss": 1.9583,
      "step": 68
    },
    {
      "epoch": 0.02763869417184058,
      "grad_norm": 1.221145749092102,
      "learning_rate": 0.00012755606494844294,
      "loss": 2.1028,
      "step": 69
    },
    {
      "epoch": 0.028039254956939715,
      "grad_norm": 1.6395137310028076,
      "learning_rate": 0.00011994013784727947,
      "loss": 1.955,
      "step": 70
    },
    {
      "epoch": 0.028439815742038854,
      "grad_norm": 1.0482176542282104,
      "learning_rate": 0.00011248624913878966,
      "loss": 2.112,
      "step": 71
    },
    {
      "epoch": 0.028840376527137994,
      "grad_norm": 1.2491412162780762,
      "learning_rate": 0.0001052036854401166,
      "loss": 2.2217,
      "step": 72
    },
    {
      "epoch": 0.029240937312237134,
      "grad_norm": 1.3600395917892456,
      "learning_rate": 9.810151991877531e-05,
      "loss": 2.2656,
      "step": 73
    },
    {
      "epoch": 0.02964149809733627,
      "grad_norm": 1.2350081205368042,
      "learning_rate": 9.118860098861537e-05,
      "loss": 2.0685,
      "step": 74
    },
    {
      "epoch": 0.03004205888243541,
      "grad_norm": 1.2208542823791504,
      "learning_rate": 8.44735412857999e-05,
      "loss": 1.539,
      "step": 75
    },
    {
      "epoch": 0.03044261966753455,
      "grad_norm": 1.370618462562561,
      "learning_rate": 7.79647069385328e-05,
      "loss": 2.0545,
      "step": 76
    },
    {
      "epoch": 0.03084318045263369,
      "grad_norm": 1.1490741968154907,
      "learning_rate": 7.167020714390501e-05,
      "loss": 2.0587,
      "step": 77
    },
    {
      "epoch": 0.031243741237732825,
      "grad_norm": 1.220718502998352,
      "learning_rate": 6.559788406484446e-05,
      "loss": 1.8599,
      "step": 78
    },
    {
      "epoch": 0.031644302022831965,
      "grad_norm": 1.64824378490448,
      "learning_rate": 5.975530305975807e-05,
      "loss": 2.3586,
      "step": 79
    },
    {
      "epoch": 0.032044862807931104,
      "grad_norm": 1.495094656944275,
      "learning_rate": 5.414974325703686e-05,
      "loss": 2.1085,
      "step": 80
    },
    {
      "epoch": 0.032445423593030244,
      "grad_norm": 1.1038875579833984,
      "learning_rate": 4.8788188486168616e-05,
      "loss": 2.1465,
      "step": 81
    },
    {
      "epoch": 0.032845984378129384,
      "grad_norm": 1.450072169303894,
      "learning_rate": 4.367731857675569e-05,
      "loss": 1.9168,
      "step": 82
    },
    {
      "epoch": 0.03324654516322852,
      "grad_norm": 1.2426930665969849,
      "learning_rate": 3.882350103627952e-05,
      "loss": 2.0372,
      "step": 83
    },
    {
      "epoch": 0.033647105948327656,
      "grad_norm": 1.189127802848816,
      "learning_rate": 3.423278311697897e-05,
      "loss": 1.6364,
      "step": 84
    },
    {
      "epoch": 0.034047666733426796,
      "grad_norm": 1.3084362745285034,
      "learning_rate": 2.9910884281727225e-05,
      "loss": 2.0304,
      "step": 85
    },
    {
      "epoch": 0.034448227518525935,
      "grad_norm": 0.7917243838310242,
      "learning_rate": 2.586318907829291e-05,
      "loss": 2.3032,
      "step": 86
    },
    {
      "epoch": 0.034848788303625075,
      "grad_norm": 1.2357211112976074,
      "learning_rate": 2.209474043086457e-05,
      "loss": 1.8531,
      "step": 87
    },
    {
      "epoch": 0.035249349088724215,
      "grad_norm": 1.5522675514221191,
      "learning_rate": 1.861023335719475e-05,
      "loss": 2.0952,
      "step": 88
    },
    {
      "epoch": 0.035649909873823354,
      "grad_norm": 1.166305422782898,
      "learning_rate": 1.5414009119192633e-05,
      "loss": 1.7682,
      "step": 89
    },
    {
      "epoch": 0.036050470658922494,
      "grad_norm": 1.2451746463775635,
      "learning_rate": 1.25100498142523e-05,
      "loss": 1.9993,
      "step": 90
    },
    {
      "epoch": 0.03645103144402163,
      "grad_norm": 1.251763105392456,
      "learning_rate": 9.901973414055187e-06,
      "loss": 1.9152,
      "step": 91
    },
    {
      "epoch": 0.036851592229120766,
      "grad_norm": 1.1293752193450928,
      "learning_rate": 7.593029257027956e-06,
      "loss": 2.0776,
      "step": 92
    },
    {
      "epoch": 0.037252153014219906,
      "grad_norm": 1.1258478164672852,
      "learning_rate": 5.5860940000714015e-06,
      "loss": 2.1167,
      "step": 93
    },
    {
      "epoch": 0.037652713799319046,
      "grad_norm": 1.185185432434082,
      "learning_rate": 3.8836680346041594e-06,
      "loss": 1.8718,
      "step": 94
    },
    {
      "epoch": 0.038053274584418185,
      "grad_norm": 1.2053008079528809,
      "learning_rate": 2.487872371386424e-06,
      "loss": 2.3429,
      "step": 95
    },
    {
      "epoch": 0.038453835369517325,
      "grad_norm": 0.8643404245376587,
      "learning_rate": 1.4004459980045125e-06,
      "loss": 1.8221,
      "step": 96
    },
    {
      "epoch": 0.038854396154616465,
      "grad_norm": 1.4989515542984009,
      "learning_rate": 6.22743712309054e-07,
      "loss": 1.8639,
      "step": 97
    },
    {
      "epoch": 0.039254956939715605,
      "grad_norm": 1.2497055530548096,
      "learning_rate": 1.557344345054501e-07,
      "loss": 2.279,
      "step": 98
    },
    {
      "epoch": 0.03965551772481474,
      "grad_norm": 1.5901930332183838,
      "learning_rate": 0.0,
      "loss": 2.0944,
      "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": 5038480606887936.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}