{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 5209,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009599692809830085,
      "grad_norm": 7.563427925109863,
      "learning_rate": 1.47e-05,
      "loss": 20.2245,
      "step": 50
    },
    {
      "epoch": 0.01919938561966017,
      "grad_norm": 29.188539505004883,
      "learning_rate": 2.97e-05,
      "loss": 16.0616,
      "step": 100
    },
    {
      "epoch": 0.028799078429490255,
      "grad_norm": 38.129608154296875,
      "learning_rate": 4.4699999999999996e-05,
      "loss": 12.7127,
      "step": 150
    },
    {
      "epoch": 0.03839877123932034,
      "grad_norm": 27.457260131835938,
      "learning_rate": 5.97e-05,
      "loss": 9.8971,
      "step": 200
    },
    {
      "epoch": 0.047998464049150424,
      "grad_norm": 29.130887985229492,
      "learning_rate": 7.47e-05,
      "loss": 7.5544,
      "step": 250
    },
    {
      "epoch": 0.05759815685898051,
      "grad_norm": 22.884220123291016,
      "learning_rate": 8.969999999999998e-05,
      "loss": 5.7283,
      "step": 300
    },
    {
      "epoch": 0.0671978496688106,
      "grad_norm": 14.968835830688477,
      "learning_rate": 0.00010469999999999998,
      "loss": 4.1701,
      "step": 350
    },
    {
      "epoch": 0.07679754247864068,
      "grad_norm": 7.887697219848633,
      "learning_rate": 0.0001197,
      "loss": 3.0776,
      "step": 400
    },
    {
      "epoch": 0.08639723528847076,
      "grad_norm": 5.031055927276611,
      "learning_rate": 0.0001347,
      "loss": 2.3821,
      "step": 450
    },
    {
      "epoch": 0.09599692809830085,
      "grad_norm": 6.178770542144775,
      "learning_rate": 0.00014969999999999998,
      "loss": 2.005,
      "step": 500
    },
    {
      "epoch": 0.10559662090813093,
      "grad_norm": 5.43004035949707,
      "learning_rate": 0.0001647,
      "loss": 1.7496,
      "step": 550
    },
    {
      "epoch": 0.11519631371796102,
      "grad_norm": 6.949675559997559,
      "learning_rate": 0.00017969999999999998,
      "loss": 1.57,
      "step": 600
    },
    {
      "epoch": 0.12479600652779112,
      "grad_norm": 4.977025508880615,
      "learning_rate": 0.0001947,
      "loss": 1.4294,
      "step": 650
    },
    {
      "epoch": 0.1343956993376212,
      "grad_norm": 9.961807250976562,
      "learning_rate": 0.00020969999999999997,
      "loss": 1.3506,
      "step": 700
    },
    {
      "epoch": 0.14399539214745127,
      "grad_norm": 3.297438383102417,
      "learning_rate": 0.0002247,
      "loss": 1.2624,
      "step": 750
    },
    {
      "epoch": 0.15359508495728136,
      "grad_norm": 3.7409021854400635,
      "learning_rate": 0.0002397,
      "loss": 1.1136,
      "step": 800
    },
    {
      "epoch": 0.16319477776711144,
      "grad_norm": 2.896446466445923,
      "learning_rate": 0.00025469999999999996,
      "loss": 0.9954,
      "step": 850
    },
    {
      "epoch": 0.17279447057694153,
      "grad_norm": 4.742156982421875,
      "learning_rate": 0.0002697,
      "loss": 0.9425,
      "step": 900
    },
    {
      "epoch": 0.1823941633867716,
      "grad_norm": 2.8668880462646484,
      "learning_rate": 0.0002847,
      "loss": 0.8012,
      "step": 950
    },
    {
      "epoch": 0.1919938561966017,
      "grad_norm": 3.0938684940338135,
      "learning_rate": 0.00029969999999999997,
      "loss": 0.6747,
      "step": 1000
    },
    {
      "epoch": 0.20159354900643178,
      "grad_norm": 2.447160005569458,
      "learning_rate": 0.0002965074839629365,
      "loss": 0.5663,
      "step": 1050
    },
    {
      "epoch": 0.21119324181626187,
      "grad_norm": 1.987984299659729,
      "learning_rate": 0.000292943692088382,
      "loss": 0.4893,
      "step": 1100
    },
    {
      "epoch": 0.22079293462609195,
      "grad_norm": 1.7457754611968994,
      "learning_rate": 0.0002893799002138275,
      "loss": 0.438,
      "step": 1150
    },
    {
      "epoch": 0.23039262743592204,
      "grad_norm": 1.5488331317901611,
      "learning_rate": 0.000285816108339273,
      "loss": 0.3947,
      "step": 1200
    },
    {
      "epoch": 0.23999232024575212,
      "grad_norm": 2.7451088428497314,
      "learning_rate": 0.00028225231646471845,
      "loss": 0.3685,
      "step": 1250
    },
    {
      "epoch": 0.24959201305558223,
      "grad_norm": 1.4951989650726318,
      "learning_rate": 0.0002786885245901639,
      "loss": 0.3416,
      "step": 1300
    },
    {
      "epoch": 0.2591917058654123,
      "grad_norm": 1.9799026250839233,
      "learning_rate": 0.0002751247327156094,
      "loss": 0.3128,
      "step": 1350
    },
    {
      "epoch": 0.2687913986752424,
      "grad_norm": 1.9234377145767212,
      "learning_rate": 0.00027156094084105487,
      "loss": 0.2892,
      "step": 1400
    },
    {
      "epoch": 0.27839109148507246,
      "grad_norm": 1.1122220754623413,
      "learning_rate": 0.00026799714896650034,
      "loss": 0.2641,
      "step": 1450
    },
    {
      "epoch": 0.28799078429490255,
      "grad_norm": 1.6626770496368408,
      "learning_rate": 0.0002644333570919458,
      "loss": 0.2503,
      "step": 1500
    },
    {
      "epoch": 0.29759047710473263,
      "grad_norm": 0.8336459398269653,
      "learning_rate": 0.0002608695652173913,
      "loss": 0.2558,
      "step": 1550
    },
    {
      "epoch": 0.3071901699145627,
      "grad_norm": 0.6865236163139343,
      "learning_rate": 0.00025730577334283675,
      "loss": 0.2341,
      "step": 1600
    },
    {
      "epoch": 0.3167898627243928,
      "grad_norm": 0.6718222498893738,
      "learning_rate": 0.0002537419814682822,
      "loss": 0.2129,
      "step": 1650
    },
    {
      "epoch": 0.3263895555342229,
      "grad_norm": 1.026585340499878,
      "learning_rate": 0.0002501781895937277,
      "loss": 0.2072,
      "step": 1700
    },
    {
      "epoch": 0.33598924834405297,
      "grad_norm": 0.6105709671974182,
      "learning_rate": 0.00024661439771917317,
      "loss": 0.2088,
      "step": 1750
    },
    {
      "epoch": 0.34558894115388306,
      "grad_norm": 0.6215556263923645,
      "learning_rate": 0.00024305060584461867,
      "loss": 0.1949,
      "step": 1800
    },
    {
      "epoch": 0.35518863396371314,
      "grad_norm": 0.8784211874008179,
      "learning_rate": 0.00023948681397006414,
      "loss": 0.1872,
      "step": 1850
    },
    {
      "epoch": 0.3647883267735432,
      "grad_norm": 0.6036493182182312,
      "learning_rate": 0.0002359230220955096,
      "loss": 0.1776,
      "step": 1900
    },
    {
      "epoch": 0.3743880195833733,
      "grad_norm": 1.1696622371673584,
      "learning_rate": 0.00023235923022095505,
      "loss": 0.1665,
      "step": 1950
    },
    {
      "epoch": 0.3839877123932034,
      "grad_norm": 0.624737560749054,
      "learning_rate": 0.00022879543834640053,
      "loss": 0.1595,
      "step": 2000
    },
    {
      "epoch": 0.3935874052030335,
      "grad_norm": 0.6369844079017639,
      "learning_rate": 0.00022523164647184602,
      "loss": 0.1548,
      "step": 2050
    },
    {
      "epoch": 0.40318709801286357,
      "grad_norm": 0.4880986511707306,
      "learning_rate": 0.0002216678545972915,
      "loss": 0.1525,
      "step": 2100
    },
    {
      "epoch": 0.41278679082269365,
      "grad_norm": 0.6220801472663879,
      "learning_rate": 0.00021810406272273697,
      "loss": 0.1483,
      "step": 2150
    },
    {
      "epoch": 0.42238648363252373,
      "grad_norm": 0.6783862709999084,
      "learning_rate": 0.00021454027084818244,
      "loss": 0.1469,
      "step": 2200
    },
    {
      "epoch": 0.4319861764423538,
      "grad_norm": 0.9673178195953369,
      "learning_rate": 0.00021097647897362794,
      "loss": 0.1472,
      "step": 2250
    },
    {
      "epoch": 0.4415858692521839,
      "grad_norm": 0.5814102292060852,
      "learning_rate": 0.0002074126870990734,
      "loss": 0.1451,
      "step": 2300
    },
    {
      "epoch": 0.451185562062014,
      "grad_norm": 2.7569072246551514,
      "learning_rate": 0.00020384889522451888,
      "loss": 0.1535,
      "step": 2350
    },
    {
      "epoch": 0.4607852548718441,
      "grad_norm": 0.7196153402328491,
      "learning_rate": 0.00020028510334996435,
      "loss": 0.1564,
      "step": 2400
    },
    {
      "epoch": 0.47038494768167416,
      "grad_norm": 0.44885897636413574,
      "learning_rate": 0.0001967213114754098,
      "loss": 0.1474,
      "step": 2450
    },
    {
      "epoch": 0.47998464049150424,
      "grad_norm": 0.715428352355957,
      "learning_rate": 0.00019315751960085527,
      "loss": 0.1366,
      "step": 2500
    },
    {
      "epoch": 0.4895843333013344,
      "grad_norm": 0.33587202429771423,
      "learning_rate": 0.00018959372772630077,
      "loss": 0.1338,
      "step": 2550
    },
    {
      "epoch": 0.49918402611116447,
      "grad_norm": 0.3589983284473419,
      "learning_rate": 0.00018602993585174624,
      "loss": 0.1256,
      "step": 2600
    },
    {
      "epoch": 0.5087837189209945,
      "grad_norm": 0.2169811725616455,
      "learning_rate": 0.0001824661439771917,
      "loss": 0.1286,
      "step": 2650
    },
    {
      "epoch": 0.5183834117308246,
      "grad_norm": 0.4184163510799408,
      "learning_rate": 0.00017890235210263718,
      "loss": 0.1246,
      "step": 2700
    },
    {
      "epoch": 0.5279831045406547,
      "grad_norm": 0.33475199341773987,
      "learning_rate": 0.00017533856022808268,
      "loss": 0.1249,
      "step": 2750
    },
    {
      "epoch": 0.5375827973504848,
      "grad_norm": 0.5484436750411987,
      "learning_rate": 0.00017177476835352815,
      "loss": 0.125,
      "step": 2800
    },
    {
      "epoch": 0.5471824901603148,
      "grad_norm": 0.34854593873023987,
      "learning_rate": 0.00016821097647897363,
      "loss": 0.1277,
      "step": 2850
    },
    {
      "epoch": 0.5567821829701449,
      "grad_norm": 0.3453426659107208,
      "learning_rate": 0.0001646471846044191,
      "loss": 0.1271,
      "step": 2900
    },
    {
      "epoch": 0.566381875779975,
      "grad_norm": 0.34477025270462036,
      "learning_rate": 0.00016108339272986454,
      "loss": 0.1211,
      "step": 2950
    },
    {
      "epoch": 0.5759815685898051,
      "grad_norm": 0.2906150221824646,
      "learning_rate": 0.00015751960085531,
      "loss": 0.124,
      "step": 3000
    },
    {
      "epoch": 0.5855812613996352,
      "grad_norm": 0.2288372963666916,
      "learning_rate": 0.0001539558089807555,
      "loss": 0.1189,
      "step": 3050
    },
    {
      "epoch": 0.5951809542094653,
      "grad_norm": 0.3227977752685547,
      "learning_rate": 0.00015039201710620098,
      "loss": 0.1227,
      "step": 3100
    },
    {
      "epoch": 0.6047806470192953,
      "grad_norm": 0.40704479813575745,
      "learning_rate": 0.00014682822523164645,
      "loss": 0.1202,
      "step": 3150
    },
    {
      "epoch": 0.6143803398291254,
      "grad_norm": 0.3058551847934723,
      "learning_rate": 0.00014326443335709193,
      "loss": 0.1178,
      "step": 3200
    },
    {
      "epoch": 0.6239800326389555,
      "grad_norm": 0.2437949925661087,
      "learning_rate": 0.00013970064148253743,
      "loss": 0.1156,
      "step": 3250
    },
    {
      "epoch": 0.6335797254487856,
      "grad_norm": 0.24965952336788177,
      "learning_rate": 0.0001361368496079829,
      "loss": 0.1131,
      "step": 3300
    },
    {
      "epoch": 0.6431794182586157,
      "grad_norm": 0.4167115092277527,
      "learning_rate": 0.00013257305773342834,
      "loss": 0.115,
      "step": 3350
    },
    {
      "epoch": 0.6527791110684458,
      "grad_norm": 0.30340147018432617,
      "learning_rate": 0.00012900926585887384,
      "loss": 0.1131,
      "step": 3400
    },
    {
      "epoch": 0.6623788038782759,
      "grad_norm": 0.43558454513549805,
      "learning_rate": 0.0001254454739843193,
      "loss": 0.113,
      "step": 3450
    },
    {
      "epoch": 0.6719784966881059,
      "grad_norm": 0.30567434430122375,
      "learning_rate": 0.00012188168210976478,
      "loss": 0.1142,
      "step": 3500
    },
    {
      "epoch": 0.681578189497936,
      "grad_norm": 0.28799161314964294,
      "learning_rate": 0.00011831789023521026,
      "loss": 0.1111,
      "step": 3550
    },
    {
      "epoch": 0.6911778823077661,
      "grad_norm": 0.28393957018852234,
      "learning_rate": 0.00011475409836065573,
      "loss": 0.1117,
      "step": 3600
    },
    {
      "epoch": 0.7007775751175962,
      "grad_norm": 0.27800044417381287,
      "learning_rate": 0.0001111903064861012,
      "loss": 0.111,
      "step": 3650
    },
    {
      "epoch": 0.7103772679274263,
      "grad_norm": 0.19541418552398682,
      "learning_rate": 0.00010762651461154668,
      "loss": 0.1092,
      "step": 3700
    },
    {
      "epoch": 0.7199769607372564,
      "grad_norm": 0.24023820459842682,
      "learning_rate": 0.00010406272273699216,
      "loss": 0.1099,
      "step": 3750
    },
    {
      "epoch": 0.7295766535470865,
      "grad_norm": 0.259033203125,
      "learning_rate": 0.00010049893086243763,
      "loss": 0.109,
      "step": 3800
    },
    {
      "epoch": 0.7391763463569165,
      "grad_norm": 0.25941726565361023,
      "learning_rate": 9.69351389878831e-05,
      "loss": 0.106,
      "step": 3850
    },
    {
      "epoch": 0.7487760391667466,
      "grad_norm": 0.15513530373573303,
      "learning_rate": 9.337134711332857e-05,
      "loss": 0.1056,
      "step": 3900
    },
    {
      "epoch": 0.7583757319765767,
      "grad_norm": 0.2611596882343292,
      "learning_rate": 8.980755523877404e-05,
      "loss": 0.1065,
      "step": 3950
    },
    {
      "epoch": 0.7679754247864068,
      "grad_norm": 0.2952909469604492,
      "learning_rate": 8.624376336421953e-05,
      "loss": 0.1066,
      "step": 4000
    },
    {
      "epoch": 0.7775751175962369,
      "grad_norm": 0.251472532749176,
      "learning_rate": 8.2679971489665e-05,
      "loss": 0.1082,
      "step": 4050
    },
    {
      "epoch": 0.787174810406067,
      "grad_norm": 0.1387886255979538,
      "learning_rate": 7.911617961511047e-05,
      "loss": 0.1055,
      "step": 4100
    },
    {
      "epoch": 0.796774503215897,
      "grad_norm": 0.28730371594429016,
      "learning_rate": 7.555238774055594e-05,
      "loss": 0.1071,
      "step": 4150
    },
    {
      "epoch": 0.8063741960257271,
      "grad_norm": 0.12195300310850143,
      "learning_rate": 7.198859586600141e-05,
      "loss": 0.1048,
      "step": 4200
    },
    {
      "epoch": 0.8159738888355572,
      "grad_norm": 0.22190533578395844,
      "learning_rate": 6.84248039914469e-05,
      "loss": 0.1025,
      "step": 4250
    },
    {
      "epoch": 0.8255735816453873,
      "grad_norm": 0.1989029198884964,
      "learning_rate": 6.486101211689237e-05,
      "loss": 0.1015,
      "step": 4300
    },
    {
      "epoch": 0.8351732744552174,
      "grad_norm": 0.1682548075914383,
      "learning_rate": 6.129722024233784e-05,
      "loss": 0.1033,
      "step": 4350
    },
    {
      "epoch": 0.8447729672650475,
      "grad_norm": 0.13227292895317078,
      "learning_rate": 5.7733428367783314e-05,
      "loss": 0.1038,
      "step": 4400
    },
    {
      "epoch": 0.8543726600748776,
      "grad_norm": 0.19235797226428986,
      "learning_rate": 5.416963649322879e-05,
      "loss": 0.1034,
      "step": 4450
    },
    {
      "epoch": 0.8639723528847076,
      "grad_norm": 0.1321435123682022,
      "learning_rate": 5.060584461867427e-05,
      "loss": 0.1029,
      "step": 4500
    },
    {
      "epoch": 0.8735720456945377,
      "grad_norm": 0.1909589022397995,
      "learning_rate": 4.7042052744119735e-05,
      "loss": 0.1045,
      "step": 4550
    },
    {
      "epoch": 0.8831717385043678,
      "grad_norm": 0.15285654366016388,
      "learning_rate": 4.3478260869565214e-05,
      "loss": 0.1032,
      "step": 4600
    },
    {
      "epoch": 0.8927714313141979,
      "grad_norm": 0.1674521118402481,
      "learning_rate": 3.9914468995010685e-05,
      "loss": 0.1023,
      "step": 4650
    },
    {
      "epoch": 0.902371124124028,
      "grad_norm": 0.11908634752035141,
      "learning_rate": 3.6350677120456164e-05,
      "loss": 0.1021,
      "step": 4700
    },
    {
      "epoch": 0.9119708169338581,
      "grad_norm": 0.1627221256494522,
      "learning_rate": 3.2786885245901635e-05,
      "loss": 0.1019,
      "step": 4750
    },
    {
      "epoch": 0.9215705097436881,
      "grad_norm": 0.17971652746200562,
      "learning_rate": 2.922309337134711e-05,
      "loss": 0.1003,
      "step": 4800
    },
    {
      "epoch": 0.9311702025535182,
      "grad_norm": 0.1855141818523407,
      "learning_rate": 2.5659301496792585e-05,
      "loss": 0.1036,
      "step": 4850
    },
    {
      "epoch": 0.9407698953633483,
      "grad_norm": 0.13592451810836792,
      "learning_rate": 2.209550962223806e-05,
      "loss": 0.101,
      "step": 4900
    },
    {
      "epoch": 0.9503695881731784,
      "grad_norm": 0.18601875007152557,
      "learning_rate": 1.8531717747683532e-05,
      "loss": 0.1019,
      "step": 4950
    },
    {
      "epoch": 0.9599692809830085,
      "grad_norm": 0.15403127670288086,
      "learning_rate": 1.4967925873129009e-05,
      "loss": 0.0992,
      "step": 5000
    },
    {
      "epoch": 0.9695689737928387,
      "grad_norm": 0.13198044896125793,
      "learning_rate": 1.1404133998574482e-05,
      "loss": 0.1023,
      "step": 5050
    },
    {
      "epoch": 0.9791686666026688,
      "grad_norm": 0.139701709151268,
      "learning_rate": 7.840342124019957e-06,
      "loss": 0.1015,
      "step": 5100
    },
    {
      "epoch": 0.9887683594124989,
      "grad_norm": 0.1343325823545456,
      "learning_rate": 4.276550249465431e-06,
      "loss": 0.1036,
      "step": 5150
    },
    {
      "epoch": 0.9983680522223289,
      "grad_norm": 0.1440255045890808,
      "learning_rate": 7.127583749109051e-07,
      "loss": 0.1022,
      "step": 5200
    }
  ],
  "logging_steps": 50,
  "max_steps": 5209,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1425482385706189e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}