{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.49930871025083945,
  "eval_steps": 16,
  "global_step": 79,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006320363420896702,
      "grad_norm": 1.03125,
      "learning_rate": 2e-05,
      "loss": 0.5558,
      "step": 1
    },
    {
      "epoch": 0.006320363420896702,
      "eval_loss": 0.5296231508255005,
      "eval_runtime": 52.0012,
      "eval_samples_per_second": 20.5,
      "eval_steps_per_second": 20.5,
      "step": 1
    },
    {
      "epoch": 0.012640726841793404,
      "grad_norm": 0.96484375,
      "learning_rate": 4e-05,
      "loss": 0.5376,
      "step": 2
    },
    {
      "epoch": 0.018961090262690106,
      "grad_norm": 0.9609375,
      "learning_rate": 6e-05,
      "loss": 0.5124,
      "step": 3
    },
    {
      "epoch": 0.025281453683586808,
      "grad_norm": 0.71484375,
      "learning_rate": 8e-05,
      "loss": 0.4336,
      "step": 4
    },
    {
      "epoch": 0.03160181710448351,
      "grad_norm": 0.427734375,
      "learning_rate": 0.0001,
      "loss": 0.332,
      "step": 5
    },
    {
      "epoch": 0.03792218052538021,
      "grad_norm": 0.326171875,
      "learning_rate": 0.00012,
      "loss": 0.2481,
      "step": 6
    },
    {
      "epoch": 0.04424254394627691,
      "grad_norm": 0.34375,
      "learning_rate": 0.00014,
      "loss": 0.225,
      "step": 7
    },
    {
      "epoch": 0.050562907367173615,
      "grad_norm": 0.30078125,
      "learning_rate": 0.00016,
      "loss": 0.1996,
      "step": 8
    },
    {
      "epoch": 0.05688327078807032,
      "grad_norm": 0.298828125,
      "learning_rate": 0.00018,
      "loss": 0.1811,
      "step": 9
    },
    {
      "epoch": 0.06320363420896702,
      "grad_norm": 0.240234375,
      "learning_rate": 0.0002,
      "loss": 0.1933,
      "step": 10
    },
    {
      "epoch": 0.06952399762986372,
      "grad_norm": 0.267578125,
      "learning_rate": 0.00019999770790755575,
      "loss": 0.2048,
      "step": 11
    },
    {
      "epoch": 0.07584436105076042,
      "grad_norm": 0.2177734375,
      "learning_rate": 0.00019999083173529673,
      "loss": 0.1728,
      "step": 12
    },
    {
      "epoch": 0.08216472447165712,
      "grad_norm": 0.1748046875,
      "learning_rate": 0.00019997937179843937,
      "loss": 0.1804,
      "step": 13
    },
    {
      "epoch": 0.08848508789255383,
      "grad_norm": 0.1826171875,
      "learning_rate": 0.0001999633286223284,
      "loss": 0.1894,
      "step": 14
    },
    {
      "epoch": 0.09480545131345053,
      "grad_norm": 0.15234375,
      "learning_rate": 0.00019994270294241266,
      "loss": 0.1633,
      "step": 15
    },
    {
      "epoch": 0.10112581473434723,
      "grad_norm": 0.1455078125,
      "learning_rate": 0.00019991749570421146,
      "loss": 0.1574,
      "step": 16
    },
    {
      "epoch": 0.10112581473434723,
      "eval_loss": 0.16320638358592987,
      "eval_runtime": 56.0359,
      "eval_samples_per_second": 19.024,
      "eval_steps_per_second": 19.024,
      "step": 16
    },
    {
      "epoch": 0.10744617815524393,
      "grad_norm": 0.1328125,
      "learning_rate": 0.0001998877080632712,
      "loss": 0.1589,
      "step": 17
    },
    {
      "epoch": 0.11376654157614063,
      "grad_norm": 0.1650390625,
      "learning_rate": 0.00019985334138511237,
      "loss": 0.1718,
      "step": 18
    },
    {
      "epoch": 0.12008690499703734,
      "grad_norm": 0.1455078125,
      "learning_rate": 0.00019981439724516716,
      "loss": 0.156,
      "step": 19
    },
    {
      "epoch": 0.12640726841793404,
      "grad_norm": 0.162109375,
      "learning_rate": 0.0001997708774287068,
      "loss": 0.1781,
      "step": 20
    },
    {
      "epoch": 0.13272763183883074,
      "grad_norm": 0.1416015625,
      "learning_rate": 0.00019972278393076023,
      "loss": 0.1347,
      "step": 21
    },
    {
      "epoch": 0.13904799525972744,
      "grad_norm": 0.130859375,
      "learning_rate": 0.0001996701189560223,
      "loss": 0.1389,
      "step": 22
    },
    {
      "epoch": 0.14536835868062414,
      "grad_norm": 0.138671875,
      "learning_rate": 0.00019961288491875278,
      "loss": 0.1418,
      "step": 23
    },
    {
      "epoch": 0.15168872210152085,
      "grad_norm": 0.11279296875,
      "learning_rate": 0.00019955108444266585,
      "loss": 0.1269,
      "step": 24
    },
    {
      "epoch": 0.15800908552241755,
      "grad_norm": 0.1435546875,
      "learning_rate": 0.00019948472036080949,
      "loss": 0.1659,
      "step": 25
    },
    {
      "epoch": 0.16432944894331425,
      "grad_norm": 0.13671875,
      "learning_rate": 0.00019941379571543596,
      "loss": 0.124,
      "step": 26
    },
    {
      "epoch": 0.17064981236421095,
      "grad_norm": 0.1396484375,
      "learning_rate": 0.00019933831375786216,
      "loss": 0.1423,
      "step": 27
    },
    {
      "epoch": 0.17697017578510765,
      "grad_norm": 0.1494140625,
      "learning_rate": 0.00019925827794832056,
      "loss": 0.1394,
      "step": 28
    },
    {
      "epoch": 0.18329053920600435,
      "grad_norm": 0.1279296875,
      "learning_rate": 0.00019917369195580063,
      "loss": 0.1168,
      "step": 29
    },
    {
      "epoch": 0.18961090262690106,
      "grad_norm": 0.1435546875,
      "learning_rate": 0.00019908455965788067,
      "loss": 0.147,
      "step": 30
    },
    {
      "epoch": 0.19593126604779776,
      "grad_norm": 0.1318359375,
      "learning_rate": 0.00019899088514055004,
      "loss": 0.13,
      "step": 31
    },
    {
      "epoch": 0.20225162946869446,
      "grad_norm": 0.11865234375,
      "learning_rate": 0.00019889267269802176,
      "loss": 0.1279,
      "step": 32
    },
    {
      "epoch": 0.20225162946869446,
      "eval_loss": 0.137903094291687,
      "eval_runtime": 55.5398,
      "eval_samples_per_second": 19.193,
      "eval_steps_per_second": 19.193,
      "step": 32
    },
    {
      "epoch": 0.20857199288959116,
      "grad_norm": 0.125,
      "learning_rate": 0.00019878992683253582,
      "loss": 0.123,
      "step": 33
    },
    {
      "epoch": 0.21489235631048786,
      "grad_norm": 0.125,
      "learning_rate": 0.00019868265225415265,
      "loss": 0.1264,
      "step": 34
    },
    {
      "epoch": 0.22121271973138457,
      "grad_norm": 0.1279296875,
      "learning_rate": 0.00019857085388053723,
      "loss": 0.1295,
      "step": 35
    },
    {
      "epoch": 0.22753308315228127,
      "grad_norm": 0.138671875,
      "learning_rate": 0.00019845453683673368,
      "loss": 0.1448,
      "step": 36
    },
    {
      "epoch": 0.23385344657317797,
      "grad_norm": 0.126953125,
      "learning_rate": 0.00019833370645493047,
      "loss": 0.1293,
      "step": 37
    },
    {
      "epoch": 0.24017380999407467,
      "grad_norm": 0.130859375,
      "learning_rate": 0.0001982083682742156,
      "loss": 0.1387,
      "step": 38
    },
    {
      "epoch": 0.24649417341497137,
      "grad_norm": 0.10888671875,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.1027,
      "step": 39
    },
    {
      "epoch": 0.2528145368358681,
      "grad_norm": 0.1240234375,
      "learning_rate": 0.00019794419170536916,
      "loss": 0.1166,
      "step": 40
    },
    {
      "epoch": 0.2591349002567648,
      "grad_norm": 0.1337890625,
      "learning_rate": 0.00019780536542758,
      "loss": 0.1218,
      "step": 41
    },
    {
      "epoch": 0.2654552636776615,
      "grad_norm": 0.11865234375,
      "learning_rate": 0.00019766205557100868,
      "loss": 0.1291,
      "step": 42
    },
    {
      "epoch": 0.2717756270985582,
      "grad_norm": 0.138671875,
      "learning_rate": 0.00019751426870524407,
      "loss": 0.1409,
      "step": 43
    },
    {
      "epoch": 0.2780959905194549,
      "grad_norm": 0.12109375,
      "learning_rate": 0.00019736201160510931,
      "loss": 0.1275,
      "step": 44
    },
    {
      "epoch": 0.2844163539403516,
      "grad_norm": 0.125,
      "learning_rate": 0.0001972052912503514,
      "loss": 0.1319,
      "step": 45
    },
    {
      "epoch": 0.2907367173612483,
      "grad_norm": 0.12158203125,
      "learning_rate": 0.00019704411482532116,
      "loss": 0.134,
      "step": 46
    },
    {
      "epoch": 0.297057080782145,
      "grad_norm": 0.119140625,
      "learning_rate": 0.00019687848971864389,
      "loss": 0.1334,
      "step": 47
    },
    {
      "epoch": 0.3033774442030417,
      "grad_norm": 0.119140625,
      "learning_rate": 0.0001967084235228807,
      "loss": 0.1166,
      "step": 48
    },
    {
      "epoch": 0.3033774442030417,
      "eval_loss": 0.12646569311618805,
      "eval_runtime": 55.7378,
      "eval_samples_per_second": 19.125,
      "eval_steps_per_second": 19.125,
      "step": 48
    },
    {
      "epoch": 0.3096978076239384,
      "grad_norm": 0.12109375,
      "learning_rate": 0.00019653392403418043,
      "loss": 0.1242,
      "step": 49
    },
    {
      "epoch": 0.3160181710448351,
      "grad_norm": 0.1201171875,
      "learning_rate": 0.0001963549992519223,
      "loss": 0.1309,
      "step": 50
    },
    {
      "epoch": 0.3223385344657318,
      "grad_norm": 0.1044921875,
      "learning_rate": 0.00019617165737834916,
      "loss": 0.1041,
      "step": 51
    },
    {
      "epoch": 0.3286588978866285,
      "grad_norm": 0.1318359375,
      "learning_rate": 0.0001959839068181914,
      "loss": 0.1219,
      "step": 52
    },
    {
      "epoch": 0.3349792613075252,
      "grad_norm": 0.12109375,
      "learning_rate": 0.00019579175617828187,
      "loss": 0.1421,
      "step": 53
    },
    {
      "epoch": 0.3412996247284219,
      "grad_norm": 0.11767578125,
      "learning_rate": 0.00019559521426716118,
      "loss": 0.1176,
      "step": 54
    },
    {
      "epoch": 0.3476199881493186,
      "grad_norm": 0.119140625,
      "learning_rate": 0.0001953942900946739,
      "loss": 0.1206,
      "step": 55
    },
    {
      "epoch": 0.3539403515702153,
      "grad_norm": 0.12158203125,
      "learning_rate": 0.00019518899287155556,
      "loss": 0.1174,
      "step": 56
    },
    {
      "epoch": 0.360260714991112,
      "grad_norm": 0.1181640625,
      "learning_rate": 0.0001949793320090105,
      "loss": 0.1228,
      "step": 57
    },
    {
      "epoch": 0.3665810784120087,
      "grad_norm": 0.13671875,
      "learning_rate": 0.00019476531711828027,
      "loss": 0.125,
      "step": 58
    },
    {
      "epoch": 0.3729014418329054,
      "grad_norm": 0.11962890625,
      "learning_rate": 0.0001945469580102031,
      "loss": 0.1094,
      "step": 59
    },
    {
      "epoch": 0.3792218052538021,
      "grad_norm": 0.10498046875,
      "learning_rate": 0.0001943242646947643,
      "loss": 0.0983,
      "step": 60
    },
    {
      "epoch": 0.3855421686746988,
      "grad_norm": 0.1220703125,
      "learning_rate": 0.00019409724738063714,
      "loss": 0.1164,
      "step": 61
    },
    {
      "epoch": 0.3918625320955955,
      "grad_norm": 0.11767578125,
      "learning_rate": 0.00019386591647471506,
      "loss": 0.1124,
      "step": 62
    },
    {
      "epoch": 0.3981828955164922,
      "grad_norm": 0.11669921875,
      "learning_rate": 0.00019363028258163447,
      "loss": 0.1188,
      "step": 63
    },
    {
      "epoch": 0.4045032589373889,
      "grad_norm": 0.12255859375,
      "learning_rate": 0.00019339035650328869,
      "loss": 0.1335,
      "step": 64
    },
    {
      "epoch": 0.4045032589373889,
      "eval_loss": 0.11877521872520447,
      "eval_runtime": 55.4677,
      "eval_samples_per_second": 19.218,
      "eval_steps_per_second": 19.218,
      "step": 64
    },
    {
      "epoch": 0.4108236223582856,
      "grad_norm": 0.1279296875,
      "learning_rate": 0.0001931461492383327,
      "loss": 0.1447,
      "step": 65
    },
    {
      "epoch": 0.4171439857791823,
      "grad_norm": 0.1044921875,
      "learning_rate": 0.00019289767198167916,
      "loss": 0.1004,
      "step": 66
    },
    {
      "epoch": 0.423464349200079,
      "grad_norm": 0.1171875,
      "learning_rate": 0.00019264493612398481,
      "loss": 0.1228,
      "step": 67
    },
    {
      "epoch": 0.42978471262097573,
      "grad_norm": 0.099609375,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0963,
      "step": 68
    },
    {
      "epoch": 0.43610507604187243,
      "grad_norm": 0.1015625,
      "learning_rate": 0.0001921267351436808,
      "loss": 0.1025,
      "step": 69
    },
    {
      "epoch": 0.44242543946276913,
      "grad_norm": 0.123046875,
      "learning_rate": 0.0001918612937763622,
      "loss": 0.124,
      "step": 70
    },
    {
      "epoch": 0.44874580288366583,
      "grad_norm": 0.109375,
      "learning_rate": 0.00019159164131749587,
      "loss": 0.1203,
      "step": 71
    },
    {
      "epoch": 0.45506616630456254,
      "grad_norm": 0.109375,
      "learning_rate": 0.00019131779012844912,
      "loss": 0.1052,
      "step": 72
    },
    {
      "epoch": 0.46138652972545924,
      "grad_norm": 0.1162109375,
      "learning_rate": 0.00019103975276306678,
      "loss": 0.1181,
      "step": 73
    },
    {
      "epoch": 0.46770689314635594,
      "grad_norm": 0.11181640625,
      "learning_rate": 0.00019075754196709572,
      "loss": 0.1065,
      "step": 74
    },
    {
      "epoch": 0.47402725656725264,
      "grad_norm": 0.109375,
      "learning_rate": 0.0001904711706776006,
      "loss": 0.1075,
      "step": 75
    },
    {
      "epoch": 0.48034761998814934,
      "grad_norm": 0.11865234375,
      "learning_rate": 0.00019018065202237083,
      "loss": 0.1182,
      "step": 76
    },
    {
      "epoch": 0.48666798340904605,
      "grad_norm": 0.09814453125,
      "learning_rate": 0.00018988599931931866,
      "loss": 0.0913,
      "step": 77
    },
    {
      "epoch": 0.49298834682994275,
      "grad_norm": 0.10791015625,
      "learning_rate": 0.0001895872260758688,
      "loss": 0.103,
      "step": 78
    },
    {
      "epoch": 0.49930871025083945,
      "grad_norm": 0.111328125,
      "learning_rate": 0.00018928434598833912,
      "loss": 0.1106,
      "step": 79
    }
  ],
  "logging_steps": 1,
  "max_steps": 474,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 79,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3440458340728832e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}