{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12573344509639564,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016764459346186086,
      "grad_norm": 41.98318099975586,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 7.7669,
      "step": 1
    },
    {
      "epoch": 0.0016764459346186086,
      "eval_loss": 8.831981658935547,
      "eval_runtime": 25.9299,
      "eval_samples_per_second": 19.398,
      "eval_steps_per_second": 9.719,
      "step": 1
    },
    {
      "epoch": 0.003352891869237217,
      "grad_norm": 50.515586853027344,
      "learning_rate": 6.666666666666667e-05,
      "loss": 11.2237,
      "step": 2
    },
    {
      "epoch": 0.005029337803855826,
      "grad_norm": 52.518070220947266,
      "learning_rate": 0.0001,
      "loss": 8.3685,
      "step": 3
    },
    {
      "epoch": 0.006705783738474434,
      "grad_norm": 28.536165237426758,
      "learning_rate": 9.99524110790929e-05,
      "loss": 5.3907,
      "step": 4
    },
    {
      "epoch": 0.008382229673093043,
      "grad_norm": 28.03000259399414,
      "learning_rate": 9.980973490458728e-05,
      "loss": 4.1955,
      "step": 5
    },
    {
      "epoch": 0.010058675607711651,
      "grad_norm": 24.324188232421875,
      "learning_rate": 9.957224306869053e-05,
      "loss": 3.3303,
      "step": 6
    },
    {
      "epoch": 0.01173512154233026,
      "grad_norm": 25.27045440673828,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.5867,
      "step": 7
    },
    {
      "epoch": 0.013411567476948869,
      "grad_norm": 18.81125259399414,
      "learning_rate": 9.881480035599667e-05,
      "loss": 1.4315,
      "step": 8
    },
    {
      "epoch": 0.015088013411567477,
      "grad_norm": 14.121123313903809,
      "learning_rate": 9.829629131445342e-05,
      "loss": 1.0803,
      "step": 9
    },
    {
      "epoch": 0.016764459346186086,
      "grad_norm": 15.772384643554688,
      "learning_rate": 9.768584753741134e-05,
      "loss": 1.0693,
      "step": 10
    },
    {
      "epoch": 0.018440905280804692,
      "grad_norm": 17.11600685119629,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.8722,
      "step": 11
    },
    {
      "epoch": 0.020117351215423303,
      "grad_norm": 13.86662769317627,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.7378,
      "step": 12
    },
    {
      "epoch": 0.02179379715004191,
      "grad_norm": 13.181978225708008,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.6078,
      "step": 13
    },
    {
      "epoch": 0.02347024308466052,
      "grad_norm": 8.900806427001953,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.3962,
      "step": 14
    },
    {
      "epoch": 0.025146689019279127,
      "grad_norm": 12.434109687805176,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.5659,
      "step": 15
    },
    {
      "epoch": 0.026823134953897737,
      "grad_norm": 10.655670166015625,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.6674,
      "step": 16
    },
    {
      "epoch": 0.028499580888516344,
      "grad_norm": 7.57264518737793,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.2832,
      "step": 17
    },
    {
      "epoch": 0.030176026823134954,
      "grad_norm": 8.742619514465332,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.437,
      "step": 18
    },
    {
      "epoch": 0.03185247275775356,
      "grad_norm": 5.534316539764404,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.1241,
      "step": 19
    },
    {
      "epoch": 0.03352891869237217,
      "grad_norm": 5.564460277557373,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.2132,
      "step": 20
    },
    {
      "epoch": 0.03520536462699078,
      "grad_norm": 3.952474594116211,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1064,
      "step": 21
    },
    {
      "epoch": 0.036881810561609385,
      "grad_norm": 4.8364129066467285,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.1232,
      "step": 22
    },
    {
      "epoch": 0.038558256496227995,
      "grad_norm": 7.046288013458252,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1325,
      "step": 23
    },
    {
      "epoch": 0.040234702430846606,
      "grad_norm": 9.619534492492676,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.3749,
      "step": 24
    },
    {
      "epoch": 0.041911148365465216,
      "grad_norm": 8.914854049682617,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.1327,
      "step": 25
    },
    {
      "epoch": 0.041911148365465216,
      "eval_loss": 0.24791227281093597,
      "eval_runtime": 25.7908,
      "eval_samples_per_second": 19.503,
      "eval_steps_per_second": 9.771,
      "step": 25
    },
    {
      "epoch": 0.04358759430008382,
      "grad_norm": 10.980728149414062,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.2975,
      "step": 26
    },
    {
      "epoch": 0.04526404023470243,
      "grad_norm": 8.236481666564941,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2102,
      "step": 27
    },
    {
      "epoch": 0.04694048616932104,
      "grad_norm": 7.4617767333984375,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.2197,
      "step": 28
    },
    {
      "epoch": 0.04861693210393965,
      "grad_norm": 10.079323768615723,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.3974,
      "step": 29
    },
    {
      "epoch": 0.050293378038558254,
      "grad_norm": 6.351953983306885,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.242,
      "step": 30
    },
    {
      "epoch": 0.051969823973176864,
      "grad_norm": 8.568976402282715,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.2159,
      "step": 31
    },
    {
      "epoch": 0.053646269907795474,
      "grad_norm": 3.9171841144561768,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.1036,
      "step": 32
    },
    {
      "epoch": 0.055322715842414084,
      "grad_norm": 1.558870553970337,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0284,
      "step": 33
    },
    {
      "epoch": 0.05699916177703269,
      "grad_norm": 2.970895767211914,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 0.0734,
      "step": 34
    },
    {
      "epoch": 0.0586756077116513,
      "grad_norm": 5.282650470733643,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0669,
      "step": 35
    },
    {
      "epoch": 0.06035205364626991,
      "grad_norm": 4.935418605804443,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.1214,
      "step": 36
    },
    {
      "epoch": 0.06202849958088852,
      "grad_norm": 4.224859714508057,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.1697,
      "step": 37
    },
    {
      "epoch": 0.06370494551550712,
      "grad_norm": 8.419668197631836,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.245,
      "step": 38
    },
    {
      "epoch": 0.06538139145012574,
      "grad_norm": 4.401646137237549,
      "learning_rate": 5e-05,
      "loss": 0.0996,
      "step": 39
    },
    {
      "epoch": 0.06705783738474434,
      "grad_norm": 1.9046088457107544,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.0401,
      "step": 40
    },
    {
      "epoch": 0.06873428331936295,
      "grad_norm": 7.665452003479004,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.1484,
      "step": 41
    },
    {
      "epoch": 0.07041072925398156,
      "grad_norm": 3.5041327476501465,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0514,
      "step": 42
    },
    {
      "epoch": 0.07208717518860017,
      "grad_norm": 8.407772064208984,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1707,
      "step": 43
    },
    {
      "epoch": 0.07376362112321877,
      "grad_norm": 8.42634105682373,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.0916,
      "step": 44
    },
    {
      "epoch": 0.07544006705783739,
      "grad_norm": 4.17021369934082,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0612,
      "step": 45
    },
    {
      "epoch": 0.07711651299245599,
      "grad_norm": 9.347469329833984,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.2845,
      "step": 46
    },
    {
      "epoch": 0.07879295892707461,
      "grad_norm": 8.287640571594238,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1242,
      "step": 47
    },
    {
      "epoch": 0.08046940486169321,
      "grad_norm": 9.394111633300781,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0785,
      "step": 48
    },
    {
      "epoch": 0.08214585079631181,
      "grad_norm": 2.0844478607177734,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.0241,
      "step": 49
    },
    {
      "epoch": 0.08382229673093043,
      "grad_norm": 3.97900128364563,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 0.187,
      "step": 50
    },
    {
      "epoch": 0.08382229673093043,
      "eval_loss": 0.13281704485416412,
      "eval_runtime": 25.9404,
      "eval_samples_per_second": 19.391,
      "eval_steps_per_second": 9.715,
      "step": 50
    },
    {
      "epoch": 0.08549874266554904,
      "grad_norm": 15.202658653259277,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.3028,
      "step": 51
    },
    {
      "epoch": 0.08717518860016764,
      "grad_norm": 6.734172821044922,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 0.077,
      "step": 52
    },
    {
      "epoch": 0.08885163453478626,
      "grad_norm": 4.562060356140137,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.0778,
      "step": 53
    },
    {
      "epoch": 0.09052808046940486,
      "grad_norm": 6.335085391998291,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0984,
      "step": 54
    },
    {
      "epoch": 0.09220452640402348,
      "grad_norm": 2.6599574089050293,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0262,
      "step": 55
    },
    {
      "epoch": 0.09388097233864208,
      "grad_norm": 12.04505729675293,
      "learning_rate": 1.622048961921699e-05,
      "loss": 0.1365,
      "step": 56
    },
    {
      "epoch": 0.09555741827326068,
      "grad_norm": 7.626361846923828,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1941,
      "step": 57
    },
    {
      "epoch": 0.0972338642078793,
      "grad_norm": 0.9918619990348816,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 0.0123,
      "step": 58
    },
    {
      "epoch": 0.0989103101424979,
      "grad_norm": 9.633624076843262,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.1876,
      "step": 59
    },
    {
      "epoch": 0.10058675607711651,
      "grad_norm": 9.637693405151367,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.3459,
      "step": 60
    },
    {
      "epoch": 0.10226320201173512,
      "grad_norm": 4.565035820007324,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.0406,
      "step": 61
    },
    {
      "epoch": 0.10393964794635373,
      "grad_norm": 1.4430716037750244,
      "learning_rate": 7.830427709355725e-06,
      "loss": 0.018,
      "step": 62
    },
    {
      "epoch": 0.10561609388097234,
      "grad_norm": 8.149222373962402,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0857,
      "step": 63
    },
    {
      "epoch": 0.10729253981559095,
      "grad_norm": 4.575587272644043,
      "learning_rate": 5.649458341088915e-06,
      "loss": 0.0566,
      "step": 64
    },
    {
      "epoch": 0.10896898575020955,
      "grad_norm": 1.9635497331619263,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.0207,
      "step": 65
    },
    {
      "epoch": 0.11064543168482817,
      "grad_norm": 9.607479095458984,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.1747,
      "step": 66
    },
    {
      "epoch": 0.11232187761944677,
      "grad_norm": 6.042574882507324,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0783,
      "step": 67
    },
    {
      "epoch": 0.11399832355406538,
      "grad_norm": 6.86273717880249,
      "learning_rate": 2.314152462588659e-06,
      "loss": 0.2708,
      "step": 68
    },
    {
      "epoch": 0.11567476948868399,
      "grad_norm": 7.4351301193237305,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.1418,
      "step": 69
    },
    {
      "epoch": 0.1173512154233026,
      "grad_norm": 1.9024800062179565,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 0.0269,
      "step": 70
    },
    {
      "epoch": 0.11902766135792121,
      "grad_norm": 2.739542007446289,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0247,
      "step": 71
    },
    {
      "epoch": 0.12070410729253982,
      "grad_norm": 4.755945205688477,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.1258,
      "step": 72
    },
    {
      "epoch": 0.12238055322715842,
      "grad_norm": 3.5293490886688232,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.0726,
      "step": 73
    },
    {
      "epoch": 0.12405699916177704,
      "grad_norm": 2.227370262145996,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 0.035,
      "step": 74
    },
    {
      "epoch": 0.12573344509639564,
      "grad_norm": 2.4517362117767334,
      "learning_rate": 0.0,
      "loss": 0.0323,
      "step": 75
    },
    {
      "epoch": 0.12573344509639564,
      "eval_loss": 0.09524670988321304,
      "eval_runtime": 25.8009,
      "eval_samples_per_second": 19.495,
      "eval_steps_per_second": 9.767,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": 2.98024458780672e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}