{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.28155795401220085,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003754106053496011,
      "grad_norm": 5.032824516296387,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 10.732,
      "step": 1
    },
    {
      "epoch": 0.003754106053496011,
      "eval_loss": 10.386579513549805,
      "eval_runtime": 23.6744,
      "eval_samples_per_second": 9.504,
      "eval_steps_per_second": 4.773,
      "step": 1
    },
    {
      "epoch": 0.007508212106992022,
      "grad_norm": 4.45830774307251,
      "learning_rate": 6.666666666666667e-05,
      "loss": 10.1977,
      "step": 2
    },
    {
      "epoch": 0.011262318160488035,
      "grad_norm": 4.931914806365967,
      "learning_rate": 0.0001,
      "loss": 10.4683,
      "step": 3
    },
    {
      "epoch": 0.015016424213984044,
      "grad_norm": 5.310385227203369,
      "learning_rate": 9.99524110790929e-05,
      "loss": 10.0276,
      "step": 4
    },
    {
      "epoch": 0.018770530267480056,
      "grad_norm": 5.923955917358398,
      "learning_rate": 9.980973490458728e-05,
      "loss": 8.8427,
      "step": 5
    },
    {
      "epoch": 0.02252463632097607,
      "grad_norm": 6.323431015014648,
      "learning_rate": 9.957224306869053e-05,
      "loss": 8.1762,
      "step": 6
    },
    {
      "epoch": 0.02627874237447208,
      "grad_norm": 7.335643291473389,
      "learning_rate": 9.924038765061042e-05,
      "loss": 6.8706,
      "step": 7
    },
    {
      "epoch": 0.03003284842796809,
      "grad_norm": 8.605307579040527,
      "learning_rate": 9.881480035599667e-05,
      "loss": 5.6587,
      "step": 8
    },
    {
      "epoch": 0.0337869544814641,
      "grad_norm": 8.2649564743042,
      "learning_rate": 9.829629131445342e-05,
      "loss": 4.7449,
      "step": 9
    },
    {
      "epoch": 0.03754106053496011,
      "grad_norm": 8.937447547912598,
      "learning_rate": 9.768584753741134e-05,
      "loss": 3.5373,
      "step": 10
    },
    {
      "epoch": 0.041295166588456125,
      "grad_norm": 7.276700019836426,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.5148,
      "step": 11
    },
    {
      "epoch": 0.04504927264195214,
      "grad_norm": 6.3739237785339355,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.8054,
      "step": 12
    },
    {
      "epoch": 0.048803378695448145,
      "grad_norm": 9.503493309020996,
      "learning_rate": 9.53153893518325e-05,
      "loss": 1.4151,
      "step": 13
    },
    {
      "epoch": 0.05255748474894416,
      "grad_norm": 7.375895977020264,
      "learning_rate": 9.435054165891109e-05,
      "loss": 1.3681,
      "step": 14
    },
    {
      "epoch": 0.05631159080244017,
      "grad_norm": 5.152674674987793,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.6395,
      "step": 15
    },
    {
      "epoch": 0.06006569685593618,
      "grad_norm": 3.77114200592041,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.529,
      "step": 16
    },
    {
      "epoch": 0.06381980290943219,
      "grad_norm": 5.566516876220703,
      "learning_rate": 9.09576022144496e-05,
      "loss": 1.0785,
      "step": 17
    },
    {
      "epoch": 0.0675739089629282,
      "grad_norm": 6.849836826324463,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.4344,
      "step": 18
    },
    {
      "epoch": 0.07132801501642422,
      "grad_norm": 1.5408703088760376,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.2114,
      "step": 19
    },
    {
      "epoch": 0.07508212106992022,
      "grad_norm": 4.369248390197754,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.4968,
      "step": 20
    },
    {
      "epoch": 0.07883622712341623,
      "grad_norm": 7.375030040740967,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6239,
      "step": 21
    },
    {
      "epoch": 0.08259033317691225,
      "grad_norm": 3.9516844749450684,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.2511,
      "step": 22
    },
    {
      "epoch": 0.08634443923040826,
      "grad_norm": 12.229116439819336,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.3429,
      "step": 23
    },
    {
      "epoch": 0.09009854528390428,
      "grad_norm": 5.0463337898254395,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.156,
      "step": 24
    },
    {
      "epoch": 0.09385265133740028,
      "grad_norm": 6.648087978363037,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.1689,
      "step": 25
    },
    {
      "epoch": 0.09385265133740028,
      "eval_loss": 0.1127062663435936,
      "eval_runtime": 23.1821,
      "eval_samples_per_second": 9.706,
      "eval_steps_per_second": 4.874,
      "step": 25
    },
    {
      "epoch": 0.09760675739089629,
      "grad_norm": 1.7941869497299194,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.1451,
      "step": 26
    },
    {
      "epoch": 0.10136086344439231,
      "grad_norm": 4.530095100402832,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.2568,
      "step": 27
    },
    {
      "epoch": 0.10511496949788832,
      "grad_norm": 2.566866636276245,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.1024,
      "step": 28
    },
    {
      "epoch": 0.10886907555138432,
      "grad_norm": 1.405090570449829,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.0991,
      "step": 29
    },
    {
      "epoch": 0.11262318160488034,
      "grad_norm": 1.2196756601333618,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0372,
      "step": 30
    },
    {
      "epoch": 0.11637728765837635,
      "grad_norm": 2.8575334548950195,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.1209,
      "step": 31
    },
    {
      "epoch": 0.12013139371187236,
      "grad_norm": 1.67503821849823,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.0985,
      "step": 32
    },
    {
      "epoch": 0.12388549976536838,
      "grad_norm": 2.7599682807922363,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.1226,
      "step": 33
    },
    {
      "epoch": 0.12763960581886438,
      "grad_norm": 0.700145423412323,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 0.0623,
      "step": 34
    },
    {
      "epoch": 0.1313937118723604,
      "grad_norm": 1.034289836883545,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0414,
      "step": 35
    },
    {
      "epoch": 0.1351478179258564,
      "grad_norm": 2.3948283195495605,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0645,
      "step": 36
    },
    {
      "epoch": 0.13890192397935242,
      "grad_norm": 4.111328125,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.1108,
      "step": 37
    },
    {
      "epoch": 0.14265603003284844,
      "grad_norm": 2.2279419898986816,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.0874,
      "step": 38
    },
    {
      "epoch": 0.14641013608634443,
      "grad_norm": 1.1830275058746338,
      "learning_rate": 5e-05,
      "loss": 0.0498,
      "step": 39
    },
    {
      "epoch": 0.15016424213984045,
      "grad_norm": 0.3365573585033417,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.0223,
      "step": 40
    },
    {
      "epoch": 0.15391834819333647,
      "grad_norm": 2.0155816078186035,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.1617,
      "step": 41
    },
    {
      "epoch": 0.15767245424683246,
      "grad_norm": 3.003706455230713,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.102,
      "step": 42
    },
    {
      "epoch": 0.16142656030032848,
      "grad_norm": 1.5898525714874268,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0484,
      "step": 43
    },
    {
      "epoch": 0.1651806663538245,
      "grad_norm": 0.8386490345001221,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.0363,
      "step": 44
    },
    {
      "epoch": 0.1689347724073205,
      "grad_norm": 1.006565809249878,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0238,
      "step": 45
    },
    {
      "epoch": 0.17268887846081651,
      "grad_norm": 1.485731601715088,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.0654,
      "step": 46
    },
    {
      "epoch": 0.17644298451431253,
      "grad_norm": 1.6186491250991821,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.1113,
      "step": 47
    },
    {
      "epoch": 0.18019709056780855,
      "grad_norm": 2.721684217453003,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.1347,
      "step": 48
    },
    {
      "epoch": 0.18395119662130455,
      "grad_norm": 0.671211302280426,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.0177,
      "step": 49
    },
    {
      "epoch": 0.18770530267480057,
      "grad_norm": 0.7374471426010132,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 0.0291,
      "step": 50
    },
    {
      "epoch": 0.18770530267480057,
      "eval_loss": 0.03728002309799194,
      "eval_runtime": 23.2151,
      "eval_samples_per_second": 9.692,
      "eval_steps_per_second": 4.868,
      "step": 50
    },
    {
      "epoch": 0.1914594087282966,
      "grad_norm": 0.2194223254919052,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.006,
      "step": 51
    },
    {
      "epoch": 0.19521351478179258,
      "grad_norm": 0.8518089056015015,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 0.0223,
      "step": 52
    },
    {
      "epoch": 0.1989676208352886,
      "grad_norm": 1.0204380750656128,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.027,
      "step": 53
    },
    {
      "epoch": 0.20272172688878462,
      "grad_norm": 1.9320348501205444,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.0502,
      "step": 54
    },
    {
      "epoch": 0.2064758329422806,
      "grad_norm": 1.0254801511764526,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0232,
      "step": 55
    },
    {
      "epoch": 0.21022993899577663,
      "grad_norm": 0.39294230937957764,
      "learning_rate": 1.622048961921699e-05,
      "loss": 0.0112,
      "step": 56
    },
    {
      "epoch": 0.21398404504927265,
      "grad_norm": 0.06195160001516342,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0033,
      "step": 57
    },
    {
      "epoch": 0.21773815110276865,
      "grad_norm": 0.6369668841362,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 0.038,
      "step": 58
    },
    {
      "epoch": 0.22149225715626467,
      "grad_norm": 0.4076542556285858,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0095,
      "step": 59
    },
    {
      "epoch": 0.22524636320976069,
      "grad_norm": 0.6492363214492798,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0206,
      "step": 60
    },
    {
      "epoch": 0.22900046926325668,
      "grad_norm": 0.630257248878479,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.0199,
      "step": 61
    },
    {
      "epoch": 0.2327545753167527,
      "grad_norm": 0.5601248145103455,
      "learning_rate": 7.830427709355725e-06,
      "loss": 0.0139,
      "step": 62
    },
    {
      "epoch": 0.23650868137024872,
      "grad_norm": 0.7685927152633667,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0222,
      "step": 63
    },
    {
      "epoch": 0.2402627874237447,
      "grad_norm": 0.995885968208313,
      "learning_rate": 5.649458341088915e-06,
      "loss": 0.0187,
      "step": 64
    },
    {
      "epoch": 0.24401689347724073,
      "grad_norm": 0.505293071269989,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.0163,
      "step": 65
    },
    {
      "epoch": 0.24777099953073675,
      "grad_norm": 0.4831348955631256,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0372,
      "step": 66
    },
    {
      "epoch": 0.25152510558423274,
      "grad_norm": 0.6265993118286133,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0232,
      "step": 67
    },
    {
      "epoch": 0.25527921163772876,
      "grad_norm": 0.8600174188613892,
      "learning_rate": 2.314152462588659e-06,
      "loss": 0.0164,
      "step": 68
    },
    {
      "epoch": 0.2590333176912248,
      "grad_norm": 0.46614569425582886,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.022,
      "step": 69
    },
    {
      "epoch": 0.2627874237447208,
      "grad_norm": 0.19857588410377502,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 0.0041,
      "step": 70
    },
    {
      "epoch": 0.2665415297982168,
      "grad_norm": 0.3438130021095276,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0181,
      "step": 71
    },
    {
      "epoch": 0.2702956358517128,
      "grad_norm": 1.681471347808838,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0286,
      "step": 72
    },
    {
      "epoch": 0.2740497419052088,
      "grad_norm": 0.05950739607214928,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.0024,
      "step": 73
    },
    {
      "epoch": 0.27780384795870483,
      "grad_norm": 0.18584494292736053,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 0.0057,
      "step": 74
    },
    {
      "epoch": 0.28155795401220085,
      "grad_norm": 0.41768908500671387,
      "learning_rate": 0.0,
      "loss": 0.0132,
      "step": 75
    },
    {
      "epoch": 0.28155795401220085,
      "eval_loss": 0.022396452724933624,
      "eval_runtime": 23.2271,
      "eval_samples_per_second": 9.687,
      "eval_steps_per_second": 4.865,
      "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": 1.048558039990272e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}