{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.21986075485525833,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0029314767314034445,
      "grad_norm": 4.896785259246826,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.4996,
      "step": 1
    },
    {
      "epoch": 0.0029314767314034445,
      "eval_loss": 1.0614820718765259,
      "eval_runtime": 20.3602,
      "eval_samples_per_second": 14.145,
      "eval_steps_per_second": 7.073,
      "step": 1
    },
    {
      "epoch": 0.005862953462806889,
      "grad_norm": 2.8189775943756104,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.1143,
      "step": 2
    },
    {
      "epoch": 0.008794430194210334,
      "grad_norm": 2.35616135597229,
      "learning_rate": 0.0001,
      "loss": 0.8383,
      "step": 3
    },
    {
      "epoch": 0.011725906925613778,
      "grad_norm": 1.8003149032592773,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.6748,
      "step": 4
    },
    {
      "epoch": 0.014657383657017223,
      "grad_norm": 2.207160472869873,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.7224,
      "step": 5
    },
    {
      "epoch": 0.01758886038842067,
      "grad_norm": 2.059014320373535,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.7348,
      "step": 6
    },
    {
      "epoch": 0.020520337119824112,
      "grad_norm": 1.301095962524414,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.4525,
      "step": 7
    },
    {
      "epoch": 0.023451813851227556,
      "grad_norm": 1.3723230361938477,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.4029,
      "step": 8
    },
    {
      "epoch": 0.026383290582631,
      "grad_norm": 1.4173338413238525,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.3076,
      "step": 9
    },
    {
      "epoch": 0.029314767314034446,
      "grad_norm": 1.3965848684310913,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.2697,
      "step": 10
    },
    {
      "epoch": 0.03224624404543789,
      "grad_norm": 1.271812081336975,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2067,
      "step": 11
    },
    {
      "epoch": 0.03517772077684134,
      "grad_norm": 1.1979728937149048,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2204,
      "step": 12
    },
    {
      "epoch": 0.03810919750824478,
      "grad_norm": 1.1956003904342651,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.1251,
      "step": 13
    },
    {
      "epoch": 0.041040674239648224,
      "grad_norm": 0.7809640765190125,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.0761,
      "step": 14
    },
    {
      "epoch": 0.043972150971051664,
      "grad_norm": 0.9528048634529114,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.1389,
      "step": 15
    },
    {
      "epoch": 0.04690362770245511,
      "grad_norm": 0.7418190240859985,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.0984,
      "step": 16
    },
    {
      "epoch": 0.04983510443385856,
      "grad_norm": 0.8109403252601624,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.1611,
      "step": 17
    },
    {
      "epoch": 0.052766581165262,
      "grad_norm": 0.6052976846694946,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.0726,
      "step": 18
    },
    {
      "epoch": 0.055698057896665445,
      "grad_norm": 0.6859976053237915,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0853,
      "step": 19
    },
    {
      "epoch": 0.05862953462806889,
      "grad_norm": 0.8153113126754761,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.133,
      "step": 20
    },
    {
      "epoch": 0.06156101135947233,
      "grad_norm": 0.6893975734710693,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0523,
      "step": 21
    },
    {
      "epoch": 0.06449248809087578,
      "grad_norm": 0.7115774750709534,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.0751,
      "step": 22
    },
    {
      "epoch": 0.06742396482227922,
      "grad_norm": 0.7574334740638733,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.0751,
      "step": 23
    },
    {
      "epoch": 0.07035544155368267,
      "grad_norm": 0.7631270289421082,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.091,
      "step": 24
    },
    {
      "epoch": 0.07328691828508611,
      "grad_norm": 0.4982626438140869,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.0477,
      "step": 25
    },
    {
      "epoch": 0.07328691828508611,
      "eval_loss": 0.08081666380167007,
      "eval_runtime": 20.8896,
      "eval_samples_per_second": 13.787,
      "eval_steps_per_second": 6.893,
      "step": 25
    },
    {
      "epoch": 0.07621839501648955,
      "grad_norm": 0.8068152666091919,
      "learning_rate": 7.68649804173412e-05,
      "loss": 0.1082,
      "step": 26
    },
    {
      "epoch": 0.079149871747893,
      "grad_norm": 0.3823889493942261,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0364,
      "step": 27
    },
    {
      "epoch": 0.08208134847929645,
      "grad_norm": 0.9048523306846619,
      "learning_rate": 7.308743066175172e-05,
      "loss": 0.1366,
      "step": 28
    },
    {
      "epoch": 0.08501282521069989,
      "grad_norm": 0.8256965279579163,
      "learning_rate": 7.113091308703498e-05,
      "loss": 0.107,
      "step": 29
    },
    {
      "epoch": 0.08794430194210333,
      "grad_norm": 0.5980184078216553,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0635,
      "step": 30
    },
    {
      "epoch": 0.09087577867350678,
      "grad_norm": 0.5219781398773193,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.0253,
      "step": 31
    },
    {
      "epoch": 0.09380725540491022,
      "grad_norm": 0.6775377988815308,
      "learning_rate": 6.503528997521366e-05,
      "loss": 0.1005,
      "step": 32
    },
    {
      "epoch": 0.09673873213631366,
      "grad_norm": 0.5344719886779785,
      "learning_rate": 6.294095225512603e-05,
      "loss": 0.0726,
      "step": 33
    },
    {
      "epoch": 0.09967020886771712,
      "grad_norm": 0.684424877166748,
      "learning_rate": 6.0821980696905146e-05,
      "loss": 0.0762,
      "step": 34
    },
    {
      "epoch": 0.10260168559912056,
      "grad_norm": 0.47931015491485596,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.053,
      "step": 35
    },
    {
      "epoch": 0.105533162330524,
      "grad_norm": 0.48746219277381897,
      "learning_rate": 5.6526309611002594e-05,
      "loss": 0.0769,
      "step": 36
    },
    {
      "epoch": 0.10846463906192745,
      "grad_norm": 0.41026896238327026,
      "learning_rate": 5.435778713738292e-05,
      "loss": 0.0623,
      "step": 37
    },
    {
      "epoch": 0.11139611579333089,
      "grad_norm": 0.6301044821739197,
      "learning_rate": 5.218096936826681e-05,
      "loss": 0.0854,
      "step": 38
    },
    {
      "epoch": 0.11432759252473433,
      "grad_norm": 0.43072110414505005,
      "learning_rate": 5e-05,
      "loss": 0.0488,
      "step": 39
    },
    {
      "epoch": 0.11725906925613779,
      "grad_norm": 0.49057018756866455,
      "learning_rate": 4.781903063173321e-05,
      "loss": 0.0468,
      "step": 40
    },
    {
      "epoch": 0.12019054598754123,
      "grad_norm": 0.541214108467102,
      "learning_rate": 4.564221286261709e-05,
      "loss": 0.1181,
      "step": 41
    },
    {
      "epoch": 0.12312202271894467,
      "grad_norm": 0.4960033893585205,
      "learning_rate": 4.347369038899744e-05,
      "loss": 0.0367,
      "step": 42
    },
    {
      "epoch": 0.1260534994503481,
      "grad_norm": 0.46519333124160767,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0634,
      "step": 43
    },
    {
      "epoch": 0.12898497618175156,
      "grad_norm": 0.5953696966171265,
      "learning_rate": 3.917801930309486e-05,
      "loss": 0.0357,
      "step": 44
    },
    {
      "epoch": 0.131916452913155,
      "grad_norm": 0.4260966181755066,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0504,
      "step": 45
    },
    {
      "epoch": 0.13484792964455844,
      "grad_norm": 0.35495659708976746,
      "learning_rate": 3.4964710024786354e-05,
      "loss": 0.0461,
      "step": 46
    },
    {
      "epoch": 0.1377794063759619,
      "grad_norm": 0.492147296667099,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.0833,
      "step": 47
    },
    {
      "epoch": 0.14071088310736535,
      "grad_norm": 0.47650235891342163,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0771,
      "step": 48
    },
    {
      "epoch": 0.14364235983876877,
      "grad_norm": 0.8814830780029297,
      "learning_rate": 2.886908691296504e-05,
      "loss": 0.1376,
      "step": 49
    },
    {
      "epoch": 0.14657383657017223,
      "grad_norm": 0.7530894875526428,
      "learning_rate": 2.6912569338248315e-05,
      "loss": 0.0946,
      "step": 50
    },
    {
      "epoch": 0.14657383657017223,
      "eval_loss": 0.06695578992366791,
      "eval_runtime": 20.9098,
      "eval_samples_per_second": 13.773,
      "eval_steps_per_second": 6.887,
      "step": 50
    },
    {
      "epoch": 0.14950531330157568,
      "grad_norm": 1.3906869888305664,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.2653,
      "step": 51
    },
    {
      "epoch": 0.1524367900329791,
      "grad_norm": 0.8645505309104919,
      "learning_rate": 2.3135019582658802e-05,
      "loss": 0.0972,
      "step": 52
    },
    {
      "epoch": 0.15536826676438256,
      "grad_norm": 0.3462808430194855,
      "learning_rate": 2.132117818244771e-05,
      "loss": 0.0178,
      "step": 53
    },
    {
      "epoch": 0.158299743495786,
      "grad_norm": 0.8373314142227173,
      "learning_rate": 1.9561928549563968e-05,
      "loss": 0.1511,
      "step": 54
    },
    {
      "epoch": 0.16123122022718944,
      "grad_norm": 0.5848434567451477,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.0587,
      "step": 55
    },
    {
      "epoch": 0.1641626969585929,
      "grad_norm": 0.7180687785148621,
      "learning_rate": 1.622048961921699e-05,
      "loss": 0.1289,
      "step": 56
    },
    {
      "epoch": 0.16709417368999632,
      "grad_norm": 0.4832279086112976,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0529,
      "step": 57
    },
    {
      "epoch": 0.17002565042139978,
      "grad_norm": 0.5206469893455505,
      "learning_rate": 1.3136133159493802e-05,
      "loss": 0.054,
      "step": 58
    },
    {
      "epoch": 0.17295712715280323,
      "grad_norm": 0.3522478938102722,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0454,
      "step": 59
    },
    {
      "epoch": 0.17588860388420666,
      "grad_norm": 0.6369943022727966,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0807,
      "step": 60
    },
    {
      "epoch": 0.1788200806156101,
      "grad_norm": 0.4056720435619354,
      "learning_rate": 9.042397785550405e-06,
      "loss": 0.0568,
      "step": 61
    },
    {
      "epoch": 0.18175155734701356,
      "grad_norm": 0.4317684471607208,
      "learning_rate": 7.830427709355725e-06,
      "loss": 0.0559,
      "step": 62
    },
    {
      "epoch": 0.184683034078417,
      "grad_norm": 0.5188791751861572,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.0894,
      "step": 63
    },
    {
      "epoch": 0.18761451080982045,
      "grad_norm": 0.4226022958755493,
      "learning_rate": 5.649458341088915e-06,
      "loss": 0.0641,
      "step": 64
    },
    {
      "epoch": 0.1905459875412239,
      "grad_norm": 0.6744760870933533,
      "learning_rate": 4.684610648167503e-06,
      "loss": 0.0995,
      "step": 65
    },
    {
      "epoch": 0.19347746427262733,
      "grad_norm": 0.36501771211624146,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0554,
      "step": 66
    },
    {
      "epoch": 0.19640894100403078,
      "grad_norm": 0.4740172326564789,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0403,
      "step": 67
    },
    {
      "epoch": 0.19934041773543423,
      "grad_norm": 0.37339267134666443,
      "learning_rate": 2.314152462588659e-06,
      "loss": 0.0429,
      "step": 68
    },
    {
      "epoch": 0.20227189446683766,
      "grad_norm": 0.46301230788230896,
      "learning_rate": 1.70370868554659e-06,
      "loss": 0.0245,
      "step": 69
    },
    {
      "epoch": 0.2052033711982411,
      "grad_norm": 0.37362566590309143,
      "learning_rate": 1.1851996440033319e-06,
      "loss": 0.0502,
      "step": 70
    },
    {
      "epoch": 0.20813484792964457,
      "grad_norm": 0.3411478102207184,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.0327,
      "step": 71
    },
    {
      "epoch": 0.211066324661048,
      "grad_norm": 0.6511849761009216,
      "learning_rate": 4.277569313094809e-07,
      "loss": 0.0708,
      "step": 72
    },
    {
      "epoch": 0.21399780139245145,
      "grad_norm": 0.4536079168319702,
      "learning_rate": 1.9026509541272275e-07,
      "loss": 0.05,
      "step": 73
    },
    {
      "epoch": 0.2169292781238549,
      "grad_norm": 0.5318543910980225,
      "learning_rate": 4.7588920907110094e-08,
      "loss": 0.0867,
      "step": 74
    },
    {
      "epoch": 0.21986075485525833,
      "grad_norm": 0.3312048017978668,
      "learning_rate": 0.0,
      "loss": 0.0279,
      "step": 75
    },
    {
      "epoch": 0.21986075485525833,
      "eval_loss": 0.06166088581085205,
      "eval_runtime": 20.9069,
      "eval_samples_per_second": 13.775,
      "eval_steps_per_second": 6.888,
      "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": 1.5860955711799296e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}