{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007632034191513178,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010176045588684237,
      "grad_norm": 1.1650803089141846,
      "learning_rate": 1e-05,
      "loss": 3.6868,
      "step": 1
    },
    {
      "epoch": 0.00010176045588684237,
      "eval_loss": 1.9542405605316162,
      "eval_runtime": 1284.9313,
      "eval_samples_per_second": 6.441,
      "eval_steps_per_second": 0.805,
      "step": 1
    },
    {
      "epoch": 0.00020352091177368474,
      "grad_norm": 1.4374388456344604,
      "learning_rate": 2e-05,
      "loss": 4.061,
      "step": 2
    },
    {
      "epoch": 0.0003052813676605271,
      "grad_norm": 1.189625859260559,
      "learning_rate": 3e-05,
      "loss": 3.7313,
      "step": 3
    },
    {
      "epoch": 0.0004070418235473695,
      "grad_norm": 1.3531676530838013,
      "learning_rate": 4e-05,
      "loss": 3.971,
      "step": 4
    },
    {
      "epoch": 0.0005088022794342118,
      "grad_norm": 1.3253142833709717,
      "learning_rate": 5e-05,
      "loss": 3.72,
      "step": 5
    },
    {
      "epoch": 0.0006105627353210542,
      "grad_norm": 1.5036964416503906,
      "learning_rate": 6e-05,
      "loss": 4.0241,
      "step": 6
    },
    {
      "epoch": 0.0007123231912078966,
      "grad_norm": 1.6797518730163574,
      "learning_rate": 7e-05,
      "loss": 3.7447,
      "step": 7
    },
    {
      "epoch": 0.000814083647094739,
      "grad_norm": 1.7705057859420776,
      "learning_rate": 8e-05,
      "loss": 3.5215,
      "step": 8
    },
    {
      "epoch": 0.0009158441029815813,
      "grad_norm": 2.124742269515991,
      "learning_rate": 9e-05,
      "loss": 3.4447,
      "step": 9
    },
    {
      "epoch": 0.0009158441029815813,
      "eval_loss": 1.672369360923767,
      "eval_runtime": 1284.8963,
      "eval_samples_per_second": 6.441,
      "eval_steps_per_second": 0.806,
      "step": 9
    },
    {
      "epoch": 0.0010176045588684236,
      "grad_norm": 2.0552783012390137,
      "learning_rate": 0.0001,
      "loss": 3.3965,
      "step": 10
    },
    {
      "epoch": 0.001119365014755266,
      "grad_norm": 1.7852537631988525,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.2908,
      "step": 11
    },
    {
      "epoch": 0.0012211254706421084,
      "grad_norm": 2.2228970527648926,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.8687,
      "step": 12
    },
    {
      "epoch": 0.0013228859265289508,
      "grad_norm": 2.1906330585479736,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.9292,
      "step": 13
    },
    {
      "epoch": 0.0014246463824157932,
      "grad_norm": 1.9089043140411377,
      "learning_rate": 9.951340343707852e-05,
      "loss": 2.8231,
      "step": 14
    },
    {
      "epoch": 0.0015264068383026355,
      "grad_norm": 1.6928902864456177,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.7397,
      "step": 15
    },
    {
      "epoch": 0.001628167294189478,
      "grad_norm": 1.8010334968566895,
      "learning_rate": 9.890738003669029e-05,
      "loss": 2.3339,
      "step": 16
    },
    {
      "epoch": 0.0017299277500763203,
      "grad_norm": 1.7140100002288818,
      "learning_rate": 9.851478631379982e-05,
      "loss": 2.371,
      "step": 17
    },
    {
      "epoch": 0.0018316882059631627,
      "grad_norm": 2.0291690826416016,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.9852,
      "step": 18
    },
    {
      "epoch": 0.0018316882059631627,
      "eval_loss": 1.0831049680709839,
      "eval_runtime": 1284.649,
      "eval_samples_per_second": 6.442,
      "eval_steps_per_second": 0.806,
      "step": 18
    },
    {
      "epoch": 0.001933448661850005,
      "grad_norm": 1.9884072542190552,
      "learning_rate": 9.755282581475769e-05,
      "loss": 2.172,
      "step": 19
    },
    {
      "epoch": 0.0020352091177368472,
      "grad_norm": 1.7432570457458496,
      "learning_rate": 9.698463103929542e-05,
      "loss": 2.2234,
      "step": 20
    },
    {
      "epoch": 0.0021369695736236896,
      "grad_norm": 1.6502352952957153,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.0481,
      "step": 21
    },
    {
      "epoch": 0.002238730029510532,
      "grad_norm": 1.7368217706680298,
      "learning_rate": 9.567727288213005e-05,
      "loss": 1.7579,
      "step": 22
    },
    {
      "epoch": 0.0023404904853973744,
      "grad_norm": 1.6056512594223022,
      "learning_rate": 9.493970231495835e-05,
      "loss": 1.7656,
      "step": 23
    },
    {
      "epoch": 0.0024422509412842168,
      "grad_norm": 1.198451042175293,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.7377,
      "step": 24
    },
    {
      "epoch": 0.002544011397171059,
      "grad_norm": 1.2867367267608643,
      "learning_rate": 9.330127018922194e-05,
      "loss": 1.9716,
      "step": 25
    },
    {
      "epoch": 0.0026457718530579015,
      "grad_norm": 1.6098988056182861,
      "learning_rate": 9.24024048078213e-05,
      "loss": 1.7878,
      "step": 26
    },
    {
      "epoch": 0.002747532308944744,
      "grad_norm": 1.3133220672607422,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.8123,
      "step": 27
    },
    {
      "epoch": 0.002747532308944744,
      "eval_loss": 0.8997605443000793,
      "eval_runtime": 1284.7777,
      "eval_samples_per_second": 6.442,
      "eval_steps_per_second": 0.806,
      "step": 27
    },
    {
      "epoch": 0.0028492927648315863,
      "grad_norm": 1.3010764122009277,
      "learning_rate": 9.045084971874738e-05,
      "loss": 1.7342,
      "step": 28
    },
    {
      "epoch": 0.0029510532207184287,
      "grad_norm": 1.6312528848648071,
      "learning_rate": 8.940053768033609e-05,
      "loss": 1.6338,
      "step": 29
    },
    {
      "epoch": 0.003052813676605271,
      "grad_norm": 1.3112207651138306,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.5525,
      "step": 30
    },
    {
      "epoch": 0.0031545741324921135,
      "grad_norm": 1.3443775177001953,
      "learning_rate": 8.715724127386972e-05,
      "loss": 1.475,
      "step": 31
    },
    {
      "epoch": 0.003256334588378956,
      "grad_norm": 1.4664099216461182,
      "learning_rate": 8.596699001693255e-05,
      "loss": 1.7025,
      "step": 32
    },
    {
      "epoch": 0.0033580950442657982,
      "grad_norm": 1.3237636089324951,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.7177,
      "step": 33
    },
    {
      "epoch": 0.0034598555001526406,
      "grad_norm": 1.2252451181411743,
      "learning_rate": 8.345653031794292e-05,
      "loss": 1.7062,
      "step": 34
    },
    {
      "epoch": 0.003561615956039483,
      "grad_norm": 1.4835950136184692,
      "learning_rate": 8.213938048432697e-05,
      "loss": 1.8055,
      "step": 35
    },
    {
      "epoch": 0.0036633764119263254,
      "grad_norm": 1.513283610343933,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.6516,
      "step": 36
    },
    {
      "epoch": 0.0036633764119263254,
      "eval_loss": 0.8654147386550903,
      "eval_runtime": 1284.7166,
      "eval_samples_per_second": 6.442,
      "eval_steps_per_second": 0.806,
      "step": 36
    },
    {
      "epoch": 0.0037651368678131678,
      "grad_norm": 1.346374273300171,
      "learning_rate": 7.938926261462366e-05,
      "loss": 1.5611,
      "step": 37
    },
    {
      "epoch": 0.00386689732370001,
      "grad_norm": 1.7698302268981934,
      "learning_rate": 7.795964517353735e-05,
      "loss": 1.8638,
      "step": 38
    },
    {
      "epoch": 0.003968657779586853,
      "grad_norm": 1.1590263843536377,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.6992,
      "step": 39
    },
    {
      "epoch": 0.0040704182354736945,
      "grad_norm": 1.2893553972244263,
      "learning_rate": 7.500000000000001e-05,
      "loss": 1.584,
      "step": 40
    },
    {
      "epoch": 0.004172178691360537,
      "grad_norm": 1.2301239967346191,
      "learning_rate": 7.347357813929454e-05,
      "loss": 1.8145,
      "step": 41
    },
    {
      "epoch": 0.004273939147247379,
      "grad_norm": 1.1588472127914429,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.8465,
      "step": 42
    },
    {
      "epoch": 0.004375699603134222,
      "grad_norm": 1.2996362447738647,
      "learning_rate": 7.033683215379002e-05,
      "loss": 1.8395,
      "step": 43
    },
    {
      "epoch": 0.004477460059021064,
      "grad_norm": 1.0893059968948364,
      "learning_rate": 6.873032967079561e-05,
      "loss": 1.496,
      "step": 44
    },
    {
      "epoch": 0.004579220514907906,
      "grad_norm": 1.3532724380493164,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.7816,
      "step": 45
    },
    {
      "epoch": 0.004579220514907906,
      "eval_loss": 0.8417056202888489,
      "eval_runtime": 1284.6872,
      "eval_samples_per_second": 6.442,
      "eval_steps_per_second": 0.806,
      "step": 45
    },
    {
      "epoch": 0.004680980970794749,
      "grad_norm": 1.6128814220428467,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.7634,
      "step": 46
    },
    {
      "epoch": 0.004782741426681591,
      "grad_norm": 1.1191667318344116,
      "learning_rate": 6.378186779084995e-05,
      "loss": 1.6449,
      "step": 47
    },
    {
      "epoch": 0.0048845018825684336,
      "grad_norm": 1.107248067855835,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.6289,
      "step": 48
    },
    {
      "epoch": 0.004986262338455276,
      "grad_norm": 1.3476243019104004,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 1.4822,
      "step": 49
    },
    {
      "epoch": 0.005088022794342118,
      "grad_norm": 1.3216867446899414,
      "learning_rate": 5.868240888334653e-05,
      "loss": 1.6763,
      "step": 50
    },
    {
      "epoch": 0.005189783250228961,
      "grad_norm": 1.2048275470733643,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.7216,
      "step": 51
    },
    {
      "epoch": 0.005291543706115803,
      "grad_norm": 1.3522450923919678,
      "learning_rate": 5.522642316338268e-05,
      "loss": 1.5397,
      "step": 52
    },
    {
      "epoch": 0.0053933041620026455,
      "grad_norm": 1.275253176689148,
      "learning_rate": 5.348782368720626e-05,
      "loss": 1.7373,
      "step": 53
    },
    {
      "epoch": 0.005495064617889488,
      "grad_norm": 1.192983865737915,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.6307,
      "step": 54
    },
    {
      "epoch": 0.005495064617889488,
      "eval_loss": 0.8217622637748718,
      "eval_runtime": 1284.6298,
      "eval_samples_per_second": 6.442,
      "eval_steps_per_second": 0.806,
      "step": 54
    },
    {
      "epoch": 0.00559682507377633,
      "grad_norm": 1.1133981943130493,
      "learning_rate": 5e-05,
      "loss": 1.5643,
      "step": 55
    },
    {
      "epoch": 0.005698585529663173,
      "grad_norm": 1.2751656770706177,
      "learning_rate": 4.825502516487497e-05,
      "loss": 1.6735,
      "step": 56
    },
    {
      "epoch": 0.005800345985550015,
      "grad_norm": 1.077012300491333,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.4949,
      "step": 57
    },
    {
      "epoch": 0.005902106441436857,
      "grad_norm": 1.1121612787246704,
      "learning_rate": 4.477357683661734e-05,
      "loss": 1.5884,
      "step": 58
    },
    {
      "epoch": 0.0060038668973237,
      "grad_norm": 1.2280850410461426,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 1.6159,
      "step": 59
    },
    {
      "epoch": 0.006105627353210542,
      "grad_norm": 1.2770012617111206,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.5878,
      "step": 60
    },
    {
      "epoch": 0.0062073878090973846,
      "grad_norm": 1.2348254919052124,
      "learning_rate": 3.960441545911204e-05,
      "loss": 1.5739,
      "step": 61
    },
    {
      "epoch": 0.006309148264984227,
      "grad_norm": 1.1665235757827759,
      "learning_rate": 3.790390522001662e-05,
      "loss": 1.495,
      "step": 62
    },
    {
      "epoch": 0.006410908720871069,
      "grad_norm": 1.1555850505828857,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.4763,
      "step": 63
    },
    {
      "epoch": 0.006410908720871069,
      "eval_loss": 0.8095032572746277,
      "eval_runtime": 1284.7296,
      "eval_samples_per_second": 6.442,
      "eval_steps_per_second": 0.806,
      "step": 63
    },
    {
      "epoch": 0.006512669176757912,
      "grad_norm": 1.2946234941482544,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 1.7213,
      "step": 64
    },
    {
      "epoch": 0.006614429632644754,
      "grad_norm": 1.012257695198059,
      "learning_rate": 3.289899283371657e-05,
      "loss": 1.5162,
      "step": 65
    },
    {
      "epoch": 0.0067161900885315965,
      "grad_norm": 1.1877633333206177,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.551,
      "step": 66
    },
    {
      "epoch": 0.006817950544418439,
      "grad_norm": 1.1224725246429443,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 1.5557,
      "step": 67
    },
    {
      "epoch": 0.006919711000305281,
      "grad_norm": 1.4099979400634766,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 1.6777,
      "step": 68
    },
    {
      "epoch": 0.007021471456192124,
      "grad_norm": 1.1825891733169556,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.5911,
      "step": 69
    },
    {
      "epoch": 0.007123231912078966,
      "grad_norm": 1.2803326845169067,
      "learning_rate": 2.500000000000001e-05,
      "loss": 1.5972,
      "step": 70
    },
    {
      "epoch": 0.007224992367965808,
      "grad_norm": 1.4079381227493286,
      "learning_rate": 2.350403678833976e-05,
      "loss": 1.761,
      "step": 71
    },
    {
      "epoch": 0.007326752823852651,
      "grad_norm": 1.3135712146759033,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.4069,
      "step": 72
    },
    {
      "epoch": 0.007326752823852651,
      "eval_loss": 0.801685094833374,
      "eval_runtime": 1284.4704,
      "eval_samples_per_second": 6.443,
      "eval_steps_per_second": 0.806,
      "step": 72
    },
    {
      "epoch": 0.007428513279739493,
      "grad_norm": 1.438674807548523,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.5137,
      "step": 73
    },
    {
      "epoch": 0.0075302737356263355,
      "grad_norm": 1.1607484817504883,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 1.5216,
      "step": 74
    },
    {
      "epoch": 0.007632034191513178,
      "grad_norm": 1.2360979318618774,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.4009,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.521684545536e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}