{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1111934766493699,
  "eval_steps": 9,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014825796886582653,
      "grad_norm": 2.8474559783935547,
      "learning_rate": 1e-05,
      "loss": 5.225,
      "step": 1
    },
    {
      "epoch": 0.0014825796886582653,
      "eval_loss": 2.508056402206421,
      "eval_runtime": 69.5324,
      "eval_samples_per_second": 8.169,
      "eval_steps_per_second": 1.021,
      "step": 1
    },
    {
      "epoch": 0.0029651593773165306,
      "grad_norm": 2.3535349369049072,
      "learning_rate": 2e-05,
      "loss": 4.6645,
      "step": 2
    },
    {
      "epoch": 0.004447739065974796,
      "grad_norm": 2.6361703872680664,
      "learning_rate": 3e-05,
      "loss": 4.8725,
      "step": 3
    },
    {
      "epoch": 0.005930318754633061,
      "grad_norm": 4.400317192077637,
      "learning_rate": 4e-05,
      "loss": 4.7542,
      "step": 4
    },
    {
      "epoch": 0.007412898443291327,
      "grad_norm": 2.6915769577026367,
      "learning_rate": 5e-05,
      "loss": 5.1234,
      "step": 5
    },
    {
      "epoch": 0.008895478131949592,
      "grad_norm": 3.3075225353240967,
      "learning_rate": 6e-05,
      "loss": 4.5994,
      "step": 6
    },
    {
      "epoch": 0.010378057820607857,
      "grad_norm": 3.946103572845459,
      "learning_rate": 7e-05,
      "loss": 4.6332,
      "step": 7
    },
    {
      "epoch": 0.011860637509266123,
      "grad_norm": 4.162266731262207,
      "learning_rate": 8e-05,
      "loss": 4.7407,
      "step": 8
    },
    {
      "epoch": 0.013343217197924388,
      "grad_norm": 5.167053699493408,
      "learning_rate": 9e-05,
      "loss": 4.3724,
      "step": 9
    },
    {
      "epoch": 0.013343217197924388,
      "eval_loss": 1.8550039529800415,
      "eval_runtime": 69.5376,
      "eval_samples_per_second": 8.168,
      "eval_steps_per_second": 1.021,
      "step": 9
    },
    {
      "epoch": 0.014825796886582653,
      "grad_norm": 4.388719081878662,
      "learning_rate": 0.0001,
      "loss": 3.382,
      "step": 10
    },
    {
      "epoch": 0.01630837657524092,
      "grad_norm": 5.396074295043945,
      "learning_rate": 9.99695413509548e-05,
      "loss": 3.0693,
      "step": 11
    },
    {
      "epoch": 0.017790956263899184,
      "grad_norm": 5.097604751586914,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.345,
      "step": 12
    },
    {
      "epoch": 0.01927353595255745,
      "grad_norm": 5.280440807342529,
      "learning_rate": 9.972609476841367e-05,
      "loss": 2.0353,
      "step": 13
    },
    {
      "epoch": 0.020756115641215715,
      "grad_norm": 3.470097780227661,
      "learning_rate": 9.951340343707852e-05,
      "loss": 1.1178,
      "step": 14
    },
    {
      "epoch": 0.02223869532987398,
      "grad_norm": 4.099720478057861,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.1429,
      "step": 15
    },
    {
      "epoch": 0.023721275018532245,
      "grad_norm": 3.006298065185547,
      "learning_rate": 9.890738003669029e-05,
      "loss": 1.0927,
      "step": 16
    },
    {
      "epoch": 0.025203854707190512,
      "grad_norm": 1.9103775024414062,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.6789,
      "step": 17
    },
    {
      "epoch": 0.026686434395848776,
      "grad_norm": 3.037099599838257,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.3045,
      "step": 18
    },
    {
      "epoch": 0.026686434395848776,
      "eval_loss": 0.32767146825790405,
      "eval_runtime": 69.5401,
      "eval_samples_per_second": 8.168,
      "eval_steps_per_second": 1.021,
      "step": 18
    },
    {
      "epoch": 0.028169014084507043,
      "grad_norm": 4.88580322265625,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.8711,
      "step": 19
    },
    {
      "epoch": 0.029651593773165306,
      "grad_norm": 14.325489044189453,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.6723,
      "step": 20
    },
    {
      "epoch": 0.031134173461823574,
      "grad_norm": 1.8659063577651978,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.3444,
      "step": 21
    },
    {
      "epoch": 0.03261675315048184,
      "grad_norm": 1.1169908046722412,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.1008,
      "step": 22
    },
    {
      "epoch": 0.0340993328391401,
      "grad_norm": 3.31902813911438,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.5448,
      "step": 23
    },
    {
      "epoch": 0.03558191252779837,
      "grad_norm": 2.234715700149536,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.2588,
      "step": 24
    },
    {
      "epoch": 0.037064492216456635,
      "grad_norm": 1.7870392799377441,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.219,
      "step": 25
    },
    {
      "epoch": 0.0385470719051149,
      "grad_norm": 2.5575437545776367,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.5638,
      "step": 26
    },
    {
      "epoch": 0.04002965159377316,
      "grad_norm": 3.1489202976226807,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.1793,
      "step": 27
    },
    {
      "epoch": 0.04002965159377316,
      "eval_loss": 0.14556753635406494,
      "eval_runtime": 69.5326,
      "eval_samples_per_second": 8.169,
      "eval_steps_per_second": 1.021,
      "step": 27
    },
    {
      "epoch": 0.04151223128243143,
      "grad_norm": 2.429274559020996,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.4793,
      "step": 28
    },
    {
      "epoch": 0.042994810971089696,
      "grad_norm": 1.9509632587432861,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.4278,
      "step": 29
    },
    {
      "epoch": 0.04447739065974796,
      "grad_norm": 1.8806370496749878,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.3179,
      "step": 30
    },
    {
      "epoch": 0.04595997034840623,
      "grad_norm": 1.5672978162765503,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.2368,
      "step": 31
    },
    {
      "epoch": 0.04744255003706449,
      "grad_norm": 1.8994029760360718,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.3258,
      "step": 32
    },
    {
      "epoch": 0.04892512972572276,
      "grad_norm": 0.3584083914756775,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.0261,
      "step": 33
    },
    {
      "epoch": 0.050407709414381024,
      "grad_norm": 20.641138076782227,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.2844,
      "step": 34
    },
    {
      "epoch": 0.05189028910303929,
      "grad_norm": 1.0512652397155762,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.078,
      "step": 35
    },
    {
      "epoch": 0.05337286879169755,
      "grad_norm": 1.5341689586639404,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.1862,
      "step": 36
    },
    {
      "epoch": 0.05337286879169755,
      "eval_loss": 0.10944854468107224,
      "eval_runtime": 69.5263,
      "eval_samples_per_second": 8.17,
      "eval_steps_per_second": 1.021,
      "step": 36
    },
    {
      "epoch": 0.05485544848035582,
      "grad_norm": 1.0907577276229858,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.0845,
      "step": 37
    },
    {
      "epoch": 0.056338028169014086,
      "grad_norm": 3.018357515335083,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.2438,
      "step": 38
    },
    {
      "epoch": 0.05782060785767235,
      "grad_norm": 2.455247640609741,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.2814,
      "step": 39
    },
    {
      "epoch": 0.05930318754633061,
      "grad_norm": 1.3131052255630493,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.15,
      "step": 40
    },
    {
      "epoch": 0.06078576723498888,
      "grad_norm": 3.73819899559021,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.5374,
      "step": 41
    },
    {
      "epoch": 0.06226834692364715,
      "grad_norm": 2.3663792610168457,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.2676,
      "step": 42
    },
    {
      "epoch": 0.06375092661230541,
      "grad_norm": 1.835417628288269,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.1357,
      "step": 43
    },
    {
      "epoch": 0.06523350630096368,
      "grad_norm": 2.896899461746216,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.1411,
      "step": 44
    },
    {
      "epoch": 0.06671608598962195,
      "grad_norm": 1.5244169235229492,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.2247,
      "step": 45
    },
    {
      "epoch": 0.06671608598962195,
      "eval_loss": 0.08920716494321823,
      "eval_runtime": 69.558,
      "eval_samples_per_second": 8.166,
      "eval_steps_per_second": 1.021,
      "step": 45
    },
    {
      "epoch": 0.0681986656782802,
      "grad_norm": 1.3107813596725464,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3675,
      "step": 46
    },
    {
      "epoch": 0.06968124536693847,
      "grad_norm": 1.982515573501587,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.2806,
      "step": 47
    },
    {
      "epoch": 0.07116382505559674,
      "grad_norm": 0.5991136431694031,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0344,
      "step": 48
    },
    {
      "epoch": 0.072646404744255,
      "grad_norm": 0.9610239267349243,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.183,
      "step": 49
    },
    {
      "epoch": 0.07412898443291327,
      "grad_norm": 6.47637939453125,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0722,
      "step": 50
    },
    {
      "epoch": 0.07561156412157154,
      "grad_norm": 1.6755069494247437,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.1886,
      "step": 51
    },
    {
      "epoch": 0.0770941438102298,
      "grad_norm": 1.4019275903701782,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2802,
      "step": 52
    },
    {
      "epoch": 0.07857672349888807,
      "grad_norm": 1.2601383924484253,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.1966,
      "step": 53
    },
    {
      "epoch": 0.08005930318754632,
      "grad_norm": 2.310203790664673,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0976,
      "step": 54
    },
    {
      "epoch": 0.08005930318754632,
      "eval_loss": 0.0861150324344635,
      "eval_runtime": 69.5538,
      "eval_samples_per_second": 8.166,
      "eval_steps_per_second": 1.021,
      "step": 54
    },
    {
      "epoch": 0.08154188287620459,
      "grad_norm": 1.8496018648147583,
      "learning_rate": 5e-05,
      "loss": 0.1013,
      "step": 55
    },
    {
      "epoch": 0.08302446256486286,
      "grad_norm": 2.3585057258605957,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.4208,
      "step": 56
    },
    {
      "epoch": 0.08450704225352113,
      "grad_norm": 1.9495047330856323,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.1957,
      "step": 57
    },
    {
      "epoch": 0.08598962194217939,
      "grad_norm": 0.7716205716133118,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.2906,
      "step": 58
    },
    {
      "epoch": 0.08747220163083766,
      "grad_norm": 0.6261329054832458,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.0633,
      "step": 59
    },
    {
      "epoch": 0.08895478131949593,
      "grad_norm": 0.622874915599823,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.1441,
      "step": 60
    },
    {
      "epoch": 0.0904373610081542,
      "grad_norm": 0.31516921520233154,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.0166,
      "step": 61
    },
    {
      "epoch": 0.09191994069681246,
      "grad_norm": 1.9802504777908325,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.2408,
      "step": 62
    },
    {
      "epoch": 0.09340252038547071,
      "grad_norm": 0.5901920795440674,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.0406,
      "step": 63
    },
    {
      "epoch": 0.09340252038547071,
      "eval_loss": 0.07249511033296585,
      "eval_runtime": 69.5376,
      "eval_samples_per_second": 8.168,
      "eval_steps_per_second": 1.021,
      "step": 63
    },
    {
      "epoch": 0.09488510007412898,
      "grad_norm": 0.49623680114746094,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0985,
      "step": 64
    },
    {
      "epoch": 0.09636767976278725,
      "grad_norm": 1.2704252004623413,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.2287,
      "step": 65
    },
    {
      "epoch": 0.09785025945144551,
      "grad_norm": 0.3415655195713043,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0341,
      "step": 66
    },
    {
      "epoch": 0.09933283914010378,
      "grad_norm": 1.9959161281585693,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.2905,
      "step": 67
    },
    {
      "epoch": 0.10081541882876205,
      "grad_norm": 1.1924718618392944,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.2025,
      "step": 68
    },
    {
      "epoch": 0.10229799851742032,
      "grad_norm": 0.9648506045341492,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.224,
      "step": 69
    },
    {
      "epoch": 0.10378057820607858,
      "grad_norm": 0.41112014651298523,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.1015,
      "step": 70
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.44839367270469666,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.0422,
      "step": 71
    },
    {
      "epoch": 0.1067457375833951,
      "grad_norm": 0.6787695288658142,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0655,
      "step": 72
    },
    {
      "epoch": 0.1067457375833951,
      "eval_loss": 0.06948262453079224,
      "eval_runtime": 69.544,
      "eval_samples_per_second": 8.167,
      "eval_steps_per_second": 1.021,
      "step": 72
    },
    {
      "epoch": 0.10822831727205337,
      "grad_norm": 0.8753631114959717,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.1026,
      "step": 73
    },
    {
      "epoch": 0.10971089696071164,
      "grad_norm": 0.4623323082923889,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.1358,
      "step": 74
    },
    {
      "epoch": 0.1111934766493699,
      "grad_norm": 2.5765066146850586,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.4581,
      "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": 4.90098483265536e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}