{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.059982005398380486,
  "eval_steps": 25,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007997600719784065,
      "grad_norm": 6.327381610870361,
      "learning_rate": 6.666666666666667e-05,
      "loss": 7.5777,
      "step": 1
    },
    {
      "epoch": 0.0007997600719784065,
      "eval_loss": 8.017860412597656,
      "eval_runtime": 287.8541,
      "eval_samples_per_second": 3.658,
      "eval_steps_per_second": 1.831,
      "step": 1
    },
    {
      "epoch": 0.001599520143956813,
      "grad_norm": 6.17039155960083,
      "learning_rate": 0.00013333333333333334,
      "loss": 7.6098,
      "step": 2
    },
    {
      "epoch": 0.0023992802159352195,
      "grad_norm": 5.528576850891113,
      "learning_rate": 0.0002,
      "loss": 7.7284,
      "step": 3
    },
    {
      "epoch": 0.003199040287913626,
      "grad_norm": 6.728517532348633,
      "learning_rate": 0.0001999048221581858,
      "loss": 7.4974,
      "step": 4
    },
    {
      "epoch": 0.003998800359892032,
      "grad_norm": 5.695092678070068,
      "learning_rate": 0.00019961946980917456,
      "loss": 5.9835,
      "step": 5
    },
    {
      "epoch": 0.004798560431870439,
      "grad_norm": 6.079351902008057,
      "learning_rate": 0.00019914448613738106,
      "loss": 5.1384,
      "step": 6
    },
    {
      "epoch": 0.005598320503848845,
      "grad_norm": 6.481296539306641,
      "learning_rate": 0.00019848077530122083,
      "loss": 5.0691,
      "step": 7
    },
    {
      "epoch": 0.006398080575827252,
      "grad_norm": 7.214561462402344,
      "learning_rate": 0.00019762960071199333,
      "loss": 4.8119,
      "step": 8
    },
    {
      "epoch": 0.0071978406478056586,
      "grad_norm": 7.010176658630371,
      "learning_rate": 0.00019659258262890683,
      "loss": 4.5991,
      "step": 9
    },
    {
      "epoch": 0.007997600719784064,
      "grad_norm": 6.9982590675354,
      "learning_rate": 0.0001953716950748227,
      "loss": 4.6868,
      "step": 10
    },
    {
      "epoch": 0.00879736079176247,
      "grad_norm": 6.621185302734375,
      "learning_rate": 0.00019396926207859084,
      "loss": 4.2868,
      "step": 11
    },
    {
      "epoch": 0.009597120863740878,
      "grad_norm": 5.465557098388672,
      "learning_rate": 0.0001923879532511287,
      "loss": 4.0701,
      "step": 12
    },
    {
      "epoch": 0.010396880935719284,
      "grad_norm": 6.433826923370361,
      "learning_rate": 0.000190630778703665,
      "loss": 4.166,
      "step": 13
    },
    {
      "epoch": 0.01119664100769769,
      "grad_norm": 6.815083026885986,
      "learning_rate": 0.00018870108331782217,
      "loss": 4.2868,
      "step": 14
    },
    {
      "epoch": 0.011996401079676098,
      "grad_norm": 5.863327980041504,
      "learning_rate": 0.00018660254037844388,
      "loss": 4.2603,
      "step": 15
    },
    {
      "epoch": 0.012796161151654504,
      "grad_norm": 4.982174396514893,
      "learning_rate": 0.0001843391445812886,
      "loss": 4.2987,
      "step": 16
    },
    {
      "epoch": 0.01359592122363291,
      "grad_norm": 4.87175178527832,
      "learning_rate": 0.0001819152044288992,
      "loss": 3.9961,
      "step": 17
    },
    {
      "epoch": 0.014395681295611317,
      "grad_norm": 5.400818347930908,
      "learning_rate": 0.00017933533402912354,
      "loss": 4.143,
      "step": 18
    },
    {
      "epoch": 0.015195441367589723,
      "grad_norm": 5.048769950866699,
      "learning_rate": 0.0001766044443118978,
      "loss": 4.2183,
      "step": 19
    },
    {
      "epoch": 0.01599520143956813,
      "grad_norm": 4.657977104187012,
      "learning_rate": 0.0001737277336810124,
      "loss": 4.0424,
      "step": 20
    },
    {
      "epoch": 0.016794961511546535,
      "grad_norm": 5.078902244567871,
      "learning_rate": 0.00017071067811865476,
      "loss": 4.3025,
      "step": 21
    },
    {
      "epoch": 0.01759472158352494,
      "grad_norm": 5.692748069763184,
      "learning_rate": 0.00016755902076156604,
      "loss": 4.0202,
      "step": 22
    },
    {
      "epoch": 0.01839448165550335,
      "grad_norm": 4.6804070472717285,
      "learning_rate": 0.00016427876096865394,
      "loss": 4.2141,
      "step": 23
    },
    {
      "epoch": 0.019194241727481756,
      "grad_norm": 4.39948844909668,
      "learning_rate": 0.00016087614290087208,
      "loss": 4.0431,
      "step": 24
    },
    {
      "epoch": 0.019994001799460162,
      "grad_norm": 5.215299606323242,
      "learning_rate": 0.0001573576436351046,
      "loss": 4.0373,
      "step": 25
    },
    {
      "epoch": 0.019994001799460162,
      "eval_loss": 3.997077703475952,
      "eval_runtime": 289.3626,
      "eval_samples_per_second": 3.639,
      "eval_steps_per_second": 1.821,
      "step": 25
    },
    {
      "epoch": 0.020793761871438568,
      "grad_norm": 5.740684986114502,
      "learning_rate": 0.0001537299608346824,
      "loss": 4.2566,
      "step": 26
    },
    {
      "epoch": 0.021593521943416974,
      "grad_norm": 5.554161548614502,
      "learning_rate": 0.00015000000000000001,
      "loss": 3.9106,
      "step": 27
    },
    {
      "epoch": 0.02239328201539538,
      "grad_norm": 4.885501384735107,
      "learning_rate": 0.00014617486132350343,
      "loss": 4.0344,
      "step": 28
    },
    {
      "epoch": 0.02319304208737379,
      "grad_norm": 6.132773399353027,
      "learning_rate": 0.00014226182617406996,
      "loss": 4.4499,
      "step": 29
    },
    {
      "epoch": 0.023992802159352195,
      "grad_norm": 4.748602390289307,
      "learning_rate": 0.000138268343236509,
      "loss": 4.0122,
      "step": 30
    },
    {
      "epoch": 0.0247925622313306,
      "grad_norm": 4.478851318359375,
      "learning_rate": 0.00013420201433256689,
      "loss": 3.8626,
      "step": 31
    },
    {
      "epoch": 0.025592322303309007,
      "grad_norm": 4.523096561431885,
      "learning_rate": 0.00013007057995042732,
      "loss": 3.9546,
      "step": 32
    },
    {
      "epoch": 0.026392082375287413,
      "grad_norm": 6.3320794105529785,
      "learning_rate": 0.00012588190451025207,
      "loss": 4.3883,
      "step": 33
    },
    {
      "epoch": 0.02719184244726582,
      "grad_norm": 5.49621057510376,
      "learning_rate": 0.00012164396139381029,
      "loss": 4.14,
      "step": 34
    },
    {
      "epoch": 0.02799160251924423,
      "grad_norm": 5.168715000152588,
      "learning_rate": 0.00011736481776669306,
      "loss": 3.6449,
      "step": 35
    },
    {
      "epoch": 0.028791362591222634,
      "grad_norm": 5.227668285369873,
      "learning_rate": 0.00011305261922200519,
      "loss": 3.6928,
      "step": 36
    },
    {
      "epoch": 0.02959112266320104,
      "grad_norm": 4.343628406524658,
      "learning_rate": 0.00010871557427476583,
      "loss": 3.6469,
      "step": 37
    },
    {
      "epoch": 0.030390882735179446,
      "grad_norm": 6.07112455368042,
      "learning_rate": 0.00010436193873653361,
      "loss": 3.7737,
      "step": 38
    },
    {
      "epoch": 0.031190642807157852,
      "grad_norm": 6.020794868469238,
      "learning_rate": 0.0001,
      "loss": 4.0414,
      "step": 39
    },
    {
      "epoch": 0.03199040287913626,
      "grad_norm": 5.776181221008301,
      "learning_rate": 9.563806126346642e-05,
      "loss": 3.78,
      "step": 40
    },
    {
      "epoch": 0.032790162951114664,
      "grad_norm": 5.805772304534912,
      "learning_rate": 9.128442572523417e-05,
      "loss": 3.882,
      "step": 41
    },
    {
      "epoch": 0.03358992302309307,
      "grad_norm": 5.020073413848877,
      "learning_rate": 8.694738077799488e-05,
      "loss": 3.8944,
      "step": 42
    },
    {
      "epoch": 0.034389683095071476,
      "grad_norm": 4.815114974975586,
      "learning_rate": 8.263518223330697e-05,
      "loss": 3.6254,
      "step": 43
    },
    {
      "epoch": 0.03518944316704988,
      "grad_norm": 5.086230754852295,
      "learning_rate": 7.835603860618972e-05,
      "loss": 3.9899,
      "step": 44
    },
    {
      "epoch": 0.035989203239028295,
      "grad_norm": 5.002678871154785,
      "learning_rate": 7.411809548974792e-05,
      "loss": 3.681,
      "step": 45
    },
    {
      "epoch": 0.0367889633110067,
      "grad_norm": 4.317289352416992,
      "learning_rate": 6.992942004957271e-05,
      "loss": 3.8644,
      "step": 46
    },
    {
      "epoch": 0.037588723382985106,
      "grad_norm": 4.629146575927734,
      "learning_rate": 6.579798566743314e-05,
      "loss": 3.9064,
      "step": 47
    },
    {
      "epoch": 0.03838848345496351,
      "grad_norm": 4.717955112457275,
      "learning_rate": 6.173165676349103e-05,
      "loss": 3.7925,
      "step": 48
    },
    {
      "epoch": 0.03918824352694192,
      "grad_norm": 4.8145856857299805,
      "learning_rate": 5.773817382593008e-05,
      "loss": 3.78,
      "step": 49
    },
    {
      "epoch": 0.039988003598920324,
      "grad_norm": 3.983384370803833,
      "learning_rate": 5.382513867649663e-05,
      "loss": 3.963,
      "step": 50
    },
    {
      "epoch": 0.039988003598920324,
      "eval_loss": 3.8365397453308105,
      "eval_runtime": 288.8744,
      "eval_samples_per_second": 3.645,
      "eval_steps_per_second": 1.824,
      "step": 50
    },
    {
      "epoch": 0.04078776367089873,
      "grad_norm": 5.371262073516846,
      "learning_rate": 5.000000000000002e-05,
      "loss": 3.942,
      "step": 51
    },
    {
      "epoch": 0.041587523742877136,
      "grad_norm": 5.728109359741211,
      "learning_rate": 4.6270039165317605e-05,
      "loss": 3.8686,
      "step": 52
    },
    {
      "epoch": 0.04238728381485554,
      "grad_norm": 4.341375827789307,
      "learning_rate": 4.264235636489542e-05,
      "loss": 3.5577,
      "step": 53
    },
    {
      "epoch": 0.04318704388683395,
      "grad_norm": 4.182137966156006,
      "learning_rate": 3.9123857099127936e-05,
      "loss": 3.485,
      "step": 54
    },
    {
      "epoch": 0.043986803958812354,
      "grad_norm": 4.7370405197143555,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 3.9982,
      "step": 55
    },
    {
      "epoch": 0.04478656403079076,
      "grad_norm": 4.426697731018066,
      "learning_rate": 3.244097923843398e-05,
      "loss": 3.6931,
      "step": 56
    },
    {
      "epoch": 0.04558632410276917,
      "grad_norm": 4.092799186706543,
      "learning_rate": 2.9289321881345254e-05,
      "loss": 3.7611,
      "step": 57
    },
    {
      "epoch": 0.04638608417474758,
      "grad_norm": 4.8570098876953125,
      "learning_rate": 2.6272266318987603e-05,
      "loss": 3.4304,
      "step": 58
    },
    {
      "epoch": 0.047185844246725984,
      "grad_norm": 4.567028522491455,
      "learning_rate": 2.339555568810221e-05,
      "loss": 3.7632,
      "step": 59
    },
    {
      "epoch": 0.04798560431870439,
      "grad_norm": 5.1109185218811035,
      "learning_rate": 2.0664665970876496e-05,
      "loss": 4.0769,
      "step": 60
    },
    {
      "epoch": 0.048785364390682796,
      "grad_norm": 4.340146064758301,
      "learning_rate": 1.808479557110081e-05,
      "loss": 3.6998,
      "step": 61
    },
    {
      "epoch": 0.0495851244626612,
      "grad_norm": 5.708188056945801,
      "learning_rate": 1.566085541871145e-05,
      "loss": 3.684,
      "step": 62
    },
    {
      "epoch": 0.05038488453463961,
      "grad_norm": 4.427576065063477,
      "learning_rate": 1.339745962155613e-05,
      "loss": 3.8579,
      "step": 63
    },
    {
      "epoch": 0.051184644606618014,
      "grad_norm": 5.3037800788879395,
      "learning_rate": 1.129891668217783e-05,
      "loss": 4.1091,
      "step": 64
    },
    {
      "epoch": 0.05198440467859642,
      "grad_norm": 4.853593826293945,
      "learning_rate": 9.369221296335006e-06,
      "loss": 4.2218,
      "step": 65
    },
    {
      "epoch": 0.052784164750574826,
      "grad_norm": 6.393092155456543,
      "learning_rate": 7.612046748871327e-06,
      "loss": 3.8463,
      "step": 66
    },
    {
      "epoch": 0.05358392482255323,
      "grad_norm": 4.756587028503418,
      "learning_rate": 6.030737921409169e-06,
      "loss": 4.0146,
      "step": 67
    },
    {
      "epoch": 0.05438368489453164,
      "grad_norm": 4.337407112121582,
      "learning_rate": 4.628304925177318e-06,
      "loss": 3.5736,
      "step": 68
    },
    {
      "epoch": 0.055183444966510044,
      "grad_norm": 4.383087635040283,
      "learning_rate": 3.40741737109318e-06,
      "loss": 3.7182,
      "step": 69
    },
    {
      "epoch": 0.05598320503848846,
      "grad_norm": 4.449667453765869,
      "learning_rate": 2.3703992880066638e-06,
      "loss": 3.8575,
      "step": 70
    },
    {
      "epoch": 0.05678296511046686,
      "grad_norm": 4.845231533050537,
      "learning_rate": 1.5192246987791981e-06,
      "loss": 3.6972,
      "step": 71
    },
    {
      "epoch": 0.05758272518244527,
      "grad_norm": 4.200953483581543,
      "learning_rate": 8.555138626189618e-07,
      "loss": 3.937,
      "step": 72
    },
    {
      "epoch": 0.058382485254423674,
      "grad_norm": 5.014280319213867,
      "learning_rate": 3.805301908254455e-07,
      "loss": 3.5019,
      "step": 73
    },
    {
      "epoch": 0.05918224532640208,
      "grad_norm": 4.5435919761657715,
      "learning_rate": 9.517784181422019e-08,
      "loss": 4.1094,
      "step": 74
    },
    {
      "epoch": 0.059982005398380486,
      "grad_norm": 4.351820945739746,
      "learning_rate": 0.0,
      "loss": 3.8918,
      "step": 75
    },
    {
      "epoch": 0.059982005398380486,
      "eval_loss": 3.7904601097106934,
      "eval_runtime": 288.9933,
      "eval_samples_per_second": 3.644,
      "eval_steps_per_second": 1.824,
      "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": 1.112831529320448e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}