{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1662510390689942,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016625103906899418,
      "grad_norm": 0.04670165851712227,
      "learning_rate": 1e-05,
      "loss": 11.7674,
      "step": 1
    },
    {
      "epoch": 0.0016625103906899418,
      "eval_loss": 11.760279655456543,
      "eval_runtime": 10.8414,
      "eval_samples_per_second": 46.765,
      "eval_steps_per_second": 5.903,
      "step": 1
    },
    {
      "epoch": 0.0033250207813798837,
      "grad_norm": 0.04368332028388977,
      "learning_rate": 2e-05,
      "loss": 11.7606,
      "step": 2
    },
    {
      "epoch": 0.004987531172069825,
      "grad_norm": 0.044506169855594635,
      "learning_rate": 3e-05,
      "loss": 11.7567,
      "step": 3
    },
    {
      "epoch": 0.006650041562759767,
      "grad_norm": 0.0508490614593029,
      "learning_rate": 4e-05,
      "loss": 11.7595,
      "step": 4
    },
    {
      "epoch": 0.00831255195344971,
      "grad_norm": 0.044127244502305984,
      "learning_rate": 5e-05,
      "loss": 11.7587,
      "step": 5
    },
    {
      "epoch": 0.00997506234413965,
      "grad_norm": 0.05494147166609764,
      "learning_rate": 6e-05,
      "loss": 11.7636,
      "step": 6
    },
    {
      "epoch": 0.011637572734829594,
      "grad_norm": 0.044881321489810944,
      "learning_rate": 7e-05,
      "loss": 11.7567,
      "step": 7
    },
    {
      "epoch": 0.013300083125519535,
      "grad_norm": 0.05256935581564903,
      "learning_rate": 8e-05,
      "loss": 11.7558,
      "step": 8
    },
    {
      "epoch": 0.014962593516209476,
      "grad_norm": 0.05547723546624184,
      "learning_rate": 9e-05,
      "loss": 11.7578,
      "step": 9
    },
    {
      "epoch": 0.014962593516209476,
      "eval_loss": 11.760008811950684,
      "eval_runtime": 10.8532,
      "eval_samples_per_second": 46.714,
      "eval_steps_per_second": 5.897,
      "step": 9
    },
    {
      "epoch": 0.01662510390689942,
      "grad_norm": 0.050355251878499985,
      "learning_rate": 0.0001,
      "loss": 11.7521,
      "step": 10
    },
    {
      "epoch": 0.01828761429758936,
      "grad_norm": 0.05273785442113876,
      "learning_rate": 9.99695413509548e-05,
      "loss": 11.7576,
      "step": 11
    },
    {
      "epoch": 0.0199501246882793,
      "grad_norm": 0.047757700085639954,
      "learning_rate": 9.987820251299122e-05,
      "loss": 11.7637,
      "step": 12
    },
    {
      "epoch": 0.021612635078969242,
      "grad_norm": 0.04381760209798813,
      "learning_rate": 9.972609476841367e-05,
      "loss": 11.7615,
      "step": 13
    },
    {
      "epoch": 0.023275145469659187,
      "grad_norm": 0.05205358564853668,
      "learning_rate": 9.951340343707852e-05,
      "loss": 11.7624,
      "step": 14
    },
    {
      "epoch": 0.02493765586034913,
      "grad_norm": 0.05228843539953232,
      "learning_rate": 9.924038765061042e-05,
      "loss": 11.7613,
      "step": 15
    },
    {
      "epoch": 0.02660016625103907,
      "grad_norm": 0.04606500267982483,
      "learning_rate": 9.890738003669029e-05,
      "loss": 11.7586,
      "step": 16
    },
    {
      "epoch": 0.02826267664172901,
      "grad_norm": 0.05653437227010727,
      "learning_rate": 9.851478631379982e-05,
      "loss": 11.7601,
      "step": 17
    },
    {
      "epoch": 0.029925187032418952,
      "grad_norm": 0.049704670906066895,
      "learning_rate": 9.806308479691595e-05,
      "loss": 11.7634,
      "step": 18
    },
    {
      "epoch": 0.029925187032418952,
      "eval_loss": 11.759297370910645,
      "eval_runtime": 10.8593,
      "eval_samples_per_second": 46.688,
      "eval_steps_per_second": 5.894,
      "step": 18
    },
    {
      "epoch": 0.03158769742310889,
      "grad_norm": 0.06516430526971817,
      "learning_rate": 9.755282581475769e-05,
      "loss": 11.7569,
      "step": 19
    },
    {
      "epoch": 0.03325020781379884,
      "grad_norm": 0.05210546776652336,
      "learning_rate": 9.698463103929542e-05,
      "loss": 11.7583,
      "step": 20
    },
    {
      "epoch": 0.034912718204488775,
      "grad_norm": 0.05196945369243622,
      "learning_rate": 9.635919272833938e-05,
      "loss": 11.7641,
      "step": 21
    },
    {
      "epoch": 0.03657522859517872,
      "grad_norm": 0.052862655371427536,
      "learning_rate": 9.567727288213005e-05,
      "loss": 11.7536,
      "step": 22
    },
    {
      "epoch": 0.038237738985868665,
      "grad_norm": 0.05532236397266388,
      "learning_rate": 9.493970231495835e-05,
      "loss": 11.756,
      "step": 23
    },
    {
      "epoch": 0.0399002493765586,
      "grad_norm": 0.05812180042266846,
      "learning_rate": 9.414737964294636e-05,
      "loss": 11.7572,
      "step": 24
    },
    {
      "epoch": 0.04156275976724855,
      "grad_norm": 0.06880798190832138,
      "learning_rate": 9.330127018922194e-05,
      "loss": 11.7558,
      "step": 25
    },
    {
      "epoch": 0.043225270157938485,
      "grad_norm": 0.06178494170308113,
      "learning_rate": 9.24024048078213e-05,
      "loss": 11.7574,
      "step": 26
    },
    {
      "epoch": 0.04488778054862843,
      "grad_norm": 0.055603306740522385,
      "learning_rate": 9.145187862775209e-05,
      "loss": 11.7611,
      "step": 27
    },
    {
      "epoch": 0.04488778054862843,
      "eval_loss": 11.758519172668457,
      "eval_runtime": 10.6894,
      "eval_samples_per_second": 47.43,
      "eval_steps_per_second": 5.987,
      "step": 27
    },
    {
      "epoch": 0.046550290939318374,
      "grad_norm": 0.047771960496902466,
      "learning_rate": 9.045084971874738e-05,
      "loss": 11.7565,
      "step": 28
    },
    {
      "epoch": 0.04821280133000831,
      "grad_norm": 0.061024993658065796,
      "learning_rate": 8.940053768033609e-05,
      "loss": 11.7541,
      "step": 29
    },
    {
      "epoch": 0.04987531172069826,
      "grad_norm": 0.06483989953994751,
      "learning_rate": 8.83022221559489e-05,
      "loss": 11.7603,
      "step": 30
    },
    {
      "epoch": 0.051537822111388194,
      "grad_norm": 0.05010339245200157,
      "learning_rate": 8.715724127386972e-05,
      "loss": 11.7539,
      "step": 31
    },
    {
      "epoch": 0.05320033250207814,
      "grad_norm": 0.04719735309481621,
      "learning_rate": 8.596699001693255e-05,
      "loss": 11.7539,
      "step": 32
    },
    {
      "epoch": 0.05486284289276808,
      "grad_norm": 0.05507144331932068,
      "learning_rate": 8.473291852294987e-05,
      "loss": 11.7593,
      "step": 33
    },
    {
      "epoch": 0.05652535328345802,
      "grad_norm": 0.0661148950457573,
      "learning_rate": 8.345653031794292e-05,
      "loss": 11.7532,
      "step": 34
    },
    {
      "epoch": 0.058187863674147966,
      "grad_norm": 0.08241010457277298,
      "learning_rate": 8.213938048432697e-05,
      "loss": 11.756,
      "step": 35
    },
    {
      "epoch": 0.059850374064837904,
      "grad_norm": 0.06910108774900436,
      "learning_rate": 8.07830737662829e-05,
      "loss": 11.7557,
      "step": 36
    },
    {
      "epoch": 0.059850374064837904,
      "eval_loss": 11.757696151733398,
      "eval_runtime": 10.6836,
      "eval_samples_per_second": 47.456,
      "eval_steps_per_second": 5.99,
      "step": 36
    },
    {
      "epoch": 0.06151288445552785,
      "grad_norm": 0.058035943657159805,
      "learning_rate": 7.938926261462366e-05,
      "loss": 11.7563,
      "step": 37
    },
    {
      "epoch": 0.06317539484621779,
      "grad_norm": 0.06133880466222763,
      "learning_rate": 7.795964517353735e-05,
      "loss": 11.757,
      "step": 38
    },
    {
      "epoch": 0.06483790523690773,
      "grad_norm": 0.05848357081413269,
      "learning_rate": 7.649596321166024e-05,
      "loss": 11.752,
      "step": 39
    },
    {
      "epoch": 0.06650041562759768,
      "grad_norm": 0.05439987778663635,
      "learning_rate": 7.500000000000001e-05,
      "loss": 11.7565,
      "step": 40
    },
    {
      "epoch": 0.06816292601828762,
      "grad_norm": 0.06417480856180191,
      "learning_rate": 7.347357813929454e-05,
      "loss": 11.7488,
      "step": 41
    },
    {
      "epoch": 0.06982543640897755,
      "grad_norm": 0.061617761850357056,
      "learning_rate": 7.191855733945387e-05,
      "loss": 11.7599,
      "step": 42
    },
    {
      "epoch": 0.0714879467996675,
      "grad_norm": 0.051751330494880676,
      "learning_rate": 7.033683215379002e-05,
      "loss": 11.7565,
      "step": 43
    },
    {
      "epoch": 0.07315045719035744,
      "grad_norm": 0.0564432330429554,
      "learning_rate": 6.873032967079561e-05,
      "loss": 11.7629,
      "step": 44
    },
    {
      "epoch": 0.07481296758104738,
      "grad_norm": 0.05816029757261276,
      "learning_rate": 6.710100716628344e-05,
      "loss": 11.7613,
      "step": 45
    },
    {
      "epoch": 0.07481296758104738,
      "eval_loss": 11.756857872009277,
      "eval_runtime": 10.9655,
      "eval_samples_per_second": 46.236,
      "eval_steps_per_second": 5.836,
      "step": 45
    },
    {
      "epoch": 0.07647547797173733,
      "grad_norm": 0.08202195912599564,
      "learning_rate": 6.545084971874738e-05,
      "loss": 11.7502,
      "step": 46
    },
    {
      "epoch": 0.07813798836242726,
      "grad_norm": 0.06265095621347427,
      "learning_rate": 6.378186779084995e-05,
      "loss": 11.7583,
      "step": 47
    },
    {
      "epoch": 0.0798004987531172,
      "grad_norm": 0.09170009940862656,
      "learning_rate": 6.209609477998338e-05,
      "loss": 11.7566,
      "step": 48
    },
    {
      "epoch": 0.08146300914380715,
      "grad_norm": 0.06977274268865585,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 11.7544,
      "step": 49
    },
    {
      "epoch": 0.0831255195344971,
      "grad_norm": 0.060967620462179184,
      "learning_rate": 5.868240888334653e-05,
      "loss": 11.754,
      "step": 50
    },
    {
      "epoch": 0.08478802992518704,
      "grad_norm": 0.0709136351943016,
      "learning_rate": 5.695865504800327e-05,
      "loss": 11.756,
      "step": 51
    },
    {
      "epoch": 0.08645054031587697,
      "grad_norm": 0.05604271590709686,
      "learning_rate": 5.522642316338268e-05,
      "loss": 11.7583,
      "step": 52
    },
    {
      "epoch": 0.08811305070656691,
      "grad_norm": 0.06510225683450699,
      "learning_rate": 5.348782368720626e-05,
      "loss": 11.7568,
      "step": 53
    },
    {
      "epoch": 0.08977556109725686,
      "grad_norm": 0.06891396641731262,
      "learning_rate": 5.174497483512506e-05,
      "loss": 11.7463,
      "step": 54
    },
    {
      "epoch": 0.08977556109725686,
      "eval_loss": 11.756059646606445,
      "eval_runtime": 10.8526,
      "eval_samples_per_second": 46.717,
      "eval_steps_per_second": 5.897,
      "step": 54
    },
    {
      "epoch": 0.0914380714879468,
      "grad_norm": 0.05632815137505531,
      "learning_rate": 5e-05,
      "loss": 11.7531,
      "step": 55
    },
    {
      "epoch": 0.09310058187863675,
      "grad_norm": 0.0708206370472908,
      "learning_rate": 4.825502516487497e-05,
      "loss": 11.7558,
      "step": 56
    },
    {
      "epoch": 0.09476309226932668,
      "grad_norm": 0.08333998173475266,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 11.7516,
      "step": 57
    },
    {
      "epoch": 0.09642560266001662,
      "grad_norm": 0.06372737884521484,
      "learning_rate": 4.477357683661734e-05,
      "loss": 11.7488,
      "step": 58
    },
    {
      "epoch": 0.09808811305070657,
      "grad_norm": 0.05615927651524544,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 11.7482,
      "step": 59
    },
    {
      "epoch": 0.09975062344139651,
      "grad_norm": 0.0624222457408905,
      "learning_rate": 4.131759111665349e-05,
      "loss": 11.7565,
      "step": 60
    },
    {
      "epoch": 0.10141313383208644,
      "grad_norm": 0.06704821437597275,
      "learning_rate": 3.960441545911204e-05,
      "loss": 11.7547,
      "step": 61
    },
    {
      "epoch": 0.10307564422277639,
      "grad_norm": 0.09131279587745667,
      "learning_rate": 3.790390522001662e-05,
      "loss": 11.7494,
      "step": 62
    },
    {
      "epoch": 0.10473815461346633,
      "grad_norm": 0.06280036270618439,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 11.7585,
      "step": 63
    },
    {
      "epoch": 0.10473815461346633,
      "eval_loss": 11.755424499511719,
      "eval_runtime": 10.8532,
      "eval_samples_per_second": 46.714,
      "eval_steps_per_second": 5.897,
      "step": 63
    },
    {
      "epoch": 0.10640066500415628,
      "grad_norm": 0.07713477313518524,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 11.7581,
      "step": 64
    },
    {
      "epoch": 0.10806317539484622,
      "grad_norm": 0.080855593085289,
      "learning_rate": 3.289899283371657e-05,
      "loss": 11.7548,
      "step": 65
    },
    {
      "epoch": 0.10972568578553615,
      "grad_norm": 0.06689275801181793,
      "learning_rate": 3.12696703292044e-05,
      "loss": 11.7557,
      "step": 66
    },
    {
      "epoch": 0.1113881961762261,
      "grad_norm": 0.0768292099237442,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 11.7577,
      "step": 67
    },
    {
      "epoch": 0.11305070656691604,
      "grad_norm": 0.052165545523166656,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 11.7578,
      "step": 68
    },
    {
      "epoch": 0.11471321695760599,
      "grad_norm": 0.07575516402721405,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 11.7549,
      "step": 69
    },
    {
      "epoch": 0.11637572734829593,
      "grad_norm": 0.05817292258143425,
      "learning_rate": 2.500000000000001e-05,
      "loss": 11.7565,
      "step": 70
    },
    {
      "epoch": 0.11803823773898586,
      "grad_norm": 0.07991883158683777,
      "learning_rate": 2.350403678833976e-05,
      "loss": 11.7516,
      "step": 71
    },
    {
      "epoch": 0.11970074812967581,
      "grad_norm": 0.06573547422885895,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 11.7566,
      "step": 72
    },
    {
      "epoch": 0.11970074812967581,
      "eval_loss": 11.754947662353516,
      "eval_runtime": 10.8431,
      "eval_samples_per_second": 46.758,
      "eval_steps_per_second": 5.902,
      "step": 72
    },
    {
      "epoch": 0.12136325852036575,
      "grad_norm": 0.07040063291788101,
      "learning_rate": 2.061073738537635e-05,
      "loss": 11.7524,
      "step": 73
    },
    {
      "epoch": 0.1230257689110557,
      "grad_norm": 0.05799221619963646,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 11.7536,
      "step": 74
    },
    {
      "epoch": 0.12468827930174564,
      "grad_norm": 0.06470559537410736,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 11.7533,
      "step": 75
    },
    {
      "epoch": 0.12635078969243557,
      "grad_norm": 0.0871320515871048,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 11.759,
      "step": 76
    },
    {
      "epoch": 0.12801330008312553,
      "grad_norm": 0.09251094609498978,
      "learning_rate": 1.526708147705013e-05,
      "loss": 11.7559,
      "step": 77
    },
    {
      "epoch": 0.12967581047381546,
      "grad_norm": 0.08235142379999161,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 11.7498,
      "step": 78
    },
    {
      "epoch": 0.1313383208645054,
      "grad_norm": 0.08003734797239304,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 11.7497,
      "step": 79
    },
    {
      "epoch": 0.13300083125519535,
      "grad_norm": 0.06140708178281784,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 11.7542,
      "step": 80
    },
    {
      "epoch": 0.13466334164588528,
      "grad_norm": 0.06575233489274979,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 11.7592,
      "step": 81
    },
    {
      "epoch": 0.13466334164588528,
      "eval_loss": 11.754680633544922,
      "eval_runtime": 10.852,
      "eval_samples_per_second": 46.719,
      "eval_steps_per_second": 5.898,
      "step": 81
    },
    {
      "epoch": 0.13632585203657524,
      "grad_norm": 0.06072350591421127,
      "learning_rate": 9.549150281252633e-06,
      "loss": 11.7557,
      "step": 82
    },
    {
      "epoch": 0.13798836242726517,
      "grad_norm": 0.07811221480369568,
      "learning_rate": 8.548121372247918e-06,
      "loss": 11.7565,
      "step": 83
    },
    {
      "epoch": 0.1396508728179551,
      "grad_norm": 0.09204588085412979,
      "learning_rate": 7.597595192178702e-06,
      "loss": 11.7634,
      "step": 84
    },
    {
      "epoch": 0.14131338320864506,
      "grad_norm": 0.07153452932834625,
      "learning_rate": 6.698729810778065e-06,
      "loss": 11.7585,
      "step": 85
    },
    {
      "epoch": 0.142975893599335,
      "grad_norm": 0.08605170249938965,
      "learning_rate": 5.852620357053651e-06,
      "loss": 11.7568,
      "step": 86
    },
    {
      "epoch": 0.14463840399002495,
      "grad_norm": 0.08406588435173035,
      "learning_rate": 5.060297685041659e-06,
      "loss": 11.7558,
      "step": 87
    },
    {
      "epoch": 0.14630091438071488,
      "grad_norm": 0.07880561798810959,
      "learning_rate": 4.322727117869951e-06,
      "loss": 11.7556,
      "step": 88
    },
    {
      "epoch": 0.1479634247714048,
      "grad_norm": 0.05538419634103775,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 11.7538,
      "step": 89
    },
    {
      "epoch": 0.14962593516209477,
      "grad_norm": 0.07911358028650284,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 11.7514,
      "step": 90
    },
    {
      "epoch": 0.14962593516209477,
      "eval_loss": 11.754559516906738,
      "eval_runtime": 10.6897,
      "eval_samples_per_second": 47.429,
      "eval_steps_per_second": 5.987,
      "step": 90
    },
    {
      "epoch": 0.1512884455527847,
      "grad_norm": 0.07232284545898438,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 11.7607,
      "step": 91
    },
    {
      "epoch": 0.15295095594347466,
      "grad_norm": 0.09192491322755814,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 11.7541,
      "step": 92
    },
    {
      "epoch": 0.1546134663341646,
      "grad_norm": 0.07534570246934891,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 11.7526,
      "step": 93
    },
    {
      "epoch": 0.15627597672485452,
      "grad_norm": 0.09265202283859253,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 11.757,
      "step": 94
    },
    {
      "epoch": 0.15793848711554448,
      "grad_norm": 0.10842297971248627,
      "learning_rate": 7.596123493895991e-07,
      "loss": 11.7572,
      "step": 95
    },
    {
      "epoch": 0.1596009975062344,
      "grad_norm": 0.06330010294914246,
      "learning_rate": 4.865965629214819e-07,
      "loss": 11.7508,
      "step": 96
    },
    {
      "epoch": 0.16126350789692437,
      "grad_norm": 0.08400006592273712,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 11.7589,
      "step": 97
    },
    {
      "epoch": 0.1629260182876143,
      "grad_norm": 0.08327385783195496,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 11.7501,
      "step": 98
    },
    {
      "epoch": 0.16458852867830423,
      "grad_norm": 0.08100760728120804,
      "learning_rate": 3.04586490452119e-08,
      "loss": 11.7602,
      "step": 99
    },
    {
      "epoch": 0.16458852867830423,
      "eval_loss": 11.754537582397461,
      "eval_runtime": 10.6869,
      "eval_samples_per_second": 47.441,
      "eval_steps_per_second": 5.989,
      "step": 99
    },
    {
      "epoch": 0.1662510390689942,
      "grad_norm": 0.07855262607336044,
      "learning_rate": 0.0,
      "loss": 11.7542,
      "step": 100
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 20370004377600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}