{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1773049645390071,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017730496453900709,
      "grad_norm": 1.0425547361373901,
      "learning_rate": 1e-05,
      "loss": 1.706,
      "step": 1
    },
    {
      "epoch": 0.0017730496453900709,
      "eval_loss": 1.5571075677871704,
      "eval_runtime": 85.3018,
      "eval_samples_per_second": 5.568,
      "eval_steps_per_second": 0.703,
      "step": 1
    },
    {
      "epoch": 0.0035460992907801418,
      "grad_norm": 1.0336596965789795,
      "learning_rate": 2e-05,
      "loss": 1.7009,
      "step": 2
    },
    {
      "epoch": 0.005319148936170213,
      "grad_norm": 1.0084134340286255,
      "learning_rate": 3e-05,
      "loss": 1.7186,
      "step": 3
    },
    {
      "epoch": 0.0070921985815602835,
      "grad_norm": 0.9495729207992554,
      "learning_rate": 4e-05,
      "loss": 1.5377,
      "step": 4
    },
    {
      "epoch": 0.008865248226950355,
      "grad_norm": 1.0871260166168213,
      "learning_rate": 5e-05,
      "loss": 1.5425,
      "step": 5
    },
    {
      "epoch": 0.010638297872340425,
      "grad_norm": 0.9690693616867065,
      "learning_rate": 6e-05,
      "loss": 1.3581,
      "step": 6
    },
    {
      "epoch": 0.012411347517730497,
      "grad_norm": 1.0647491216659546,
      "learning_rate": 7e-05,
      "loss": 1.4738,
      "step": 7
    },
    {
      "epoch": 0.014184397163120567,
      "grad_norm": 1.152217984199524,
      "learning_rate": 8e-05,
      "loss": 1.3228,
      "step": 8
    },
    {
      "epoch": 0.015957446808510637,
      "grad_norm": 1.1283761262893677,
      "learning_rate": 9e-05,
      "loss": 1.2259,
      "step": 9
    },
    {
      "epoch": 0.015957446808510637,
      "eval_loss": 1.0514769554138184,
      "eval_runtime": 85.2545,
      "eval_samples_per_second": 5.572,
      "eval_steps_per_second": 0.704,
      "step": 9
    },
    {
      "epoch": 0.01773049645390071,
      "grad_norm": 1.226361632347107,
      "learning_rate": 0.0001,
      "loss": 1.1531,
      "step": 10
    },
    {
      "epoch": 0.01950354609929078,
      "grad_norm": 0.9020638465881348,
      "learning_rate": 9.99695413509548e-05,
      "loss": 0.9912,
      "step": 11
    },
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 0.7211796045303345,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.8484,
      "step": 12
    },
    {
      "epoch": 0.02304964539007092,
      "grad_norm": 0.6319678425788879,
      "learning_rate": 9.972609476841367e-05,
      "loss": 0.7357,
      "step": 13
    },
    {
      "epoch": 0.024822695035460994,
      "grad_norm": 0.6404615044593811,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.6613,
      "step": 14
    },
    {
      "epoch": 0.026595744680851064,
      "grad_norm": 0.7243396639823914,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.6481,
      "step": 15
    },
    {
      "epoch": 0.028368794326241134,
      "grad_norm": 0.5668323636054993,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.5135,
      "step": 16
    },
    {
      "epoch": 0.030141843971631204,
      "grad_norm": 0.6436125040054321,
      "learning_rate": 9.851478631379982e-05,
      "loss": 0.5688,
      "step": 17
    },
    {
      "epoch": 0.031914893617021274,
      "grad_norm": 0.8257077932357788,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.5156,
      "step": 18
    },
    {
      "epoch": 0.031914893617021274,
      "eval_loss": 0.5304271578788757,
      "eval_runtime": 85.3128,
      "eval_samples_per_second": 5.568,
      "eval_steps_per_second": 0.703,
      "step": 18
    },
    {
      "epoch": 0.03368794326241135,
      "grad_norm": 0.827019453048706,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.5668,
      "step": 19
    },
    {
      "epoch": 0.03546099290780142,
      "grad_norm": 0.8353906273841858,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.5739,
      "step": 20
    },
    {
      "epoch": 0.03723404255319149,
      "grad_norm": 0.6884241104125977,
      "learning_rate": 9.635919272833938e-05,
      "loss": 0.4368,
      "step": 21
    },
    {
      "epoch": 0.03900709219858156,
      "grad_norm": 0.5974341034889221,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.4444,
      "step": 22
    },
    {
      "epoch": 0.040780141843971635,
      "grad_norm": 0.5769183039665222,
      "learning_rate": 9.493970231495835e-05,
      "loss": 0.4458,
      "step": 23
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 0.512887179851532,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.3521,
      "step": 24
    },
    {
      "epoch": 0.044326241134751775,
      "grad_norm": 0.6440951824188232,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.5032,
      "step": 25
    },
    {
      "epoch": 0.04609929078014184,
      "grad_norm": 0.6105683445930481,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.4236,
      "step": 26
    },
    {
      "epoch": 0.047872340425531915,
      "grad_norm": 0.612863302230835,
      "learning_rate": 9.145187862775209e-05,
      "loss": 0.3652,
      "step": 27
    },
    {
      "epoch": 0.047872340425531915,
      "eval_loss": 0.3773229420185089,
      "eval_runtime": 85.2975,
      "eval_samples_per_second": 5.569,
      "eval_steps_per_second": 0.703,
      "step": 27
    },
    {
      "epoch": 0.04964539007092199,
      "grad_norm": 0.47044283151626587,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.3428,
      "step": 28
    },
    {
      "epoch": 0.051418439716312055,
      "grad_norm": 0.5425423383712769,
      "learning_rate": 8.940053768033609e-05,
      "loss": 0.3305,
      "step": 29
    },
    {
      "epoch": 0.05319148936170213,
      "grad_norm": 0.5877718925476074,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.3485,
      "step": 30
    },
    {
      "epoch": 0.0549645390070922,
      "grad_norm": 0.5542867183685303,
      "learning_rate": 8.715724127386972e-05,
      "loss": 0.3746,
      "step": 31
    },
    {
      "epoch": 0.05673758865248227,
      "grad_norm": 0.5582324266433716,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.4032,
      "step": 32
    },
    {
      "epoch": 0.05851063829787234,
      "grad_norm": 0.4852452278137207,
      "learning_rate": 8.473291852294987e-05,
      "loss": 0.3047,
      "step": 33
    },
    {
      "epoch": 0.06028368794326241,
      "grad_norm": 0.5330655574798584,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.3654,
      "step": 34
    },
    {
      "epoch": 0.06205673758865248,
      "grad_norm": 0.5512088537216187,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.2915,
      "step": 35
    },
    {
      "epoch": 0.06382978723404255,
      "grad_norm": 0.5143958330154419,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.3363,
      "step": 36
    },
    {
      "epoch": 0.06382978723404255,
      "eval_loss": 0.32617101073265076,
      "eval_runtime": 85.2732,
      "eval_samples_per_second": 5.57,
      "eval_steps_per_second": 0.704,
      "step": 36
    },
    {
      "epoch": 0.06560283687943262,
      "grad_norm": 0.5888123512268066,
      "learning_rate": 7.938926261462366e-05,
      "loss": 0.4433,
      "step": 37
    },
    {
      "epoch": 0.0673758865248227,
      "grad_norm": 0.5405781865119934,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.3826,
      "step": 38
    },
    {
      "epoch": 0.06914893617021277,
      "grad_norm": 0.5684509873390198,
      "learning_rate": 7.649596321166024e-05,
      "loss": 0.3074,
      "step": 39
    },
    {
      "epoch": 0.07092198581560284,
      "grad_norm": 0.5357254147529602,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.3527,
      "step": 40
    },
    {
      "epoch": 0.0726950354609929,
      "grad_norm": 0.5242685675621033,
      "learning_rate": 7.347357813929454e-05,
      "loss": 0.3603,
      "step": 41
    },
    {
      "epoch": 0.07446808510638298,
      "grad_norm": 0.487697571516037,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.2892,
      "step": 42
    },
    {
      "epoch": 0.07624113475177305,
      "grad_norm": 0.4527439773082733,
      "learning_rate": 7.033683215379002e-05,
      "loss": 0.2569,
      "step": 43
    },
    {
      "epoch": 0.07801418439716312,
      "grad_norm": 0.49759769439697266,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.2744,
      "step": 44
    },
    {
      "epoch": 0.0797872340425532,
      "grad_norm": 0.5503877997398376,
      "learning_rate": 6.710100716628344e-05,
      "loss": 0.3245,
      "step": 45
    },
    {
      "epoch": 0.0797872340425532,
      "eval_loss": 0.29267728328704834,
      "eval_runtime": 85.2478,
      "eval_samples_per_second": 5.572,
      "eval_steps_per_second": 0.704,
      "step": 45
    },
    {
      "epoch": 0.08156028368794327,
      "grad_norm": 0.6225173473358154,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.3491,
      "step": 46
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.631844699382782,
      "learning_rate": 6.378186779084995e-05,
      "loss": 0.2375,
      "step": 47
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 0.7838373184204102,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.3831,
      "step": 48
    },
    {
      "epoch": 0.08687943262411348,
      "grad_norm": 0.5574771165847778,
      "learning_rate": 6.0395584540887963e-05,
      "loss": 0.293,
      "step": 49
    },
    {
      "epoch": 0.08865248226950355,
      "grad_norm": 0.5543034076690674,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.256,
      "step": 50
    },
    {
      "epoch": 0.09042553191489362,
      "grad_norm": 0.5195747017860413,
      "learning_rate": 5.695865504800327e-05,
      "loss": 0.232,
      "step": 51
    },
    {
      "epoch": 0.09219858156028368,
      "grad_norm": 0.5101114511489868,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.2679,
      "step": 52
    },
    {
      "epoch": 0.09397163120567376,
      "grad_norm": 0.46232369542121887,
      "learning_rate": 5.348782368720626e-05,
      "loss": 0.2772,
      "step": 53
    },
    {
      "epoch": 0.09574468085106383,
      "grad_norm": 0.5173928141593933,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.2755,
      "step": 54
    },
    {
      "epoch": 0.09574468085106383,
      "eval_loss": 0.27359503507614136,
      "eval_runtime": 85.266,
      "eval_samples_per_second": 5.571,
      "eval_steps_per_second": 0.704,
      "step": 54
    },
    {
      "epoch": 0.0975177304964539,
      "grad_norm": 0.5527864694595337,
      "learning_rate": 5e-05,
      "loss": 0.3412,
      "step": 55
    },
    {
      "epoch": 0.09929078014184398,
      "grad_norm": 0.4534193277359009,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.2381,
      "step": 56
    },
    {
      "epoch": 0.10106382978723404,
      "grad_norm": 0.49728792905807495,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 0.2389,
      "step": 57
    },
    {
      "epoch": 0.10283687943262411,
      "grad_norm": 0.6069850921630859,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.308,
      "step": 58
    },
    {
      "epoch": 0.10460992907801418,
      "grad_norm": 0.5545309782028198,
      "learning_rate": 4.3041344951996746e-05,
      "loss": 0.2807,
      "step": 59
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 0.6561558246612549,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.3066,
      "step": 60
    },
    {
      "epoch": 0.10815602836879433,
      "grad_norm": 0.5162850022315979,
      "learning_rate": 3.960441545911204e-05,
      "loss": 0.2459,
      "step": 61
    },
    {
      "epoch": 0.1099290780141844,
      "grad_norm": 0.6705155372619629,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.4057,
      "step": 62
    },
    {
      "epoch": 0.11170212765957446,
      "grad_norm": 0.5775429010391235,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 0.2761,
      "step": 63
    },
    {
      "epoch": 0.11170212765957446,
      "eval_loss": 0.25868135690689087,
      "eval_runtime": 85.2805,
      "eval_samples_per_second": 5.57,
      "eval_steps_per_second": 0.704,
      "step": 63
    },
    {
      "epoch": 0.11347517730496454,
      "grad_norm": 0.5817871689796448,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.2793,
      "step": 64
    },
    {
      "epoch": 0.11524822695035461,
      "grad_norm": 0.6233260631561279,
      "learning_rate": 3.289899283371657e-05,
      "loss": 0.2508,
      "step": 65
    },
    {
      "epoch": 0.11702127659574468,
      "grad_norm": 0.4717574715614319,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.2132,
      "step": 66
    },
    {
      "epoch": 0.11879432624113476,
      "grad_norm": 0.6881227493286133,
      "learning_rate": 2.9663167846209998e-05,
      "loss": 0.3046,
      "step": 67
    },
    {
      "epoch": 0.12056737588652482,
      "grad_norm": 0.5428065061569214,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.2845,
      "step": 68
    },
    {
      "epoch": 0.12234042553191489,
      "grad_norm": 0.6920152306556702,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 0.3518,
      "step": 69
    },
    {
      "epoch": 0.12411347517730496,
      "grad_norm": 0.6600857973098755,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.3348,
      "step": 70
    },
    {
      "epoch": 0.12588652482269502,
      "grad_norm": 0.5283850431442261,
      "learning_rate": 2.350403678833976e-05,
      "loss": 0.2248,
      "step": 71
    },
    {
      "epoch": 0.1276595744680851,
      "grad_norm": 0.5939657688140869,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.288,
      "step": 72
    },
    {
      "epoch": 0.1276595744680851,
      "eval_loss": 0.24900592863559723,
      "eval_runtime": 85.2474,
      "eval_samples_per_second": 5.572,
      "eval_steps_per_second": 0.704,
      "step": 72
    },
    {
      "epoch": 0.12943262411347517,
      "grad_norm": 0.5134656429290771,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.2476,
      "step": 73
    },
    {
      "epoch": 0.13120567375886524,
      "grad_norm": 0.5056303143501282,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.2025,
      "step": 74
    },
    {
      "epoch": 0.13297872340425532,
      "grad_norm": 0.5294190049171448,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 0.2336,
      "step": 75
    },
    {
      "epoch": 0.1347517730496454,
      "grad_norm": 0.4144452214241028,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.2263,
      "step": 76
    },
    {
      "epoch": 0.13652482269503546,
      "grad_norm": 0.5535529851913452,
      "learning_rate": 1.526708147705013e-05,
      "loss": 0.2731,
      "step": 77
    },
    {
      "epoch": 0.13829787234042554,
      "grad_norm": 0.6666750907897949,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.2748,
      "step": 78
    },
    {
      "epoch": 0.1400709219858156,
      "grad_norm": 0.5558615326881409,
      "learning_rate": 1.2842758726130283e-05,
      "loss": 0.2561,
      "step": 79
    },
    {
      "epoch": 0.14184397163120568,
      "grad_norm": 0.675848662853241,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.3053,
      "step": 80
    },
    {
      "epoch": 0.14361702127659576,
      "grad_norm": 0.6196485161781311,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 0.2637,
      "step": 81
    },
    {
      "epoch": 0.14361702127659576,
      "eval_loss": 0.24386928975582123,
      "eval_runtime": 85.2732,
      "eval_samples_per_second": 5.57,
      "eval_steps_per_second": 0.704,
      "step": 81
    },
    {
      "epoch": 0.1453900709219858,
      "grad_norm": 0.7320723533630371,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.3557,
      "step": 82
    },
    {
      "epoch": 0.14716312056737588,
      "grad_norm": 0.6170211434364319,
      "learning_rate": 8.548121372247918e-06,
      "loss": 0.288,
      "step": 83
    },
    {
      "epoch": 0.14893617021276595,
      "grad_norm": 0.5411659479141235,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.269,
      "step": 84
    },
    {
      "epoch": 0.15070921985815602,
      "grad_norm": 0.6507031321525574,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2579,
      "step": 85
    },
    {
      "epoch": 0.1524822695035461,
      "grad_norm": 0.4847683608531952,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.2108,
      "step": 86
    },
    {
      "epoch": 0.15425531914893617,
      "grad_norm": 0.5241921544075012,
      "learning_rate": 5.060297685041659e-06,
      "loss": 0.2421,
      "step": 87
    },
    {
      "epoch": 0.15602836879432624,
      "grad_norm": 0.5839644074440002,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.2381,
      "step": 88
    },
    {
      "epoch": 0.15780141843971632,
      "grad_norm": 0.5057505965232849,
      "learning_rate": 3.6408072716606346e-06,
      "loss": 0.2041,
      "step": 89
    },
    {
      "epoch": 0.1595744680851064,
      "grad_norm": 0.5602439045906067,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.2442,
      "step": 90
    },
    {
      "epoch": 0.1595744680851064,
      "eval_loss": 0.24139147996902466,
      "eval_runtime": 85.2729,
      "eval_samples_per_second": 5.57,
      "eval_steps_per_second": 0.704,
      "step": 90
    },
    {
      "epoch": 0.16134751773049646,
      "grad_norm": 0.7721632122993469,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.2454,
      "step": 91
    },
    {
      "epoch": 0.16312056737588654,
      "grad_norm": 0.7036444544792175,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.2381,
      "step": 92
    },
    {
      "epoch": 0.16489361702127658,
      "grad_norm": 0.6270337104797363,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 0.2547,
      "step": 93
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.4347127676010132,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.222,
      "step": 94
    },
    {
      "epoch": 0.16843971631205673,
      "grad_norm": 0.5513346791267395,
      "learning_rate": 7.596123493895991e-07,
      "loss": 0.2501,
      "step": 95
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 0.5058043003082275,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.2783,
      "step": 96
    },
    {
      "epoch": 0.17198581560283688,
      "grad_norm": 0.5748170018196106,
      "learning_rate": 2.7390523158633554e-07,
      "loss": 0.2392,
      "step": 97
    },
    {
      "epoch": 0.17375886524822695,
      "grad_norm": 0.6403087377548218,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.2768,
      "step": 98
    },
    {
      "epoch": 0.17553191489361702,
      "grad_norm": 0.5376163125038147,
      "learning_rate": 3.04586490452119e-08,
      "loss": 0.2586,
      "step": 99
    },
    {
      "epoch": 0.17553191489361702,
      "eval_loss": 0.24068014323711395,
      "eval_runtime": 85.2941,
      "eval_samples_per_second": 5.569,
      "eval_steps_per_second": 0.703,
      "step": 99
    },
    {
      "epoch": 0.1773049645390071,
      "grad_norm": 0.5339375138282776,
      "learning_rate": 0.0,
      "loss": 0.2779,
      "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": 4.642695731478528e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}