{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1027221366204417,
  "eval_steps": 10,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001027221366204417,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7525,
      "step": 1
    },
    {
      "epoch": 0.002054442732408834,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7605,
      "step": 2
    },
    {
      "epoch": 0.0030816640986132513,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8008,
      "step": 3
    },
    {
      "epoch": 0.004108885464817668,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.809,
      "step": 4
    },
    {
      "epoch": 0.005136106831022085,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7841,
      "step": 5
    },
    {
      "epoch": 0.0061633281972265025,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7924,
      "step": 6
    },
    {
      "epoch": 0.007190549563430919,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7732,
      "step": 7
    },
    {
      "epoch": 0.008217770929635337,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7953,
      "step": 8
    },
    {
      "epoch": 0.009244992295839754,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7747,
      "step": 9
    },
    {
      "epoch": 0.01027221366204417,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7909,
      "step": 10
    },
    {
      "epoch": 0.01027221366204417,
      "eval_loss": 2.811410665512085,
      "eval_runtime": 37.9307,
      "eval_samples_per_second": 26.364,
      "eval_steps_per_second": 1.107,
      "step": 10
    },
    {
      "epoch": 0.011299435028248588,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7592,
      "step": 11
    },
    {
      "epoch": 0.012326656394453005,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7394,
      "step": 12
    },
    {
      "epoch": 0.01335387776065742,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8111,
      "step": 13
    },
    {
      "epoch": 0.014381099126861838,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7786,
      "step": 14
    },
    {
      "epoch": 0.015408320493066256,
      "grad_norm": 5.814355373382568,
      "learning_rate": 1.7123287671232876e-08,
      "loss": 2.7711,
      "step": 15
    },
    {
      "epoch": 0.016435541859270673,
      "grad_norm": 6.2984514236450195,
      "learning_rate": 3.424657534246575e-08,
      "loss": 2.7517,
      "step": 16
    },
    {
      "epoch": 0.01746276322547509,
      "grad_norm": 6.235473155975342,
      "learning_rate": 5.136986301369863e-08,
      "loss": 2.7191,
      "step": 17
    },
    {
      "epoch": 0.01848998459167951,
      "grad_norm": 6.235473155975342,
      "learning_rate": 5.136986301369863e-08,
      "loss": 2.806,
      "step": 18
    },
    {
      "epoch": 0.019517205957883924,
      "grad_norm": 6.621068000793457,
      "learning_rate": 6.84931506849315e-08,
      "loss": 2.7192,
      "step": 19
    },
    {
      "epoch": 0.02054442732408834,
      "grad_norm": 6.781496524810791,
      "learning_rate": 8.561643835616439e-08,
      "loss": 2.7862,
      "step": 20
    },
    {
      "epoch": 0.02054442732408834,
      "eval_loss": 2.8109023571014404,
      "eval_runtime": 37.527,
      "eval_samples_per_second": 26.647,
      "eval_steps_per_second": 1.119,
      "step": 20
    },
    {
      "epoch": 0.02157164869029276,
      "grad_norm": 6.336451530456543,
      "learning_rate": 1.0273972602739726e-07,
      "loss": 2.7997,
      "step": 21
    },
    {
      "epoch": 0.022598870056497175,
      "grad_norm": 6.184426307678223,
      "learning_rate": 1.1986301369863014e-07,
      "loss": 2.7938,
      "step": 22
    },
    {
      "epoch": 0.02362609142270159,
      "grad_norm": 6.443874359130859,
      "learning_rate": 1.36986301369863e-07,
      "loss": 2.7485,
      "step": 23
    },
    {
      "epoch": 0.02465331278890601,
      "grad_norm": 6.17667293548584,
      "learning_rate": 1.541095890410959e-07,
      "loss": 2.7779,
      "step": 24
    },
    {
      "epoch": 0.025680534155110426,
      "grad_norm": 5.850281715393066,
      "learning_rate": 1.7123287671232878e-07,
      "loss": 2.7598,
      "step": 25
    },
    {
      "epoch": 0.02670775552131484,
      "grad_norm": 5.788112640380859,
      "learning_rate": 1.8835616438356165e-07,
      "loss": 2.7837,
      "step": 26
    },
    {
      "epoch": 0.02773497688751926,
      "grad_norm": 5.17655086517334,
      "learning_rate": 2.0547945205479452e-07,
      "loss": 2.7513,
      "step": 27
    },
    {
      "epoch": 0.028762198253723677,
      "grad_norm": 4.698268890380859,
      "learning_rate": 2.226027397260274e-07,
      "loss": 2.7714,
      "step": 28
    },
    {
      "epoch": 0.029789419619928096,
      "grad_norm": 4.562674522399902,
      "learning_rate": 2.397260273972603e-07,
      "loss": 2.7759,
      "step": 29
    },
    {
      "epoch": 0.030816640986132512,
      "grad_norm": 4.138142108917236,
      "learning_rate": 2.568493150684932e-07,
      "loss": 2.7656,
      "step": 30
    },
    {
      "epoch": 0.030816640986132512,
      "eval_loss": 2.784187078475952,
      "eval_runtime": 36.9691,
      "eval_samples_per_second": 27.05,
      "eval_steps_per_second": 1.136,
      "step": 30
    },
    {
      "epoch": 0.03184386235233693,
      "grad_norm": 4.39779806137085,
      "learning_rate": 2.73972602739726e-07,
      "loss": 2.7377,
      "step": 31
    },
    {
      "epoch": 0.03287108371854135,
      "grad_norm": 3.9160122871398926,
      "learning_rate": 2.910958904109589e-07,
      "loss": 2.7753,
      "step": 32
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 4.828811168670654,
      "learning_rate": 3.082191780821918e-07,
      "loss": 2.7311,
      "step": 33
    },
    {
      "epoch": 0.03492552645095018,
      "grad_norm": 4.6300435066223145,
      "learning_rate": 3.2534246575342466e-07,
      "loss": 2.7287,
      "step": 34
    },
    {
      "epoch": 0.035952747817154594,
      "grad_norm": 4.47259521484375,
      "learning_rate": 3.4246575342465755e-07,
      "loss": 2.7117,
      "step": 35
    },
    {
      "epoch": 0.03697996918335902,
      "grad_norm": 4.557999610900879,
      "learning_rate": 3.595890410958904e-07,
      "loss": 2.6291,
      "step": 36
    },
    {
      "epoch": 0.03800719054956343,
      "grad_norm": 4.3974761962890625,
      "learning_rate": 3.767123287671233e-07,
      "loss": 2.7421,
      "step": 37
    },
    {
      "epoch": 0.03903441191576785,
      "grad_norm": 3.6151702404022217,
      "learning_rate": 3.938356164383562e-07,
      "loss": 2.6744,
      "step": 38
    },
    {
      "epoch": 0.040061633281972264,
      "grad_norm": 3.165523052215576,
      "learning_rate": 4.1095890410958903e-07,
      "loss": 2.6694,
      "step": 39
    },
    {
      "epoch": 0.04108885464817668,
      "grad_norm": 3.2827563285827637,
      "learning_rate": 4.2808219178082193e-07,
      "loss": 2.7177,
      "step": 40
    },
    {
      "epoch": 0.04108885464817668,
      "eval_loss": 2.705791711807251,
      "eval_runtime": 36.995,
      "eval_samples_per_second": 27.031,
      "eval_steps_per_second": 1.135,
      "step": 40
    },
    {
      "epoch": 0.042116076014381096,
      "grad_norm": 3.241729736328125,
      "learning_rate": 4.452054794520548e-07,
      "loss": 2.6703,
      "step": 41
    },
    {
      "epoch": 0.04314329738058552,
      "grad_norm": 3.401049852371216,
      "learning_rate": 4.6232876712328767e-07,
      "loss": 2.6036,
      "step": 42
    },
    {
      "epoch": 0.044170518746789934,
      "grad_norm": 3.2498552799224854,
      "learning_rate": 4.794520547945206e-07,
      "loss": 2.6666,
      "step": 43
    },
    {
      "epoch": 0.04519774011299435,
      "grad_norm": 3.1376283168792725,
      "learning_rate": 4.965753424657534e-07,
      "loss": 2.6331,
      "step": 44
    },
    {
      "epoch": 0.046224961479198766,
      "grad_norm": 2.885286569595337,
      "learning_rate": 5.136986301369864e-07,
      "loss": 2.6609,
      "step": 45
    },
    {
      "epoch": 0.04725218284540318,
      "grad_norm": 2.636420249938965,
      "learning_rate": 5.308219178082192e-07,
      "loss": 2.6462,
      "step": 46
    },
    {
      "epoch": 0.048279404211607604,
      "grad_norm": 2.5609490871429443,
      "learning_rate": 5.47945205479452e-07,
      "loss": 2.6821,
      "step": 47
    },
    {
      "epoch": 0.04930662557781202,
      "grad_norm": 2.7683653831481934,
      "learning_rate": 5.65068493150685e-07,
      "loss": 2.61,
      "step": 48
    },
    {
      "epoch": 0.050333846944016436,
      "grad_norm": 3.3999135494232178,
      "learning_rate": 5.821917808219178e-07,
      "loss": 2.6166,
      "step": 49
    },
    {
      "epoch": 0.05136106831022085,
      "grad_norm": 2.922145128250122,
      "learning_rate": 5.993150684931507e-07,
      "loss": 2.5657,
      "step": 50
    },
    {
      "epoch": 0.05136106831022085,
      "eval_loss": 2.6353814601898193,
      "eval_runtime": 37.0591,
      "eval_samples_per_second": 26.984,
      "eval_steps_per_second": 1.133,
      "step": 50
    },
    {
      "epoch": 0.05238828967642527,
      "grad_norm": 2.5821900367736816,
      "learning_rate": 6.164383561643836e-07,
      "loss": 2.5512,
      "step": 51
    },
    {
      "epoch": 0.05341551104262968,
      "grad_norm": 2.2299063205718994,
      "learning_rate": 6.335616438356165e-07,
      "loss": 2.6082,
      "step": 52
    },
    {
      "epoch": 0.054442732408834106,
      "grad_norm": 2.0938310623168945,
      "learning_rate": 6.506849315068493e-07,
      "loss": 2.5301,
      "step": 53
    },
    {
      "epoch": 0.05546995377503852,
      "grad_norm": 2.186629295349121,
      "learning_rate": 6.678082191780823e-07,
      "loss": 2.5755,
      "step": 54
    },
    {
      "epoch": 0.05649717514124294,
      "grad_norm": 2.1747493743896484,
      "learning_rate": 6.849315068493151e-07,
      "loss": 2.5451,
      "step": 55
    },
    {
      "epoch": 0.05752439650744735,
      "grad_norm": 2.5470354557037354,
      "learning_rate": 7.020547945205481e-07,
      "loss": 2.5159,
      "step": 56
    },
    {
      "epoch": 0.05855161787365177,
      "grad_norm": 2.5056023597717285,
      "learning_rate": 7.191780821917808e-07,
      "loss": 2.5431,
      "step": 57
    },
    {
      "epoch": 0.05957883923985619,
      "grad_norm": 2.6059749126434326,
      "learning_rate": 7.363013698630137e-07,
      "loss": 2.4684,
      "step": 58
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 1.87150239944458,
      "learning_rate": 7.534246575342466e-07,
      "loss": 2.5269,
      "step": 59
    },
    {
      "epoch": 0.061633281972265024,
      "grad_norm": 1.8777480125427246,
      "learning_rate": 7.705479452054795e-07,
      "loss": 2.5253,
      "step": 60
    },
    {
      "epoch": 0.061633281972265024,
      "eval_loss": 2.5705313682556152,
      "eval_runtime": 37.0929,
      "eval_samples_per_second": 26.959,
      "eval_steps_per_second": 1.132,
      "step": 60
    },
    {
      "epoch": 0.06266050333846944,
      "grad_norm": 1.8500003814697266,
      "learning_rate": 7.876712328767124e-07,
      "loss": 2.4987,
      "step": 61
    },
    {
      "epoch": 0.06368772470467386,
      "grad_norm": 1.9473347663879395,
      "learning_rate": 8.047945205479453e-07,
      "loss": 2.4866,
      "step": 62
    },
    {
      "epoch": 0.06471494607087827,
      "grad_norm": 2.2350873947143555,
      "learning_rate": 8.219178082191781e-07,
      "loss": 2.5343,
      "step": 63
    },
    {
      "epoch": 0.0657421674370827,
      "grad_norm": 2.1791350841522217,
      "learning_rate": 8.39041095890411e-07,
      "loss": 2.5185,
      "step": 64
    },
    {
      "epoch": 0.0667693888032871,
      "grad_norm": 1.8400903940200806,
      "learning_rate": 8.561643835616439e-07,
      "loss": 2.3897,
      "step": 65
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 1.7193644046783447,
      "learning_rate": 8.732876712328768e-07,
      "loss": 2.485,
      "step": 66
    },
    {
      "epoch": 0.06882383153569595,
      "grad_norm": 1.8478909730911255,
      "learning_rate": 8.904109589041097e-07,
      "loss": 2.4404,
      "step": 67
    },
    {
      "epoch": 0.06985105290190036,
      "grad_norm": 1.8803719282150269,
      "learning_rate": 9.075342465753426e-07,
      "loss": 2.4933,
      "step": 68
    },
    {
      "epoch": 0.07087827426810478,
      "grad_norm": 1.6866114139556885,
      "learning_rate": 9.246575342465753e-07,
      "loss": 2.4441,
      "step": 69
    },
    {
      "epoch": 0.07190549563430919,
      "grad_norm": 1.807783842086792,
      "learning_rate": 9.417808219178083e-07,
      "loss": 2.5477,
      "step": 70
    },
    {
      "epoch": 0.07190549563430919,
      "eval_loss": 2.5140035152435303,
      "eval_runtime": 37.1384,
      "eval_samples_per_second": 26.926,
      "eval_steps_per_second": 1.131,
      "step": 70
    },
    {
      "epoch": 0.07293271700051361,
      "grad_norm": 1.7754000425338745,
      "learning_rate": 9.589041095890411e-07,
      "loss": 2.44,
      "step": 71
    },
    {
      "epoch": 0.07395993836671803,
      "grad_norm": 1.7819652557373047,
      "learning_rate": 9.76027397260274e-07,
      "loss": 2.402,
      "step": 72
    },
    {
      "epoch": 0.07498715973292244,
      "grad_norm": 1.6666278839111328,
      "learning_rate": 9.931506849315068e-07,
      "loss": 2.4511,
      "step": 73
    },
    {
      "epoch": 0.07601438109912687,
      "grad_norm": 2.0625369548797607,
      "learning_rate": 1.0102739726027399e-06,
      "loss": 2.424,
      "step": 74
    },
    {
      "epoch": 0.07704160246533127,
      "grad_norm": 1.9408000707626343,
      "learning_rate": 1.0273972602739727e-06,
      "loss": 2.4286,
      "step": 75
    },
    {
      "epoch": 0.0780688238315357,
      "grad_norm": 1.7670842409133911,
      "learning_rate": 1.0445205479452056e-06,
      "loss": 2.407,
      "step": 76
    },
    {
      "epoch": 0.07909604519774012,
      "grad_norm": 3.045717716217041,
      "learning_rate": 1.0616438356164384e-06,
      "loss": 2.425,
      "step": 77
    },
    {
      "epoch": 0.08012326656394453,
      "grad_norm": 1.9278619289398193,
      "learning_rate": 1.0787671232876712e-06,
      "loss": 2.4306,
      "step": 78
    },
    {
      "epoch": 0.08115048793014895,
      "grad_norm": 2.405146837234497,
      "learning_rate": 1.095890410958904e-06,
      "loss": 2.3499,
      "step": 79
    },
    {
      "epoch": 0.08217770929635336,
      "grad_norm": 2.1083860397338867,
      "learning_rate": 1.1130136986301371e-06,
      "loss": 2.4115,
      "step": 80
    },
    {
      "epoch": 0.08217770929635336,
      "eval_loss": 2.4501075744628906,
      "eval_runtime": 37.1247,
      "eval_samples_per_second": 26.936,
      "eval_steps_per_second": 1.131,
      "step": 80
    },
    {
      "epoch": 0.08320493066255778,
      "grad_norm": 2.181162118911743,
      "learning_rate": 1.13013698630137e-06,
      "loss": 2.3517,
      "step": 81
    },
    {
      "epoch": 0.08423215202876219,
      "grad_norm": 2.1833999156951904,
      "learning_rate": 1.1472602739726028e-06,
      "loss": 2.38,
      "step": 82
    },
    {
      "epoch": 0.08525937339496661,
      "grad_norm": 2.670384645462036,
      "learning_rate": 1.1643835616438357e-06,
      "loss": 2.3833,
      "step": 83
    },
    {
      "epoch": 0.08628659476117104,
      "grad_norm": 2.438676118850708,
      "learning_rate": 1.1815068493150685e-06,
      "loss": 2.3399,
      "step": 84
    },
    {
      "epoch": 0.08731381612737545,
      "grad_norm": 2.7584919929504395,
      "learning_rate": 1.1986301369863014e-06,
      "loss": 2.31,
      "step": 85
    },
    {
      "epoch": 0.08834103749357987,
      "grad_norm": 2.4129064083099365,
      "learning_rate": 1.2157534246575344e-06,
      "loss": 2.3758,
      "step": 86
    },
    {
      "epoch": 0.08936825885978428,
      "grad_norm": 2.366154193878174,
      "learning_rate": 1.2328767123287673e-06,
      "loss": 2.3154,
      "step": 87
    },
    {
      "epoch": 0.0903954802259887,
      "grad_norm": 2.4916300773620605,
      "learning_rate": 1.25e-06,
      "loss": 2.3022,
      "step": 88
    },
    {
      "epoch": 0.09142270159219312,
      "grad_norm": 2.4606640338897705,
      "learning_rate": 1.267123287671233e-06,
      "loss": 2.3103,
      "step": 89
    },
    {
      "epoch": 0.09244992295839753,
      "grad_norm": 2.4134910106658936,
      "learning_rate": 1.284246575342466e-06,
      "loss": 2.2672,
      "step": 90
    },
    {
      "epoch": 0.09244992295839753,
      "eval_loss": 2.3742051124572754,
      "eval_runtime": 37.1258,
      "eval_samples_per_second": 26.935,
      "eval_steps_per_second": 1.131,
      "step": 90
    },
    {
      "epoch": 0.09347714432460195,
      "grad_norm": 2.302776336669922,
      "learning_rate": 1.3013698630136986e-06,
      "loss": 2.2798,
      "step": 91
    },
    {
      "epoch": 0.09450436569080636,
      "grad_norm": 3.397819757461548,
      "learning_rate": 1.3184931506849317e-06,
      "loss": 2.2947,
      "step": 92
    },
    {
      "epoch": 0.09553158705701079,
      "grad_norm": 2.6030948162078857,
      "learning_rate": 1.3356164383561645e-06,
      "loss": 2.2734,
      "step": 93
    },
    {
      "epoch": 0.09655880842321521,
      "grad_norm": 2.9380528926849365,
      "learning_rate": 1.3527397260273976e-06,
      "loss": 2.2635,
      "step": 94
    },
    {
      "epoch": 0.09758602978941962,
      "grad_norm": 2.9196345806121826,
      "learning_rate": 1.3698630136986302e-06,
      "loss": 2.3161,
      "step": 95
    },
    {
      "epoch": 0.09861325115562404,
      "grad_norm": 2.2380659580230713,
      "learning_rate": 1.386986301369863e-06,
      "loss": 2.21,
      "step": 96
    },
    {
      "epoch": 0.09964047252182845,
      "grad_norm": 2.730910539627075,
      "learning_rate": 1.4041095890410961e-06,
      "loss": 2.2562,
      "step": 97
    },
    {
      "epoch": 0.10066769388803287,
      "grad_norm": 2.994748830795288,
      "learning_rate": 1.421232876712329e-06,
      "loss": 2.1597,
      "step": 98
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": 2.2228171825408936,
      "learning_rate": 1.4383561643835616e-06,
      "loss": 2.1835,
      "step": 99
    },
    {
      "epoch": 0.1027221366204417,
      "grad_norm": 2.715527296066284,
      "learning_rate": 1.4554794520547946e-06,
      "loss": 2.2074,
      "step": 100
    },
    {
      "epoch": 0.1027221366204417,
      "eval_loss": 2.3061234951019287,
      "eval_runtime": 37.1393,
      "eval_samples_per_second": 26.926,
      "eval_steps_per_second": 1.131,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 2919,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.11730940936192e+16,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}