{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3081664098613251,
  "eval_steps": 10,
  "global_step": 300,
  "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
    },
    {
      "epoch": 0.10374935798664613,
      "grad_norm": 2.7054452896118164,
      "learning_rate": 1.4726027397260275e-06,
      "loss": 2.2089,
      "step": 101
    },
    {
      "epoch": 0.10477657935285054,
      "grad_norm": 2.795694589614868,
      "learning_rate": 1.4897260273972605e-06,
      "loss": 2.1802,
      "step": 102
    },
    {
      "epoch": 0.10580380071905496,
      "grad_norm": 2.634822368621826,
      "learning_rate": 1.5068493150684932e-06,
      "loss": 2.1428,
      "step": 103
    },
    {
      "epoch": 0.10683102208525937,
      "grad_norm": 2.2418437004089355,
      "learning_rate": 1.5239726027397262e-06,
      "loss": 2.1706,
      "step": 104
    },
    {
      "epoch": 0.10785824345146379,
      "grad_norm": 2.471231698989868,
      "learning_rate": 1.541095890410959e-06,
      "loss": 2.2248,
      "step": 105
    },
    {
      "epoch": 0.10888546481766821,
      "grad_norm": 2.4154577255249023,
      "learning_rate": 1.5582191780821921e-06,
      "loss": 2.1873,
      "step": 106
    },
    {
      "epoch": 0.10991268618387262,
      "grad_norm": 2.2823996543884277,
      "learning_rate": 1.5753424657534248e-06,
      "loss": 2.2237,
      "step": 107
    },
    {
      "epoch": 0.11093990755007704,
      "grad_norm": 2.8695461750030518,
      "learning_rate": 1.5924657534246576e-06,
      "loss": 2.1966,
      "step": 108
    },
    {
      "epoch": 0.11196712891628145,
      "grad_norm": 3.319650650024414,
      "learning_rate": 1.6095890410958907e-06,
      "loss": 2.066,
      "step": 109
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 2.815196990966797,
      "learning_rate": 1.6267123287671235e-06,
      "loss": 2.1355,
      "step": 110
    },
    {
      "epoch": 0.11299435028248588,
      "eval_loss": 2.250187635421753,
      "eval_runtime": 37.1645,
      "eval_samples_per_second": 26.907,
      "eval_steps_per_second": 1.13,
      "step": 110
    },
    {
      "epoch": 0.1140215716486903,
      "grad_norm": 2.9195759296417236,
      "learning_rate": 1.6438356164383561e-06,
      "loss": 2.0713,
      "step": 111
    },
    {
      "epoch": 0.1150487930148947,
      "grad_norm": 2.5600695610046387,
      "learning_rate": 1.6609589041095892e-06,
      "loss": 2.1573,
      "step": 112
    },
    {
      "epoch": 0.11607601438109913,
      "grad_norm": 2.7566795349121094,
      "learning_rate": 1.678082191780822e-06,
      "loss": 2.0909,
      "step": 113
    },
    {
      "epoch": 0.11710323574730354,
      "grad_norm": 2.5593106746673584,
      "learning_rate": 1.695205479452055e-06,
      "loss": 2.144,
      "step": 114
    },
    {
      "epoch": 0.11813045711350796,
      "grad_norm": 2.594931125640869,
      "learning_rate": 1.7123287671232877e-06,
      "loss": 2.0606,
      "step": 115
    },
    {
      "epoch": 0.11915767847971238,
      "grad_norm": 2.769916534423828,
      "learning_rate": 1.7294520547945206e-06,
      "loss": 2.1737,
      "step": 116
    },
    {
      "epoch": 0.12018489984591679,
      "grad_norm": 2.523179054260254,
      "learning_rate": 1.7465753424657536e-06,
      "loss": 2.1247,
      "step": 117
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.8153676986694336,
      "learning_rate": 1.7636986301369865e-06,
      "loss": 2.1257,
      "step": 118
    },
    {
      "epoch": 0.12223934257832562,
      "grad_norm": 2.5389721393585205,
      "learning_rate": 1.7808219178082193e-06,
      "loss": 2.1049,
      "step": 119
    },
    {
      "epoch": 0.12326656394453005,
      "grad_norm": 2.9753856658935547,
      "learning_rate": 1.7979452054794521e-06,
      "loss": 2.1871,
      "step": 120
    },
    {
      "epoch": 0.12326656394453005,
      "eval_loss": 2.2089297771453857,
      "eval_runtime": 37.897,
      "eval_samples_per_second": 26.387,
      "eval_steps_per_second": 1.108,
      "step": 120
    },
    {
      "epoch": 0.12429378531073447,
      "grad_norm": 2.737180471420288,
      "learning_rate": 1.8150684931506852e-06,
      "loss": 2.1166,
      "step": 121
    },
    {
      "epoch": 0.12532100667693888,
      "grad_norm": 2.783801794052124,
      "learning_rate": 1.832191780821918e-06,
      "loss": 2.0932,
      "step": 122
    },
    {
      "epoch": 0.1263482280431433,
      "grad_norm": 2.9615402221679688,
      "learning_rate": 1.8493150684931507e-06,
      "loss": 2.0327,
      "step": 123
    },
    {
      "epoch": 0.12737544940934772,
      "grad_norm": 3.053622007369995,
      "learning_rate": 1.8664383561643837e-06,
      "loss": 2.0665,
      "step": 124
    },
    {
      "epoch": 0.12840267077555212,
      "grad_norm": 3.265355348587036,
      "learning_rate": 1.8835616438356166e-06,
      "loss": 2.0243,
      "step": 125
    },
    {
      "epoch": 0.12942989214175654,
      "grad_norm": 2.4237143993377686,
      "learning_rate": 1.9006849315068496e-06,
      "loss": 2.0902,
      "step": 126
    },
    {
      "epoch": 0.13045711350796096,
      "grad_norm": 2.926950693130493,
      "learning_rate": 1.9178082191780823e-06,
      "loss": 2.0057,
      "step": 127
    },
    {
      "epoch": 0.1314843348741654,
      "grad_norm": 2.5317165851593018,
      "learning_rate": 1.9349315068493153e-06,
      "loss": 2.0719,
      "step": 128
    },
    {
      "epoch": 0.1325115562403698,
      "grad_norm": 2.4999701976776123,
      "learning_rate": 1.952054794520548e-06,
      "loss": 2.0969,
      "step": 129
    },
    {
      "epoch": 0.1335387776065742,
      "grad_norm": 2.7063920497894287,
      "learning_rate": 1.969178082191781e-06,
      "loss": 2.0902,
      "step": 130
    },
    {
      "epoch": 0.1335387776065742,
      "eval_loss": 2.175224542617798,
      "eval_runtime": 37.4519,
      "eval_samples_per_second": 26.701,
      "eval_steps_per_second": 1.121,
      "step": 130
    },
    {
      "epoch": 0.13456599897277863,
      "grad_norm": 2.650860071182251,
      "learning_rate": 1.9863013698630136e-06,
      "loss": 2.0191,
      "step": 131
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 2.79182505607605,
      "learning_rate": 2.0034246575342467e-06,
      "loss": 2.0856,
      "step": 132
    },
    {
      "epoch": 0.13662044170518747,
      "grad_norm": 2.453162431716919,
      "learning_rate": 2.0205479452054797e-06,
      "loss": 2.0679,
      "step": 133
    },
    {
      "epoch": 0.1376476630713919,
      "grad_norm": 2.9630799293518066,
      "learning_rate": 2.037671232876713e-06,
      "loss": 2.0038,
      "step": 134
    },
    {
      "epoch": 0.1386748844375963,
      "grad_norm": 3.0807266235351562,
      "learning_rate": 2.0547945205479454e-06,
      "loss": 2.0367,
      "step": 135
    },
    {
      "epoch": 0.1397021058038007,
      "grad_norm": 2.9712910652160645,
      "learning_rate": 2.071917808219178e-06,
      "loss": 2.0571,
      "step": 136
    },
    {
      "epoch": 0.14072932717000514,
      "grad_norm": 3.0804853439331055,
      "learning_rate": 2.089041095890411e-06,
      "loss": 1.9725,
      "step": 137
    },
    {
      "epoch": 0.14175654853620956,
      "grad_norm": 2.659608840942383,
      "learning_rate": 2.106164383561644e-06,
      "loss": 2.0572,
      "step": 138
    },
    {
      "epoch": 0.14278376990241398,
      "grad_norm": 2.8093109130859375,
      "learning_rate": 2.123287671232877e-06,
      "loss": 2.0178,
      "step": 139
    },
    {
      "epoch": 0.14381099126861838,
      "grad_norm": 2.8163881301879883,
      "learning_rate": 2.14041095890411e-06,
      "loss": 2.0085,
      "step": 140
    },
    {
      "epoch": 0.14381099126861838,
      "eval_loss": 2.147092342376709,
      "eval_runtime": 37.2453,
      "eval_samples_per_second": 26.849,
      "eval_steps_per_second": 1.128,
      "step": 140
    },
    {
      "epoch": 0.1448382126348228,
      "grad_norm": 3.795241594314575,
      "learning_rate": 2.1575342465753425e-06,
      "loss": 2.0149,
      "step": 141
    },
    {
      "epoch": 0.14586543400102722,
      "grad_norm": 3.3287174701690674,
      "learning_rate": 2.1746575342465755e-06,
      "loss": 1.9658,
      "step": 142
    },
    {
      "epoch": 0.14689265536723164,
      "grad_norm": 2.803213596343994,
      "learning_rate": 2.191780821917808e-06,
      "loss": 2.0983,
      "step": 143
    },
    {
      "epoch": 0.14791987673343607,
      "grad_norm": 3.2640199661254883,
      "learning_rate": 2.2089041095890412e-06,
      "loss": 1.9865,
      "step": 144
    },
    {
      "epoch": 0.14894709809964046,
      "grad_norm": 2.95979380607605,
      "learning_rate": 2.2260273972602743e-06,
      "loss": 1.9669,
      "step": 145
    },
    {
      "epoch": 0.14997431946584489,
      "grad_norm": 3.737175226211548,
      "learning_rate": 2.243150684931507e-06,
      "loss": 1.9691,
      "step": 146
    },
    {
      "epoch": 0.1510015408320493,
      "grad_norm": 2.7248430252075195,
      "learning_rate": 2.26027397260274e-06,
      "loss": 1.9764,
      "step": 147
    },
    {
      "epoch": 0.15202876219825373,
      "grad_norm": 2.929856061935425,
      "learning_rate": 2.2773972602739726e-06,
      "loss": 1.9967,
      "step": 148
    },
    {
      "epoch": 0.15305598356445815,
      "grad_norm": 2.8998641967773438,
      "learning_rate": 2.2945205479452057e-06,
      "loss": 2.0842,
      "step": 149
    },
    {
      "epoch": 0.15408320493066255,
      "grad_norm": 2.9672694206237793,
      "learning_rate": 2.3116438356164387e-06,
      "loss": 1.9915,
      "step": 150
    },
    {
      "epoch": 0.15408320493066255,
      "eval_loss": 2.122715473175049,
      "eval_runtime": 37.1938,
      "eval_samples_per_second": 26.886,
      "eval_steps_per_second": 1.129,
      "step": 150
    },
    {
      "epoch": 0.15511042629686697,
      "grad_norm": 2.8529887199401855,
      "learning_rate": 2.3287671232876713e-06,
      "loss": 1.9022,
      "step": 151
    },
    {
      "epoch": 0.1561376476630714,
      "grad_norm": 2.914121389389038,
      "learning_rate": 2.3458904109589044e-06,
      "loss": 1.956,
      "step": 152
    },
    {
      "epoch": 0.15716486902927582,
      "grad_norm": 3.6286494731903076,
      "learning_rate": 2.363013698630137e-06,
      "loss": 2.0118,
      "step": 153
    },
    {
      "epoch": 0.15819209039548024,
      "grad_norm": 2.789562702178955,
      "learning_rate": 2.38013698630137e-06,
      "loss": 1.9935,
      "step": 154
    },
    {
      "epoch": 0.15921931176168463,
      "grad_norm": 3.367119550704956,
      "learning_rate": 2.3972602739726027e-06,
      "loss": 1.9519,
      "step": 155
    },
    {
      "epoch": 0.16024653312788906,
      "grad_norm": 2.9345803260803223,
      "learning_rate": 2.4143835616438358e-06,
      "loss": 1.9017,
      "step": 156
    },
    {
      "epoch": 0.16127375449409348,
      "grad_norm": 2.8674590587615967,
      "learning_rate": 2.431506849315069e-06,
      "loss": 1.9731,
      "step": 157
    },
    {
      "epoch": 0.1623009758602979,
      "grad_norm": 3.144766092300415,
      "learning_rate": 2.4486301369863015e-06,
      "loss": 1.9811,
      "step": 158
    },
    {
      "epoch": 0.1633281972265023,
      "grad_norm": 3.845395088195801,
      "learning_rate": 2.4657534246575345e-06,
      "loss": 1.9523,
      "step": 159
    },
    {
      "epoch": 0.16435541859270672,
      "grad_norm": 2.776700973510742,
      "learning_rate": 2.482876712328767e-06,
      "loss": 1.9687,
      "step": 160
    },
    {
      "epoch": 0.16435541859270672,
      "eval_loss": 2.0929579734802246,
      "eval_runtime": 37.1917,
      "eval_samples_per_second": 26.888,
      "eval_steps_per_second": 1.129,
      "step": 160
    },
    {
      "epoch": 0.16538263995891114,
      "grad_norm": 3.4260904788970947,
      "learning_rate": 2.5e-06,
      "loss": 1.9665,
      "step": 161
    },
    {
      "epoch": 0.16640986132511557,
      "grad_norm": 3.1217620372772217,
      "learning_rate": 2.5171232876712333e-06,
      "loss": 1.9361,
      "step": 162
    },
    {
      "epoch": 0.16743708269132,
      "grad_norm": 3.342068910598755,
      "learning_rate": 2.534246575342466e-06,
      "loss": 1.9084,
      "step": 163
    },
    {
      "epoch": 0.16846430405752438,
      "grad_norm": 3.6485838890075684,
      "learning_rate": 2.551369863013699e-06,
      "loss": 1.9542,
      "step": 164
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 3.1247780323028564,
      "learning_rate": 2.568493150684932e-06,
      "loss": 1.9717,
      "step": 165
    },
    {
      "epoch": 0.17051874678993323,
      "grad_norm": 2.9856860637664795,
      "learning_rate": 2.585616438356164e-06,
      "loss": 1.9574,
      "step": 166
    },
    {
      "epoch": 0.17154596815613765,
      "grad_norm": 3.337902069091797,
      "learning_rate": 2.6027397260273973e-06,
      "loss": 1.8884,
      "step": 167
    },
    {
      "epoch": 0.17257318952234207,
      "grad_norm": 2.844534158706665,
      "learning_rate": 2.6198630136986303e-06,
      "loss": 1.9545,
      "step": 168
    },
    {
      "epoch": 0.17360041088854647,
      "grad_norm": 3.75907564163208,
      "learning_rate": 2.6369863013698634e-06,
      "loss": 1.9907,
      "step": 169
    },
    {
      "epoch": 0.1746276322547509,
      "grad_norm": 2.9321961402893066,
      "learning_rate": 2.654109589041096e-06,
      "loss": 1.9663,
      "step": 170
    },
    {
      "epoch": 0.1746276322547509,
      "eval_loss": 2.0753843784332275,
      "eval_runtime": 37.2389,
      "eval_samples_per_second": 26.854,
      "eval_steps_per_second": 1.128,
      "step": 170
    },
    {
      "epoch": 0.17565485362095531,
      "grad_norm": 2.952523946762085,
      "learning_rate": 2.671232876712329e-06,
      "loss": 1.9065,
      "step": 171
    },
    {
      "epoch": 0.17668207498715974,
      "grad_norm": 2.952463150024414,
      "learning_rate": 2.688356164383562e-06,
      "loss": 1.8994,
      "step": 172
    },
    {
      "epoch": 0.17770929635336416,
      "grad_norm": 3.1352880001068115,
      "learning_rate": 2.705479452054795e-06,
      "loss": 1.8902,
      "step": 173
    },
    {
      "epoch": 0.17873651771956856,
      "grad_norm": 3.5727322101593018,
      "learning_rate": 2.7226027397260274e-06,
      "loss": 1.8454,
      "step": 174
    },
    {
      "epoch": 0.17976373908577298,
      "grad_norm": 3.0562493801116943,
      "learning_rate": 2.7397260273972604e-06,
      "loss": 1.984,
      "step": 175
    },
    {
      "epoch": 0.1807909604519774,
      "grad_norm": 3.367924690246582,
      "learning_rate": 2.7568493150684935e-06,
      "loss": 1.9398,
      "step": 176
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.1982340812683105,
      "learning_rate": 2.773972602739726e-06,
      "loss": 1.8566,
      "step": 177
    },
    {
      "epoch": 0.18284540318438625,
      "grad_norm": 3.8962080478668213,
      "learning_rate": 2.791095890410959e-06,
      "loss": 1.9459,
      "step": 178
    },
    {
      "epoch": 0.18387262455059064,
      "grad_norm": 3.3503036499023438,
      "learning_rate": 2.8082191780821922e-06,
      "loss": 1.8348,
      "step": 179
    },
    {
      "epoch": 0.18489984591679506,
      "grad_norm": 3.276139497756958,
      "learning_rate": 2.8253424657534253e-06,
      "loss": 1.9849,
      "step": 180
    },
    {
      "epoch": 0.18489984591679506,
      "eval_loss": 2.0605413913726807,
      "eval_runtime": 37.2276,
      "eval_samples_per_second": 26.862,
      "eval_steps_per_second": 1.128,
      "step": 180
    },
    {
      "epoch": 0.1859270672829995,
      "grad_norm": 3.3787975311279297,
      "learning_rate": 2.842465753424658e-06,
      "loss": 1.9517,
      "step": 181
    },
    {
      "epoch": 0.1869542886492039,
      "grad_norm": 3.054290294647217,
      "learning_rate": 2.8595890410958905e-06,
      "loss": 1.9572,
      "step": 182
    },
    {
      "epoch": 0.18798151001540833,
      "grad_norm": 3.0737054347991943,
      "learning_rate": 2.876712328767123e-06,
      "loss": 1.9674,
      "step": 183
    },
    {
      "epoch": 0.18900873138161273,
      "grad_norm": 3.2833855152130127,
      "learning_rate": 2.8938356164383562e-06,
      "loss": 1.8185,
      "step": 184
    },
    {
      "epoch": 0.19003595274781715,
      "grad_norm": 2.70452880859375,
      "learning_rate": 2.9109589041095893e-06,
      "loss": 1.8552,
      "step": 185
    },
    {
      "epoch": 0.19106317411402157,
      "grad_norm": 3.2723655700683594,
      "learning_rate": 2.9280821917808223e-06,
      "loss": 1.8433,
      "step": 186
    },
    {
      "epoch": 0.192090395480226,
      "grad_norm": 2.844536066055298,
      "learning_rate": 2.945205479452055e-06,
      "loss": 1.8488,
      "step": 187
    },
    {
      "epoch": 0.19311761684643042,
      "grad_norm": 2.944545269012451,
      "learning_rate": 2.962328767123288e-06,
      "loss": 1.9131,
      "step": 188
    },
    {
      "epoch": 0.1941448382126348,
      "grad_norm": 2.812204122543335,
      "learning_rate": 2.979452054794521e-06,
      "loss": 1.8977,
      "step": 189
    },
    {
      "epoch": 0.19517205957883924,
      "grad_norm": 2.8999950885772705,
      "learning_rate": 2.9965753424657533e-06,
      "loss": 1.8477,
      "step": 190
    },
    {
      "epoch": 0.19517205957883924,
      "eval_loss": 2.051161527633667,
      "eval_runtime": 37.2363,
      "eval_samples_per_second": 26.856,
      "eval_steps_per_second": 1.128,
      "step": 190
    },
    {
      "epoch": 0.19619928094504366,
      "grad_norm": 2.7814741134643555,
      "learning_rate": 3.0136986301369864e-06,
      "loss": 1.8989,
      "step": 191
    },
    {
      "epoch": 0.19722650231124808,
      "grad_norm": 2.93346905708313,
      "learning_rate": 3.0308219178082194e-06,
      "loss": 1.8748,
      "step": 192
    },
    {
      "epoch": 0.1982537236774525,
      "grad_norm": 3.00400447845459,
      "learning_rate": 3.0479452054794525e-06,
      "loss": 1.838,
      "step": 193
    },
    {
      "epoch": 0.1992809450436569,
      "grad_norm": 2.949695110321045,
      "learning_rate": 3.065068493150685e-06,
      "loss": 1.8817,
      "step": 194
    },
    {
      "epoch": 0.20030816640986132,
      "grad_norm": 2.8858301639556885,
      "learning_rate": 3.082191780821918e-06,
      "loss": 1.8333,
      "step": 195
    },
    {
      "epoch": 0.20133538777606574,
      "grad_norm": 3.123706102371216,
      "learning_rate": 3.099315068493151e-06,
      "loss": 1.8533,
      "step": 196
    },
    {
      "epoch": 0.20236260914227017,
      "grad_norm": 3.0130505561828613,
      "learning_rate": 3.1164383561643843e-06,
      "loss": 1.842,
      "step": 197
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": 2.8823280334472656,
      "learning_rate": 3.1335616438356165e-06,
      "loss": 1.8025,
      "step": 198
    },
    {
      "epoch": 0.20441705187467898,
      "grad_norm": 2.920884132385254,
      "learning_rate": 3.1506849315068495e-06,
      "loss": 1.9488,
      "step": 199
    },
    {
      "epoch": 0.2054442732408834,
      "grad_norm": 2.9152207374572754,
      "learning_rate": 3.167808219178082e-06,
      "loss": 1.8163,
      "step": 200
    },
    {
      "epoch": 0.2054442732408834,
      "eval_loss": 2.033583641052246,
      "eval_runtime": 37.127,
      "eval_samples_per_second": 26.935,
      "eval_steps_per_second": 1.131,
      "step": 200
    },
    {
      "epoch": 0.20647149460708783,
      "grad_norm": 2.904230833053589,
      "learning_rate": 3.184931506849315e-06,
      "loss": 1.8207,
      "step": 201
    },
    {
      "epoch": 0.20749871597329225,
      "grad_norm": 3.128448486328125,
      "learning_rate": 3.2020547945205483e-06,
      "loss": 1.8051,
      "step": 202
    },
    {
      "epoch": 0.20852593733949668,
      "grad_norm": 3.0049452781677246,
      "learning_rate": 3.2191780821917813e-06,
      "loss": 1.7823,
      "step": 203
    },
    {
      "epoch": 0.20955315870570107,
      "grad_norm": 2.7612497806549072,
      "learning_rate": 3.236301369863014e-06,
      "loss": 1.7703,
      "step": 204
    },
    {
      "epoch": 0.2105803800719055,
      "grad_norm": 2.9178879261016846,
      "learning_rate": 3.253424657534247e-06,
      "loss": 1.7427,
      "step": 205
    },
    {
      "epoch": 0.21160760143810992,
      "grad_norm": 2.836967945098877,
      "learning_rate": 3.2705479452054796e-06,
      "loss": 1.8347,
      "step": 206
    },
    {
      "epoch": 0.21263482280431434,
      "grad_norm": 2.8437204360961914,
      "learning_rate": 3.2876712328767123e-06,
      "loss": 1.8147,
      "step": 207
    },
    {
      "epoch": 0.21366204417051873,
      "grad_norm": 3.0728225708007812,
      "learning_rate": 3.3047945205479453e-06,
      "loss": 1.7823,
      "step": 208
    },
    {
      "epoch": 0.21468926553672316,
      "grad_norm": 3.357631206512451,
      "learning_rate": 3.3219178082191784e-06,
      "loss": 1.8013,
      "step": 209
    },
    {
      "epoch": 0.21571648690292758,
      "grad_norm": 2.7996842861175537,
      "learning_rate": 3.3390410958904114e-06,
      "loss": 1.8279,
      "step": 210
    },
    {
      "epoch": 0.21571648690292758,
      "eval_loss": 2.024500846862793,
      "eval_runtime": 37.0122,
      "eval_samples_per_second": 27.018,
      "eval_steps_per_second": 1.135,
      "step": 210
    },
    {
      "epoch": 0.216743708269132,
      "grad_norm": 3.3635380268096924,
      "learning_rate": 3.356164383561644e-06,
      "loss": 1.8509,
      "step": 211
    },
    {
      "epoch": 0.21777092963533642,
      "grad_norm": 2.703932523727417,
      "learning_rate": 3.373287671232877e-06,
      "loss": 1.8984,
      "step": 212
    },
    {
      "epoch": 0.21879815100154082,
      "grad_norm": 2.9341695308685303,
      "learning_rate": 3.39041095890411e-06,
      "loss": 1.8381,
      "step": 213
    },
    {
      "epoch": 0.21982537236774524,
      "grad_norm": 3.072448253631592,
      "learning_rate": 3.4075342465753424e-06,
      "loss": 1.8779,
      "step": 214
    },
    {
      "epoch": 0.22085259373394966,
      "grad_norm": 2.850555419921875,
      "learning_rate": 3.4246575342465754e-06,
      "loss": 1.7656,
      "step": 215
    },
    {
      "epoch": 0.2218798151001541,
      "grad_norm": 3.0218873023986816,
      "learning_rate": 3.4417808219178085e-06,
      "loss": 1.829,
      "step": 216
    },
    {
      "epoch": 0.2229070364663585,
      "grad_norm": 2.8475091457366943,
      "learning_rate": 3.458904109589041e-06,
      "loss": 1.8121,
      "step": 217
    },
    {
      "epoch": 0.2239342578325629,
      "grad_norm": 2.8760111331939697,
      "learning_rate": 3.476027397260274e-06,
      "loss": 1.8281,
      "step": 218
    },
    {
      "epoch": 0.22496147919876733,
      "grad_norm": 2.976670265197754,
      "learning_rate": 3.4931506849315072e-06,
      "loss": 1.8274,
      "step": 219
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 2.912505865097046,
      "learning_rate": 3.5102739726027403e-06,
      "loss": 1.8316,
      "step": 220
    },
    {
      "epoch": 0.22598870056497175,
      "eval_loss": 2.0203635692596436,
      "eval_runtime": 37.0433,
      "eval_samples_per_second": 26.995,
      "eval_steps_per_second": 1.134,
      "step": 220
    },
    {
      "epoch": 0.22701592193117617,
      "grad_norm": 3.1133334636688232,
      "learning_rate": 3.527397260273973e-06,
      "loss": 1.8277,
      "step": 221
    },
    {
      "epoch": 0.2280431432973806,
      "grad_norm": 3.289062261581421,
      "learning_rate": 3.5445205479452056e-06,
      "loss": 1.7893,
      "step": 222
    },
    {
      "epoch": 0.229070364663585,
      "grad_norm": 2.814558267593384,
      "learning_rate": 3.5616438356164386e-06,
      "loss": 1.8095,
      "step": 223
    },
    {
      "epoch": 0.2300975860297894,
      "grad_norm": 3.48117733001709,
      "learning_rate": 3.5787671232876712e-06,
      "loss": 1.8701,
      "step": 224
    },
    {
      "epoch": 0.23112480739599384,
      "grad_norm": 2.922144651412964,
      "learning_rate": 3.5958904109589043e-06,
      "loss": 1.8479,
      "step": 225
    },
    {
      "epoch": 0.23215202876219826,
      "grad_norm": 3.552428960800171,
      "learning_rate": 3.6130136986301373e-06,
      "loss": 1.7822,
      "step": 226
    },
    {
      "epoch": 0.23317925012840268,
      "grad_norm": 3.058274269104004,
      "learning_rate": 3.6301369863013704e-06,
      "loss": 1.8228,
      "step": 227
    },
    {
      "epoch": 0.23420647149460708,
      "grad_norm": 3.365823268890381,
      "learning_rate": 3.647260273972603e-06,
      "loss": 1.8415,
      "step": 228
    },
    {
      "epoch": 0.2352336928608115,
      "grad_norm": 2.87333607673645,
      "learning_rate": 3.664383561643836e-06,
      "loss": 1.8474,
      "step": 229
    },
    {
      "epoch": 0.23626091422701592,
      "grad_norm": 3.185807228088379,
      "learning_rate": 3.6815068493150687e-06,
      "loss": 1.7854,
      "step": 230
    },
    {
      "epoch": 0.23626091422701592,
      "eval_loss": 2.0132367610931396,
      "eval_runtime": 37.3246,
      "eval_samples_per_second": 26.792,
      "eval_steps_per_second": 1.125,
      "step": 230
    },
    {
      "epoch": 0.23728813559322035,
      "grad_norm": 3.02864933013916,
      "learning_rate": 3.6986301369863014e-06,
      "loss": 1.8081,
      "step": 231
    },
    {
      "epoch": 0.23831535695942477,
      "grad_norm": 2.892451286315918,
      "learning_rate": 3.7157534246575344e-06,
      "loss": 1.7619,
      "step": 232
    },
    {
      "epoch": 0.23934257832562916,
      "grad_norm": 3.24947452545166,
      "learning_rate": 3.7328767123287675e-06,
      "loss": 1.8729,
      "step": 233
    },
    {
      "epoch": 0.24036979969183359,
      "grad_norm": 3.13212513923645,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 1.7849,
      "step": 234
    },
    {
      "epoch": 0.241397021058038,
      "grad_norm": 3.004814863204956,
      "learning_rate": 3.767123287671233e-06,
      "loss": 1.8217,
      "step": 235
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 2.845555067062378,
      "learning_rate": 3.784246575342466e-06,
      "loss": 1.8438,
      "step": 236
    },
    {
      "epoch": 0.24345146379044685,
      "grad_norm": 3.1796751022338867,
      "learning_rate": 3.8013698630136993e-06,
      "loss": 1.7807,
      "step": 237
    },
    {
      "epoch": 0.24447868515665125,
      "grad_norm": 2.7663002014160156,
      "learning_rate": 3.818493150684932e-06,
      "loss": 1.7981,
      "step": 238
    },
    {
      "epoch": 0.24550590652285567,
      "grad_norm": 3.0547749996185303,
      "learning_rate": 3.8356164383561645e-06,
      "loss": 1.7543,
      "step": 239
    },
    {
      "epoch": 0.2465331278890601,
      "grad_norm": 2.6994550228118896,
      "learning_rate": 3.852739726027397e-06,
      "loss": 1.8612,
      "step": 240
    },
    {
      "epoch": 0.2465331278890601,
      "eval_loss": 2.0076475143432617,
      "eval_runtime": 37.3223,
      "eval_samples_per_second": 26.794,
      "eval_steps_per_second": 1.125,
      "step": 240
    },
    {
      "epoch": 0.24756034925526452,
      "grad_norm": 2.769717216491699,
      "learning_rate": 3.869863013698631e-06,
      "loss": 1.8352,
      "step": 241
    },
    {
      "epoch": 0.24858757062146894,
      "grad_norm": 2.7526769638061523,
      "learning_rate": 3.886986301369863e-06,
      "loss": 1.7775,
      "step": 242
    },
    {
      "epoch": 0.24961479198767333,
      "grad_norm": 3.0213067531585693,
      "learning_rate": 3.904109589041096e-06,
      "loss": 1.7901,
      "step": 243
    },
    {
      "epoch": 0.25064201335387776,
      "grad_norm": 2.8562498092651367,
      "learning_rate": 3.921232876712329e-06,
      "loss": 1.7483,
      "step": 244
    },
    {
      "epoch": 0.2516692347200822,
      "grad_norm": 2.812774896621704,
      "learning_rate": 3.938356164383562e-06,
      "loss": 1.7643,
      "step": 245
    },
    {
      "epoch": 0.2526964560862866,
      "grad_norm": 3.2509777545928955,
      "learning_rate": 3.9554794520547955e-06,
      "loss": 1.729,
      "step": 246
    },
    {
      "epoch": 0.253723677452491,
      "grad_norm": 3.6394171714782715,
      "learning_rate": 3.972602739726027e-06,
      "loss": 1.8253,
      "step": 247
    },
    {
      "epoch": 0.25475089881869545,
      "grad_norm": 3.1234781742095947,
      "learning_rate": 3.989726027397261e-06,
      "loss": 1.7457,
      "step": 248
    },
    {
      "epoch": 0.25577812018489987,
      "grad_norm": 2.8587522506713867,
      "learning_rate": 4.006849315068493e-06,
      "loss": 1.804,
      "step": 249
    },
    {
      "epoch": 0.25680534155110424,
      "grad_norm": 2.9718286991119385,
      "learning_rate": 4.023972602739726e-06,
      "loss": 1.8051,
      "step": 250
    },
    {
      "epoch": 0.25680534155110424,
      "eval_loss": 2.0024874210357666,
      "eval_runtime": 37.2884,
      "eval_samples_per_second": 26.818,
      "eval_steps_per_second": 1.126,
      "step": 250
    },
    {
      "epoch": 0.25783256291730866,
      "grad_norm": 3.007124423980713,
      "learning_rate": 4.0410958904109595e-06,
      "loss": 1.7946,
      "step": 251
    },
    {
      "epoch": 0.2588597842835131,
      "grad_norm": 3.1715426445007324,
      "learning_rate": 4.058219178082192e-06,
      "loss": 1.7811,
      "step": 252
    },
    {
      "epoch": 0.2598870056497175,
      "grad_norm": 2.814269542694092,
      "learning_rate": 4.075342465753426e-06,
      "loss": 1.8024,
      "step": 253
    },
    {
      "epoch": 0.26091422701592193,
      "grad_norm": 2.841212034225464,
      "learning_rate": 4.092465753424658e-06,
      "loss": 1.7713,
      "step": 254
    },
    {
      "epoch": 0.26194144838212635,
      "grad_norm": 3.0878522396087646,
      "learning_rate": 4.109589041095891e-06,
      "loss": 1.7579,
      "step": 255
    },
    {
      "epoch": 0.2629686697483308,
      "grad_norm": 2.946709394454956,
      "learning_rate": 4.1267123287671235e-06,
      "loss": 1.823,
      "step": 256
    },
    {
      "epoch": 0.2639958911145352,
      "grad_norm": 2.8136606216430664,
      "learning_rate": 4.143835616438356e-06,
      "loss": 1.7731,
      "step": 257
    },
    {
      "epoch": 0.2650231124807396,
      "grad_norm": 2.745762825012207,
      "learning_rate": 4.16095890410959e-06,
      "loss": 1.8445,
      "step": 258
    },
    {
      "epoch": 0.26605033384694404,
      "grad_norm": 3.0986413955688477,
      "learning_rate": 4.178082191780822e-06,
      "loss": 1.8231,
      "step": 259
    },
    {
      "epoch": 0.2670775552131484,
      "grad_norm": 2.6990394592285156,
      "learning_rate": 4.195205479452055e-06,
      "loss": 1.7635,
      "step": 260
    },
    {
      "epoch": 0.2670775552131484,
      "eval_loss": 1.9839800596237183,
      "eval_runtime": 37.1612,
      "eval_samples_per_second": 26.91,
      "eval_steps_per_second": 1.13,
      "step": 260
    },
    {
      "epoch": 0.26810477657935283,
      "grad_norm": 3.281421184539795,
      "learning_rate": 4.212328767123288e-06,
      "loss": 1.7587,
      "step": 261
    },
    {
      "epoch": 0.26913199794555726,
      "grad_norm": 3.1233623027801514,
      "learning_rate": 4.229452054794521e-06,
      "loss": 1.7673,
      "step": 262
    },
    {
      "epoch": 0.2701592193117617,
      "grad_norm": 3.3131625652313232,
      "learning_rate": 4.246575342465754e-06,
      "loss": 1.7755,
      "step": 263
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 3.3002350330352783,
      "learning_rate": 4.263698630136986e-06,
      "loss": 1.7575,
      "step": 264
    },
    {
      "epoch": 0.2722136620441705,
      "grad_norm": 2.965397357940674,
      "learning_rate": 4.28082191780822e-06,
      "loss": 1.7162,
      "step": 265
    },
    {
      "epoch": 0.27324088341037495,
      "grad_norm": 2.9904608726501465,
      "learning_rate": 4.297945205479452e-06,
      "loss": 1.8794,
      "step": 266
    },
    {
      "epoch": 0.27426810477657937,
      "grad_norm": 2.707996129989624,
      "learning_rate": 4.315068493150685e-06,
      "loss": 1.7646,
      "step": 267
    },
    {
      "epoch": 0.2752953261427838,
      "grad_norm": 2.8878190517425537,
      "learning_rate": 4.3321917808219185e-06,
      "loss": 1.7559,
      "step": 268
    },
    {
      "epoch": 0.2763225475089882,
      "grad_norm": 3.1676602363586426,
      "learning_rate": 4.349315068493151e-06,
      "loss": 1.7806,
      "step": 269
    },
    {
      "epoch": 0.2773497688751926,
      "grad_norm": 2.9179935455322266,
      "learning_rate": 4.3664383561643846e-06,
      "loss": 1.7493,
      "step": 270
    },
    {
      "epoch": 0.2773497688751926,
      "eval_loss": 1.9736579656600952,
      "eval_runtime": 37.0983,
      "eval_samples_per_second": 26.955,
      "eval_steps_per_second": 1.132,
      "step": 270
    },
    {
      "epoch": 0.278376990241397,
      "grad_norm": 3.0081794261932373,
      "learning_rate": 4.383561643835616e-06,
      "loss": 1.7405,
      "step": 271
    },
    {
      "epoch": 0.2794042116076014,
      "grad_norm": 3.240462064743042,
      "learning_rate": 4.40068493150685e-06,
      "loss": 1.8326,
      "step": 272
    },
    {
      "epoch": 0.28043143297380585,
      "grad_norm": 3.324059247970581,
      "learning_rate": 4.4178082191780825e-06,
      "loss": 1.7819,
      "step": 273
    },
    {
      "epoch": 0.2814586543400103,
      "grad_norm": 2.8438684940338135,
      "learning_rate": 4.434931506849315e-06,
      "loss": 1.7435,
      "step": 274
    },
    {
      "epoch": 0.2824858757062147,
      "grad_norm": 2.9525997638702393,
      "learning_rate": 4.4520547945205486e-06,
      "loss": 1.7123,
      "step": 275
    },
    {
      "epoch": 0.2835130970724191,
      "grad_norm": 2.972714900970459,
      "learning_rate": 4.469178082191781e-06,
      "loss": 1.7693,
      "step": 276
    },
    {
      "epoch": 0.28454031843862354,
      "grad_norm": 3.4248580932617188,
      "learning_rate": 4.486301369863014e-06,
      "loss": 1.7502,
      "step": 277
    },
    {
      "epoch": 0.28556753980482796,
      "grad_norm": 2.9928481578826904,
      "learning_rate": 4.503424657534247e-06,
      "loss": 1.8064,
      "step": 278
    },
    {
      "epoch": 0.28659476117103233,
      "grad_norm": 2.944093942642212,
      "learning_rate": 4.52054794520548e-06,
      "loss": 1.7075,
      "step": 279
    },
    {
      "epoch": 0.28762198253723675,
      "grad_norm": 3.2028305530548096,
      "learning_rate": 4.537671232876713e-06,
      "loss": 1.7366,
      "step": 280
    },
    {
      "epoch": 0.28762198253723675,
      "eval_loss": 1.9768972396850586,
      "eval_runtime": 37.1078,
      "eval_samples_per_second": 26.948,
      "eval_steps_per_second": 1.132,
      "step": 280
    },
    {
      "epoch": 0.2886492039034412,
      "grad_norm": 2.8642148971557617,
      "learning_rate": 4.554794520547945e-06,
      "loss": 1.7909,
      "step": 281
    },
    {
      "epoch": 0.2896764252696456,
      "grad_norm": 3.2716004848480225,
      "learning_rate": 4.571917808219179e-06,
      "loss": 1.7906,
      "step": 282
    },
    {
      "epoch": 0.29070364663585,
      "grad_norm": 2.9601588249206543,
      "learning_rate": 4.589041095890411e-06,
      "loss": 1.7731,
      "step": 283
    },
    {
      "epoch": 0.29173086800205444,
      "grad_norm": 3.1850085258483887,
      "learning_rate": 4.606164383561644e-06,
      "loss": 1.7335,
      "step": 284
    },
    {
      "epoch": 0.29275808936825887,
      "grad_norm": 3.128908634185791,
      "learning_rate": 4.6232876712328774e-06,
      "loss": 1.748,
      "step": 285
    },
    {
      "epoch": 0.2937853107344633,
      "grad_norm": 3.063014507293701,
      "learning_rate": 4.64041095890411e-06,
      "loss": 1.7632,
      "step": 286
    },
    {
      "epoch": 0.2948125321006677,
      "grad_norm": 3.467817783355713,
      "learning_rate": 4.657534246575343e-06,
      "loss": 1.7295,
      "step": 287
    },
    {
      "epoch": 0.29583975346687214,
      "grad_norm": 2.7431066036224365,
      "learning_rate": 4.674657534246575e-06,
      "loss": 1.7728,
      "step": 288
    },
    {
      "epoch": 0.2968669748330765,
      "grad_norm": 3.271421432495117,
      "learning_rate": 4.691780821917809e-06,
      "loss": 1.7403,
      "step": 289
    },
    {
      "epoch": 0.2978941961992809,
      "grad_norm": 2.908351421356201,
      "learning_rate": 4.7089041095890414e-06,
      "loss": 1.7983,
      "step": 290
    },
    {
      "epoch": 0.2978941961992809,
      "eval_loss": 1.955810308456421,
      "eval_runtime": 37.0914,
      "eval_samples_per_second": 26.96,
      "eval_steps_per_second": 1.132,
      "step": 290
    },
    {
      "epoch": 0.29892141756548535,
      "grad_norm": 3.046114683151245,
      "learning_rate": 4.726027397260274e-06,
      "loss": 1.7612,
      "step": 291
    },
    {
      "epoch": 0.29994863893168977,
      "grad_norm": 3.275486707687378,
      "learning_rate": 4.7431506849315075e-06,
      "loss": 1.7548,
      "step": 292
    },
    {
      "epoch": 0.3009758602978942,
      "grad_norm": 2.819552183151245,
      "learning_rate": 4.76027397260274e-06,
      "loss": 1.7645,
      "step": 293
    },
    {
      "epoch": 0.3020030816640986,
      "grad_norm": 3.234227418899536,
      "learning_rate": 4.777397260273973e-06,
      "loss": 1.715,
      "step": 294
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 2.988713502883911,
      "learning_rate": 4.7945205479452054e-06,
      "loss": 1.7343,
      "step": 295
    },
    {
      "epoch": 0.30405752439650746,
      "grad_norm": 3.195387601852417,
      "learning_rate": 4.811643835616439e-06,
      "loss": 1.7421,
      "step": 296
    },
    {
      "epoch": 0.3050847457627119,
      "grad_norm": 3.617765426635742,
      "learning_rate": 4.8287671232876716e-06,
      "loss": 1.6661,
      "step": 297
    },
    {
      "epoch": 0.3061119671289163,
      "grad_norm": 2.741631269454956,
      "learning_rate": 4.845890410958904e-06,
      "loss": 1.7188,
      "step": 298
    },
    {
      "epoch": 0.3071391884951207,
      "grad_norm": 3.3230361938476562,
      "learning_rate": 4.863013698630138e-06,
      "loss": 1.721,
      "step": 299
    },
    {
      "epoch": 0.3081664098613251,
      "grad_norm": 2.696352005004883,
      "learning_rate": 4.88013698630137e-06,
      "loss": 1.7137,
      "step": 300
    },
    {
      "epoch": 0.3081664098613251,
      "eval_loss": 1.9677459001541138,
      "eval_runtime": 37.1101,
      "eval_samples_per_second": 26.947,
      "eval_steps_per_second": 1.132,
      "step": 300
    }
  ],
  "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": 9.35192822808576e+16,
  "train_batch_size": 3,
  "trial_name": null,
  "trial_params": null
}