{
  "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": 2.7873,
      "step": 1
    },
    {
      "epoch": 0.002054442732408834,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7904,
      "step": 2
    },
    {
      "epoch": 0.0030816640986132513,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8348,
      "step": 3
    },
    {
      "epoch": 0.004108885464817668,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8357,
      "step": 4
    },
    {
      "epoch": 0.005136106831022085,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8153,
      "step": 5
    },
    {
      "epoch": 0.0061633281972265025,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.825,
      "step": 6
    },
    {
      "epoch": 0.007190549563430919,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8002,
      "step": 7
    },
    {
      "epoch": 0.008217770929635337,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8413,
      "step": 8
    },
    {
      "epoch": 0.009244992295839754,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8157,
      "step": 9
    },
    {
      "epoch": 0.01027221366204417,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8249,
      "step": 10
    },
    {
      "epoch": 0.01027221366204417,
      "eval_loss": 2.8518412113189697,
      "eval_runtime": 43.212,
      "eval_samples_per_second": 23.142,
      "eval_steps_per_second": 0.972,
      "step": 10
    },
    {
      "epoch": 0.011299435028248588,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7829,
      "step": 11
    },
    {
      "epoch": 0.012326656394453005,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.7819,
      "step": 12
    },
    {
      "epoch": 0.01335387776065742,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8355,
      "step": 13
    },
    {
      "epoch": 0.014381099126861838,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.8138,
      "step": 14
    },
    {
      "epoch": 0.015408320493066256,
      "grad_norm": 5.162191390991211,
      "learning_rate": 1.7123287671232876e-08,
      "loss": 2.8088,
      "step": 15
    },
    {
      "epoch": 0.016435541859270673,
      "grad_norm": 5.5954084396362305,
      "learning_rate": 3.424657534246575e-08,
      "loss": 2.7883,
      "step": 16
    },
    {
      "epoch": 0.01746276322547509,
      "grad_norm": 5.542337417602539,
      "learning_rate": 5.136986301369863e-08,
      "loss": 2.7625,
      "step": 17
    },
    {
      "epoch": 0.01848998459167951,
      "grad_norm": 5.300518989562988,
      "learning_rate": 6.84931506849315e-08,
      "loss": 2.84,
      "step": 18
    },
    {
      "epoch": 0.019517205957883924,
      "grad_norm": 5.6646881103515625,
      "learning_rate": 8.561643835616439e-08,
      "loss": 2.761,
      "step": 19
    },
    {
      "epoch": 0.02054442732408834,
      "grad_norm": 5.375557899475098,
      "learning_rate": 1.0273972602739726e-07,
      "loss": 2.8215,
      "step": 20
    },
    {
      "epoch": 0.02054442732408834,
      "eval_loss": 2.8507144451141357,
      "eval_runtime": 45.1133,
      "eval_samples_per_second": 22.166,
      "eval_steps_per_second": 0.931,
      "step": 20
    },
    {
      "epoch": 0.02157164869029276,
      "grad_norm": 5.1731977462768555,
      "learning_rate": 1.1986301369863014e-07,
      "loss": 2.8348,
      "step": 21
    },
    {
      "epoch": 0.022598870056497175,
      "grad_norm": 5.370945930480957,
      "learning_rate": 1.36986301369863e-07,
      "loss": 2.822,
      "step": 22
    },
    {
      "epoch": 0.02362609142270159,
      "grad_norm": 5.550389289855957,
      "learning_rate": 1.541095890410959e-07,
      "loss": 2.7904,
      "step": 23
    },
    {
      "epoch": 0.02465331278890601,
      "grad_norm": 5.339347839355469,
      "learning_rate": 1.7123287671232878e-07,
      "loss": 2.8066,
      "step": 24
    },
    {
      "epoch": 0.025680534155110426,
      "grad_norm": 5.2319722175598145,
      "learning_rate": 1.8835616438356165e-07,
      "loss": 2.7976,
      "step": 25
    },
    {
      "epoch": 0.02670775552131484,
      "grad_norm": 5.207149982452393,
      "learning_rate": 2.0547945205479452e-07,
      "loss": 2.8162,
      "step": 26
    },
    {
      "epoch": 0.02773497688751926,
      "grad_norm": 4.400204181671143,
      "learning_rate": 2.226027397260274e-07,
      "loss": 2.7808,
      "step": 27
    },
    {
      "epoch": 0.028762198253723677,
      "grad_norm": 4.21675968170166,
      "learning_rate": 2.397260273972603e-07,
      "loss": 2.8044,
      "step": 28
    },
    {
      "epoch": 0.029789419619928096,
      "grad_norm": 4.406878471374512,
      "learning_rate": 2.568493150684932e-07,
      "loss": 2.8162,
      "step": 29
    },
    {
      "epoch": 0.030816640986132512,
      "grad_norm": 4.024835586547852,
      "learning_rate": 2.73972602739726e-07,
      "loss": 2.7994,
      "step": 30
    },
    {
      "epoch": 0.030816640986132512,
      "eval_loss": 2.8124029636383057,
      "eval_runtime": 43.1772,
      "eval_samples_per_second": 23.16,
      "eval_steps_per_second": 0.973,
      "step": 30
    },
    {
      "epoch": 0.03184386235233693,
      "grad_norm": 3.5378901958465576,
      "learning_rate": 2.910958904109589e-07,
      "loss": 2.7637,
      "step": 31
    },
    {
      "epoch": 0.03287108371854135,
      "grad_norm": 3.6289916038513184,
      "learning_rate": 3.082191780821918e-07,
      "loss": 2.8017,
      "step": 32
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 3.6789698600769043,
      "learning_rate": 3.2534246575342466e-07,
      "loss": 2.7723,
      "step": 33
    },
    {
      "epoch": 0.03492552645095018,
      "grad_norm": 3.491389751434326,
      "learning_rate": 3.4246575342465755e-07,
      "loss": 2.7528,
      "step": 34
    },
    {
      "epoch": 0.035952747817154594,
      "grad_norm": 3.383080005645752,
      "learning_rate": 3.595890410958904e-07,
      "loss": 2.7418,
      "step": 35
    },
    {
      "epoch": 0.03697996918335902,
      "grad_norm": 3.4823594093322754,
      "learning_rate": 3.767123287671233e-07,
      "loss": 2.6662,
      "step": 36
    },
    {
      "epoch": 0.03800719054956343,
      "grad_norm": 3.2146108150482178,
      "learning_rate": 3.938356164383562e-07,
      "loss": 2.7659,
      "step": 37
    },
    {
      "epoch": 0.03903441191576785,
      "grad_norm": 2.9549412727355957,
      "learning_rate": 4.1095890410958903e-07,
      "loss": 2.6838,
      "step": 38
    },
    {
      "epoch": 0.040061633281972264,
      "grad_norm": 3.0744080543518066,
      "learning_rate": 4.2808219178082193e-07,
      "loss": 2.6879,
      "step": 39
    },
    {
      "epoch": 0.04108885464817668,
      "grad_norm": 3.19840669631958,
      "learning_rate": 4.452054794520548e-07,
      "loss": 2.7443,
      "step": 40
    },
    {
      "epoch": 0.04108885464817668,
      "eval_loss": 2.7469444274902344,
      "eval_runtime": 46.4676,
      "eval_samples_per_second": 21.52,
      "eval_steps_per_second": 0.904,
      "step": 40
    },
    {
      "epoch": 0.042116076014381096,
      "grad_norm": 3.178406000137329,
      "learning_rate": 4.6232876712328767e-07,
      "loss": 2.7036,
      "step": 41
    },
    {
      "epoch": 0.04314329738058552,
      "grad_norm": 3.2032673358917236,
      "learning_rate": 4.794520547945206e-07,
      "loss": 2.6465,
      "step": 42
    },
    {
      "epoch": 0.044170518746789934,
      "grad_norm": 3.1525962352752686,
      "learning_rate": 4.965753424657534e-07,
      "loss": 2.6996,
      "step": 43
    },
    {
      "epoch": 0.04519774011299435,
      "grad_norm": 2.907524585723877,
      "learning_rate": 5.136986301369864e-07,
      "loss": 2.6581,
      "step": 44
    },
    {
      "epoch": 0.046224961479198766,
      "grad_norm": 2.5885250568389893,
      "learning_rate": 5.308219178082192e-07,
      "loss": 2.6773,
      "step": 45
    },
    {
      "epoch": 0.04725218284540318,
      "grad_norm": 2.569068431854248,
      "learning_rate": 5.47945205479452e-07,
      "loss": 2.6635,
      "step": 46
    },
    {
      "epoch": 0.048279404211607604,
      "grad_norm": 2.5313518047332764,
      "learning_rate": 5.65068493150685e-07,
      "loss": 2.706,
      "step": 47
    },
    {
      "epoch": 0.04930662557781202,
      "grad_norm": 2.615442991256714,
      "learning_rate": 5.821917808219178e-07,
      "loss": 2.638,
      "step": 48
    },
    {
      "epoch": 0.050333846944016436,
      "grad_norm": 2.7420806884765625,
      "learning_rate": 5.993150684931507e-07,
      "loss": 2.6398,
      "step": 49
    },
    {
      "epoch": 0.05136106831022085,
      "grad_norm": 2.5246975421905518,
      "learning_rate": 6.164383561643836e-07,
      "loss": 2.5916,
      "step": 50
    },
    {
      "epoch": 0.05136106831022085,
      "eval_loss": 2.6723692417144775,
      "eval_runtime": 46.7206,
      "eval_samples_per_second": 21.404,
      "eval_steps_per_second": 0.899,
      "step": 50
    },
    {
      "epoch": 0.05238828967642527,
      "grad_norm": 2.390143632888794,
      "learning_rate": 6.335616438356165e-07,
      "loss": 2.5773,
      "step": 51
    },
    {
      "epoch": 0.05341551104262968,
      "grad_norm": 2.0792484283447266,
      "learning_rate": 6.506849315068493e-07,
      "loss": 2.6249,
      "step": 52
    },
    {
      "epoch": 0.054442732408834106,
      "grad_norm": 1.9995019435882568,
      "learning_rate": 6.678082191780823e-07,
      "loss": 2.5425,
      "step": 53
    },
    {
      "epoch": 0.05546995377503852,
      "grad_norm": 1.985452651977539,
      "learning_rate": 6.849315068493151e-07,
      "loss": 2.5986,
      "step": 54
    },
    {
      "epoch": 0.05649717514124294,
      "grad_norm": 2.10184907913208,
      "learning_rate": 7.020547945205481e-07,
      "loss": 2.5713,
      "step": 55
    },
    {
      "epoch": 0.05752439650744735,
      "grad_norm": 2.0898985862731934,
      "learning_rate": 7.191780821917808e-07,
      "loss": 2.535,
      "step": 56
    },
    {
      "epoch": 0.05855161787365177,
      "grad_norm": 2.0239579677581787,
      "learning_rate": 7.363013698630137e-07,
      "loss": 2.5667,
      "step": 57
    },
    {
      "epoch": 0.05957883923985619,
      "grad_norm": 2.207080125808716,
      "learning_rate": 7.534246575342466e-07,
      "loss": 2.4999,
      "step": 58
    },
    {
      "epoch": 0.06060606060606061,
      "grad_norm": 1.8541918992996216,
      "learning_rate": 7.705479452054795e-07,
      "loss": 2.5582,
      "step": 59
    },
    {
      "epoch": 0.061633281972265024,
      "grad_norm": 1.8530476093292236,
      "learning_rate": 7.876712328767124e-07,
      "loss": 2.5535,
      "step": 60
    },
    {
      "epoch": 0.061633281972265024,
      "eval_loss": 2.607963800430298,
      "eval_runtime": 45.9754,
      "eval_samples_per_second": 21.751,
      "eval_steps_per_second": 0.914,
      "step": 60
    },
    {
      "epoch": 0.06266050333846944,
      "grad_norm": 1.7978090047836304,
      "learning_rate": 8.047945205479453e-07,
      "loss": 2.53,
      "step": 61
    },
    {
      "epoch": 0.06368772470467386,
      "grad_norm": 1.8173762559890747,
      "learning_rate": 8.219178082191781e-07,
      "loss": 2.5144,
      "step": 62
    },
    {
      "epoch": 0.06471494607087827,
      "grad_norm": 2.0847485065460205,
      "learning_rate": 8.39041095890411e-07,
      "loss": 2.5525,
      "step": 63
    },
    {
      "epoch": 0.0657421674370827,
      "grad_norm": 1.8691741228103638,
      "learning_rate": 8.561643835616439e-07,
      "loss": 2.5451,
      "step": 64
    },
    {
      "epoch": 0.0667693888032871,
      "grad_norm": 2.0242726802825928,
      "learning_rate": 8.732876712328768e-07,
      "loss": 2.4145,
      "step": 65
    },
    {
      "epoch": 0.06779661016949153,
      "grad_norm": 1.8268908262252808,
      "learning_rate": 8.904109589041097e-07,
      "loss": 2.5024,
      "step": 66
    },
    {
      "epoch": 0.06882383153569595,
      "grad_norm": 1.8703057765960693,
      "learning_rate": 9.075342465753426e-07,
      "loss": 2.461,
      "step": 67
    },
    {
      "epoch": 0.06985105290190036,
      "grad_norm": 1.8747144937515259,
      "learning_rate": 9.246575342465753e-07,
      "loss": 2.5122,
      "step": 68
    },
    {
      "epoch": 0.07087827426810478,
      "grad_norm": 1.744924783706665,
      "learning_rate": 9.417808219178083e-07,
      "loss": 2.4673,
      "step": 69
    },
    {
      "epoch": 0.07190549563430919,
      "grad_norm": 1.7492460012435913,
      "learning_rate": 9.589041095890411e-07,
      "loss": 2.5598,
      "step": 70
    },
    {
      "epoch": 0.07190549563430919,
      "eval_loss": 2.547417640686035,
      "eval_runtime": 49.7488,
      "eval_samples_per_second": 20.101,
      "eval_steps_per_second": 0.844,
      "step": 70
    },
    {
      "epoch": 0.07293271700051361,
      "grad_norm": 1.9218230247497559,
      "learning_rate": 9.76027397260274e-07,
      "loss": 2.4562,
      "step": 71
    },
    {
      "epoch": 0.07395993836671803,
      "grad_norm": 2.0127363204956055,
      "learning_rate": 9.931506849315068e-07,
      "loss": 2.4141,
      "step": 72
    },
    {
      "epoch": 0.07498715973292244,
      "grad_norm": 1.8700369596481323,
      "learning_rate": 1.0102739726027399e-06,
      "loss": 2.4696,
      "step": 73
    },
    {
      "epoch": 0.07601438109912687,
      "grad_norm": 2.1706016063690186,
      "learning_rate": 1.0273972602739727e-06,
      "loss": 2.4404,
      "step": 74
    },
    {
      "epoch": 0.07704160246533127,
      "grad_norm": 2.470412254333496,
      "learning_rate": 1.0445205479452056e-06,
      "loss": 2.4409,
      "step": 75
    },
    {
      "epoch": 0.0780688238315357,
      "grad_norm": 1.906569242477417,
      "learning_rate": 1.0616438356164384e-06,
      "loss": 2.4313,
      "step": 76
    },
    {
      "epoch": 0.07909604519774012,
      "grad_norm": 2.122936487197876,
      "learning_rate": 1.0787671232876712e-06,
      "loss": 2.4369,
      "step": 77
    },
    {
      "epoch": 0.08012326656394453,
      "grad_norm": 2.079127311706543,
      "learning_rate": 1.095890410958904e-06,
      "loss": 2.449,
      "step": 78
    },
    {
      "epoch": 0.08115048793014895,
      "grad_norm": 1.9173146486282349,
      "learning_rate": 1.1130136986301371e-06,
      "loss": 2.3782,
      "step": 79
    },
    {
      "epoch": 0.08217770929635336,
      "grad_norm": 1.9856903553009033,
      "learning_rate": 1.13013698630137e-06,
      "loss": 2.4215,
      "step": 80
    },
    {
      "epoch": 0.08217770929635336,
      "eval_loss": 2.479673385620117,
      "eval_runtime": 46.2211,
      "eval_samples_per_second": 21.635,
      "eval_steps_per_second": 0.909,
      "step": 80
    },
    {
      "epoch": 0.08320493066255778,
      "grad_norm": 2.3764865398406982,
      "learning_rate": 1.1472602739726028e-06,
      "loss": 2.3744,
      "step": 81
    },
    {
      "epoch": 0.08423215202876219,
      "grad_norm": 1.980668544769287,
      "learning_rate": 1.1643835616438357e-06,
      "loss": 2.3856,
      "step": 82
    },
    {
      "epoch": 0.08525937339496661,
      "grad_norm": 2.2589704990386963,
      "learning_rate": 1.1815068493150685e-06,
      "loss": 2.3853,
      "step": 83
    },
    {
      "epoch": 0.08628659476117104,
      "grad_norm": 2.171780824661255,
      "learning_rate": 1.1986301369863014e-06,
      "loss": 2.3603,
      "step": 84
    },
    {
      "epoch": 0.08731381612737545,
      "grad_norm": 2.25736403465271,
      "learning_rate": 1.2157534246575344e-06,
      "loss": 2.3189,
      "step": 85
    },
    {
      "epoch": 0.08834103749357987,
      "grad_norm": 2.3643763065338135,
      "learning_rate": 1.2328767123287673e-06,
      "loss": 2.3795,
      "step": 86
    },
    {
      "epoch": 0.08936825885978428,
      "grad_norm": 2.384516954421997,
      "learning_rate": 1.25e-06,
      "loss": 2.3257,
      "step": 87
    },
    {
      "epoch": 0.0903954802259887,
      "grad_norm": 2.5072567462921143,
      "learning_rate": 1.267123287671233e-06,
      "loss": 2.3125,
      "step": 88
    },
    {
      "epoch": 0.09142270159219312,
      "grad_norm": 2.2726807594299316,
      "learning_rate": 1.284246575342466e-06,
      "loss": 2.3297,
      "step": 89
    },
    {
      "epoch": 0.09244992295839753,
      "grad_norm": 2.4817421436309814,
      "learning_rate": 1.3013698630136986e-06,
      "loss": 2.2878,
      "step": 90
    },
    {
      "epoch": 0.09244992295839753,
      "eval_loss": 2.4065146446228027,
      "eval_runtime": 47.9372,
      "eval_samples_per_second": 20.861,
      "eval_steps_per_second": 0.876,
      "step": 90
    },
    {
      "epoch": 0.09347714432460195,
      "grad_norm": 2.2219603061676025,
      "learning_rate": 1.3184931506849317e-06,
      "loss": 2.2978,
      "step": 91
    },
    {
      "epoch": 0.09450436569080636,
      "grad_norm": 2.8790745735168457,
      "learning_rate": 1.3356164383561645e-06,
      "loss": 2.313,
      "step": 92
    },
    {
      "epoch": 0.09553158705701079,
      "grad_norm": 2.589200496673584,
      "learning_rate": 1.3527397260273976e-06,
      "loss": 2.2937,
      "step": 93
    },
    {
      "epoch": 0.09655880842321521,
      "grad_norm": 2.760016679763794,
      "learning_rate": 1.3698630136986302e-06,
      "loss": 2.277,
      "step": 94
    },
    {
      "epoch": 0.09758602978941962,
      "grad_norm": 2.2641494274139404,
      "learning_rate": 1.386986301369863e-06,
      "loss": 2.3336,
      "step": 95
    },
    {
      "epoch": 0.09861325115562404,
      "grad_norm": 2.2786386013031006,
      "learning_rate": 1.4041095890410961e-06,
      "loss": 2.233,
      "step": 96
    },
    {
      "epoch": 0.09964047252182845,
      "grad_norm": 2.5590052604675293,
      "learning_rate": 1.421232876712329e-06,
      "loss": 2.2851,
      "step": 97
    },
    {
      "epoch": 0.10066769388803287,
      "grad_norm": 2.5609471797943115,
      "learning_rate": 1.4383561643835616e-06,
      "loss": 2.1848,
      "step": 98
    },
    {
      "epoch": 0.1016949152542373,
      "grad_norm": 2.442521810531616,
      "learning_rate": 1.4554794520547946e-06,
      "loss": 2.2073,
      "step": 99
    },
    {
      "epoch": 0.1027221366204417,
      "grad_norm": 2.3735859394073486,
      "learning_rate": 1.4726027397260275e-06,
      "loss": 2.2353,
      "step": 100
    },
    {
      "epoch": 0.1027221366204417,
      "eval_loss": 2.3457911014556885,
      "eval_runtime": 51.6469,
      "eval_samples_per_second": 19.362,
      "eval_steps_per_second": 0.813,
      "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
}