{
  "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": 2.7873,
      "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
    },
    {
      "epoch": 0.10374935798664613,
      "grad_norm": 2.175354242324829,
      "learning_rate": 1.4897260273972605e-06,
      "loss": 2.2259,
      "step": 101
    },
    {
      "epoch": 0.10477657935285054,
      "grad_norm": 2.217677116394043,
      "learning_rate": 1.5068493150684932e-06,
      "loss": 2.2082,
      "step": 102
    },
    {
      "epoch": 0.10580380071905496,
      "grad_norm": 2.4618067741394043,
      "learning_rate": 1.5239726027397262e-06,
      "loss": 2.1649,
      "step": 103
    },
    {
      "epoch": 0.10683102208525937,
      "grad_norm": 2.232060432434082,
      "learning_rate": 1.541095890410959e-06,
      "loss": 2.1962,
      "step": 104
    },
    {
      "epoch": 0.10785824345146379,
      "grad_norm": 2.9140872955322266,
      "learning_rate": 1.5582191780821921e-06,
      "loss": 2.2446,
      "step": 105
    },
    {
      "epoch": 0.10888546481766821,
      "grad_norm": 2.232158660888672,
      "learning_rate": 1.5753424657534248e-06,
      "loss": 2.2179,
      "step": 106
    },
    {
      "epoch": 0.10991268618387262,
      "grad_norm": 2.804938793182373,
      "learning_rate": 1.5924657534246576e-06,
      "loss": 2.2449,
      "step": 107
    },
    {
      "epoch": 0.11093990755007704,
      "grad_norm": 2.3690710067749023,
      "learning_rate": 1.6095890410958907e-06,
      "loss": 2.225,
      "step": 108
    },
    {
      "epoch": 0.11196712891628145,
      "grad_norm": 2.7717416286468506,
      "learning_rate": 1.6267123287671235e-06,
      "loss": 2.0922,
      "step": 109
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 3.053602933883667,
      "learning_rate": 1.6438356164383561e-06,
      "loss": 2.1702,
      "step": 110
    },
    {
      "epoch": 0.11299435028248588,
      "eval_loss": 2.298161029815674,
      "eval_runtime": 44.0776,
      "eval_samples_per_second": 22.687,
      "eval_steps_per_second": 0.953,
      "step": 110
    },
    {
      "epoch": 0.1140215716486903,
      "grad_norm": 2.8673532009124756,
      "learning_rate": 1.6609589041095892e-06,
      "loss": 2.0938,
      "step": 111
    },
    {
      "epoch": 0.1150487930148947,
      "grad_norm": 2.57185959815979,
      "learning_rate": 1.678082191780822e-06,
      "loss": 2.1892,
      "step": 112
    },
    {
      "epoch": 0.11607601438109913,
      "grad_norm": 2.5278828144073486,
      "learning_rate": 1.695205479452055e-06,
      "loss": 2.1251,
      "step": 113
    },
    {
      "epoch": 0.11710323574730354,
      "grad_norm": 2.8581748008728027,
      "learning_rate": 1.7123287671232877e-06,
      "loss": 2.1699,
      "step": 114
    },
    {
      "epoch": 0.11813045711350796,
      "grad_norm": 2.924959897994995,
      "learning_rate": 1.7294520547945206e-06,
      "loss": 2.1005,
      "step": 115
    },
    {
      "epoch": 0.11915767847971238,
      "grad_norm": 2.477034091949463,
      "learning_rate": 1.7465753424657536e-06,
      "loss": 2.2016,
      "step": 116
    },
    {
      "epoch": 0.12018489984591679,
      "grad_norm": 2.8719305992126465,
      "learning_rate": 1.7636986301369865e-06,
      "loss": 2.1588,
      "step": 117
    },
    {
      "epoch": 0.12121212121212122,
      "grad_norm": 2.4403953552246094,
      "learning_rate": 1.7808219178082193e-06,
      "loss": 2.1445,
      "step": 118
    },
    {
      "epoch": 0.12223934257832562,
      "grad_norm": 2.7994632720947266,
      "learning_rate": 1.7979452054794521e-06,
      "loss": 2.1369,
      "step": 119
    },
    {
      "epoch": 0.12326656394453005,
      "grad_norm": 2.163196563720703,
      "learning_rate": 1.8150684931506852e-06,
      "loss": 2.2195,
      "step": 120
    },
    {
      "epoch": 0.12326656394453005,
      "eval_loss": 2.2648775577545166,
      "eval_runtime": 49.47,
      "eval_samples_per_second": 20.214,
      "eval_steps_per_second": 0.849,
      "step": 120
    },
    {
      "epoch": 0.12429378531073447,
      "grad_norm": 2.6743483543395996,
      "learning_rate": 1.832191780821918e-06,
      "loss": 2.1521,
      "step": 121
    },
    {
      "epoch": 0.12532100667693888,
      "grad_norm": 2.54795503616333,
      "learning_rate": 1.8493150684931507e-06,
      "loss": 2.1158,
      "step": 122
    },
    {
      "epoch": 0.1263482280431433,
      "grad_norm": 2.9093267917633057,
      "learning_rate": 1.8664383561643837e-06,
      "loss": 2.0707,
      "step": 123
    },
    {
      "epoch": 0.12737544940934772,
      "grad_norm": 2.416940212249756,
      "learning_rate": 1.8835616438356166e-06,
      "loss": 2.0901,
      "step": 124
    },
    {
      "epoch": 0.12840267077555212,
      "grad_norm": 2.8333663940429688,
      "learning_rate": 1.9006849315068496e-06,
      "loss": 2.0545,
      "step": 125
    },
    {
      "epoch": 0.12942989214175654,
      "grad_norm": 2.483051061630249,
      "learning_rate": 1.9178082191780823e-06,
      "loss": 2.1274,
      "step": 126
    },
    {
      "epoch": 0.13045711350796096,
      "grad_norm": 2.3486859798431396,
      "learning_rate": 1.9349315068493153e-06,
      "loss": 2.0478,
      "step": 127
    },
    {
      "epoch": 0.1314843348741654,
      "grad_norm": 3.1512887477874756,
      "learning_rate": 1.952054794520548e-06,
      "loss": 2.1041,
      "step": 128
    },
    {
      "epoch": 0.1325115562403698,
      "grad_norm": 2.902873992919922,
      "learning_rate": 1.969178082191781e-06,
      "loss": 2.1332,
      "step": 129
    },
    {
      "epoch": 0.1335387776065742,
      "grad_norm": 2.779132127761841,
      "learning_rate": 1.9863013698630136e-06,
      "loss": 2.1297,
      "step": 130
    },
    {
      "epoch": 0.1335387776065742,
      "eval_loss": 2.2391879558563232,
      "eval_runtime": 55.3018,
      "eval_samples_per_second": 18.083,
      "eval_steps_per_second": 0.759,
      "step": 130
    },
    {
      "epoch": 0.13456599897277863,
      "grad_norm": 2.703019618988037,
      "learning_rate": 2.0034246575342467e-06,
      "loss": 2.0506,
      "step": 131
    },
    {
      "epoch": 0.13559322033898305,
      "grad_norm": 3.0187575817108154,
      "learning_rate": 2.0205479452054797e-06,
      "loss": 2.1291,
      "step": 132
    },
    {
      "epoch": 0.13662044170518747,
      "grad_norm": 2.7629971504211426,
      "learning_rate": 2.037671232876713e-06,
      "loss": 2.1003,
      "step": 133
    },
    {
      "epoch": 0.1376476630713919,
      "grad_norm": 3.175776720046997,
      "learning_rate": 2.0547945205479454e-06,
      "loss": 2.0429,
      "step": 134
    },
    {
      "epoch": 0.1386748844375963,
      "grad_norm": 3.0342514514923096,
      "learning_rate": 2.071917808219178e-06,
      "loss": 2.0858,
      "step": 135
    },
    {
      "epoch": 0.1397021058038007,
      "grad_norm": 3.0861928462982178,
      "learning_rate": 2.089041095890411e-06,
      "loss": 2.0964,
      "step": 136
    },
    {
      "epoch": 0.14072932717000514,
      "grad_norm": 3.151945114135742,
      "learning_rate": 2.106164383561644e-06,
      "loss": 2.0194,
      "step": 137
    },
    {
      "epoch": 0.14175654853620956,
      "grad_norm": 2.9069676399230957,
      "learning_rate": 2.123287671232877e-06,
      "loss": 2.1131,
      "step": 138
    },
    {
      "epoch": 0.14278376990241398,
      "grad_norm": 3.2285282611846924,
      "learning_rate": 2.14041095890411e-06,
      "loss": 2.0643,
      "step": 139
    },
    {
      "epoch": 0.14381099126861838,
      "grad_norm": 2.500481367111206,
      "learning_rate": 2.1575342465753425e-06,
      "loss": 2.0625,
      "step": 140
    },
    {
      "epoch": 0.14381099126861838,
      "eval_loss": 2.211498975753784,
      "eval_runtime": 55.1046,
      "eval_samples_per_second": 18.147,
      "eval_steps_per_second": 0.762,
      "step": 140
    },
    {
      "epoch": 0.1448382126348228,
      "grad_norm": 4.004592418670654,
      "learning_rate": 2.1746575342465755e-06,
      "loss": 2.0644,
      "step": 141
    },
    {
      "epoch": 0.14586543400102722,
      "grad_norm": 2.9258391857147217,
      "learning_rate": 2.191780821917808e-06,
      "loss": 2.0174,
      "step": 142
    },
    {
      "epoch": 0.14689265536723164,
      "grad_norm": 3.0073509216308594,
      "learning_rate": 2.2089041095890412e-06,
      "loss": 2.1417,
      "step": 143
    },
    {
      "epoch": 0.14791987673343607,
      "grad_norm": 3.040708065032959,
      "learning_rate": 2.2260273972602743e-06,
      "loss": 2.0357,
      "step": 144
    },
    {
      "epoch": 0.14894709809964046,
      "grad_norm": 2.9062869548797607,
      "learning_rate": 2.243150684931507e-06,
      "loss": 2.0122,
      "step": 145
    },
    {
      "epoch": 0.14997431946584489,
      "grad_norm": 3.28969669342041,
      "learning_rate": 2.26027397260274e-06,
      "loss": 2.0255,
      "step": 146
    },
    {
      "epoch": 0.1510015408320493,
      "grad_norm": 3.608752727508545,
      "learning_rate": 2.2773972602739726e-06,
      "loss": 2.0184,
      "step": 147
    },
    {
      "epoch": 0.15202876219825373,
      "grad_norm": 2.900341033935547,
      "learning_rate": 2.2945205479452057e-06,
      "loss": 2.0532,
      "step": 148
    },
    {
      "epoch": 0.15305598356445815,
      "grad_norm": 2.881843328475952,
      "learning_rate": 2.3116438356164387e-06,
      "loss": 2.1336,
      "step": 149
    },
    {
      "epoch": 0.15408320493066255,
      "grad_norm": 3.4043259620666504,
      "learning_rate": 2.3287671232876713e-06,
      "loss": 2.0536,
      "step": 150
    },
    {
      "epoch": 0.15408320493066255,
      "eval_loss": 2.192880153656006,
      "eval_runtime": 53.7838,
      "eval_samples_per_second": 18.593,
      "eval_steps_per_second": 0.781,
      "step": 150
    },
    {
      "epoch": 0.15511042629686697,
      "grad_norm": 2.693107843399048,
      "learning_rate": 2.3458904109589044e-06,
      "loss": 1.9503,
      "step": 151
    },
    {
      "epoch": 0.1561376476630714,
      "grad_norm": 2.885260581970215,
      "learning_rate": 2.363013698630137e-06,
      "loss": 2.0081,
      "step": 152
    },
    {
      "epoch": 0.15716486902927582,
      "grad_norm": 3.4459924697875977,
      "learning_rate": 2.38013698630137e-06,
      "loss": 2.0649,
      "step": 153
    },
    {
      "epoch": 0.15819209039548024,
      "grad_norm": 2.8447093963623047,
      "learning_rate": 2.3972602739726027e-06,
      "loss": 2.0476,
      "step": 154
    },
    {
      "epoch": 0.15921931176168463,
      "grad_norm": 2.755176305770874,
      "learning_rate": 2.4143835616438358e-06,
      "loss": 2.0006,
      "step": 155
    },
    {
      "epoch": 0.16024653312788906,
      "grad_norm": 2.8677561283111572,
      "learning_rate": 2.431506849315069e-06,
      "loss": 1.9663,
      "step": 156
    },
    {
      "epoch": 0.16127375449409348,
      "grad_norm": 2.783351182937622,
      "learning_rate": 2.4486301369863015e-06,
      "loss": 2.0301,
      "step": 157
    },
    {
      "epoch": 0.1623009758602979,
      "grad_norm": 2.7545998096466064,
      "learning_rate": 2.4657534246575345e-06,
      "loss": 2.0438,
      "step": 158
    },
    {
      "epoch": 0.1633281972265023,
      "grad_norm": 2.8140594959259033,
      "learning_rate": 2.482876712328767e-06,
      "loss": 2.0055,
      "step": 159
    },
    {
      "epoch": 0.16435541859270672,
      "grad_norm": 2.6072335243225098,
      "learning_rate": 2.5e-06,
      "loss": 2.0262,
      "step": 160
    },
    {
      "epoch": 0.16435541859270672,
      "eval_loss": 2.179842710494995,
      "eval_runtime": 52.6159,
      "eval_samples_per_second": 19.006,
      "eval_steps_per_second": 0.798,
      "step": 160
    },
    {
      "epoch": 0.16538263995891114,
      "grad_norm": 2.830212354660034,
      "learning_rate": 2.5171232876712333e-06,
      "loss": 2.0154,
      "step": 161
    },
    {
      "epoch": 0.16640986132511557,
      "grad_norm": 2.677140712738037,
      "learning_rate": 2.534246575342466e-06,
      "loss": 1.9933,
      "step": 162
    },
    {
      "epoch": 0.16743708269132,
      "grad_norm": 2.837759017944336,
      "learning_rate": 2.551369863013699e-06,
      "loss": 1.9602,
      "step": 163
    },
    {
      "epoch": 0.16846430405752438,
      "grad_norm": 3.9556589126586914,
      "learning_rate": 2.568493150684932e-06,
      "loss": 2.0121,
      "step": 164
    },
    {
      "epoch": 0.1694915254237288,
      "grad_norm": 2.8715925216674805,
      "learning_rate": 2.585616438356164e-06,
      "loss": 2.0219,
      "step": 165
    },
    {
      "epoch": 0.17051874678993323,
      "grad_norm": 3.5073623657226562,
      "learning_rate": 2.6027397260273973e-06,
      "loss": 2.0202,
      "step": 166
    },
    {
      "epoch": 0.17154596815613765,
      "grad_norm": 2.751962900161743,
      "learning_rate": 2.6198630136986303e-06,
      "loss": 1.9528,
      "step": 167
    },
    {
      "epoch": 0.17257318952234207,
      "grad_norm": 3.7753474712371826,
      "learning_rate": 2.6369863013698634e-06,
      "loss": 2.0208,
      "step": 168
    },
    {
      "epoch": 0.17360041088854647,
      "grad_norm": 2.642289876937866,
      "learning_rate": 2.654109589041096e-06,
      "loss": 2.0386,
      "step": 169
    },
    {
      "epoch": 0.1746276322547509,
      "grad_norm": 2.82173490524292,
      "learning_rate": 2.671232876712329e-06,
      "loss": 2.0355,
      "step": 170
    },
    {
      "epoch": 0.1746276322547509,
      "eval_loss": 2.1699249744415283,
      "eval_runtime": 50.0341,
      "eval_samples_per_second": 19.986,
      "eval_steps_per_second": 0.839,
      "step": 170
    },
    {
      "epoch": 0.17565485362095531,
      "grad_norm": 3.342280149459839,
      "learning_rate": 2.688356164383562e-06,
      "loss": 1.9672,
      "step": 171
    },
    {
      "epoch": 0.17668207498715974,
      "grad_norm": 2.6548173427581787,
      "learning_rate": 2.705479452054795e-06,
      "loss": 1.9669,
      "step": 172
    },
    {
      "epoch": 0.17770929635336416,
      "grad_norm": 2.6548173427581787,
      "learning_rate": 2.705479452054795e-06,
      "loss": 1.961,
      "step": 173
    },
    {
      "epoch": 0.17873651771956856,
      "grad_norm": 3.4306116104125977,
      "learning_rate": 2.7226027397260274e-06,
      "loss": 1.9173,
      "step": 174
    },
    {
      "epoch": 0.17976373908577298,
      "grad_norm": 2.7991764545440674,
      "learning_rate": 2.7397260273972604e-06,
      "loss": 2.0339,
      "step": 175
    },
    {
      "epoch": 0.1807909604519774,
      "grad_norm": 3.6040217876434326,
      "learning_rate": 2.7568493150684935e-06,
      "loss": 2.0218,
      "step": 176
    },
    {
      "epoch": 0.18181818181818182,
      "grad_norm": 3.0253515243530273,
      "learning_rate": 2.773972602739726e-06,
      "loss": 1.9245,
      "step": 177
    },
    {
      "epoch": 0.18284540318438625,
      "grad_norm": 3.405141830444336,
      "learning_rate": 2.791095890410959e-06,
      "loss": 2.0136,
      "step": 178
    },
    {
      "epoch": 0.18387262455059064,
      "grad_norm": 2.7518203258514404,
      "learning_rate": 2.8082191780821922e-06,
      "loss": 1.8925,
      "step": 179
    },
    {
      "epoch": 0.18489984591679506,
      "grad_norm": 3.1903367042541504,
      "learning_rate": 2.8253424657534253e-06,
      "loss": 2.0523,
      "step": 180
    },
    {
      "epoch": 0.18489984591679506,
      "eval_loss": 2.158029794692993,
      "eval_runtime": 48.6162,
      "eval_samples_per_second": 20.569,
      "eval_steps_per_second": 0.864,
      "step": 180
    },
    {
      "epoch": 0.1859270672829995,
      "grad_norm": 3.0331413745880127,
      "learning_rate": 2.842465753424658e-06,
      "loss": 2.0167,
      "step": 181
    },
    {
      "epoch": 0.1869542886492039,
      "grad_norm": 2.919433116912842,
      "learning_rate": 2.8595890410958905e-06,
      "loss": 2.0197,
      "step": 182
    },
    {
      "epoch": 0.18798151001540833,
      "grad_norm": 2.9013049602508545,
      "learning_rate": 2.876712328767123e-06,
      "loss": 2.0301,
      "step": 183
    },
    {
      "epoch": 0.18900873138161273,
      "grad_norm": 2.738800525665283,
      "learning_rate": 2.8938356164383562e-06,
      "loss": 1.894,
      "step": 184
    },
    {
      "epoch": 0.19003595274781715,
      "grad_norm": 2.670806407928467,
      "learning_rate": 2.9109589041095893e-06,
      "loss": 1.9127,
      "step": 185
    },
    {
      "epoch": 0.19106317411402157,
      "grad_norm": 3.0435004234313965,
      "learning_rate": 2.9280821917808223e-06,
      "loss": 1.8996,
      "step": 186
    },
    {
      "epoch": 0.192090395480226,
      "grad_norm": 3.2139949798583984,
      "learning_rate": 2.945205479452055e-06,
      "loss": 1.9255,
      "step": 187
    },
    {
      "epoch": 0.19311761684643042,
      "grad_norm": 3.252965211868286,
      "learning_rate": 2.962328767123288e-06,
      "loss": 1.9809,
      "step": 188
    },
    {
      "epoch": 0.1941448382126348,
      "grad_norm": 2.9325191974639893,
      "learning_rate": 2.979452054794521e-06,
      "loss": 1.9691,
      "step": 189
    },
    {
      "epoch": 0.19517205957883924,
      "grad_norm": 3.5879862308502197,
      "learning_rate": 2.9965753424657533e-06,
      "loss": 1.9205,
      "step": 190
    },
    {
      "epoch": 0.19517205957883924,
      "eval_loss": 2.13791561126709,
      "eval_runtime": 44.8545,
      "eval_samples_per_second": 22.294,
      "eval_steps_per_second": 0.936,
      "step": 190
    },
    {
      "epoch": 0.19619928094504366,
      "grad_norm": 3.0025253295898438,
      "learning_rate": 3.0136986301369864e-06,
      "loss": 1.9717,
      "step": 191
    },
    {
      "epoch": 0.19722650231124808,
      "grad_norm": 3.1785972118377686,
      "learning_rate": 3.0308219178082194e-06,
      "loss": 1.9535,
      "step": 192
    },
    {
      "epoch": 0.1982537236774525,
      "grad_norm": 3.121065378189087,
      "learning_rate": 3.0479452054794525e-06,
      "loss": 1.9026,
      "step": 193
    },
    {
      "epoch": 0.1992809450436569,
      "grad_norm": 2.838779926300049,
      "learning_rate": 3.065068493150685e-06,
      "loss": 1.941,
      "step": 194
    },
    {
      "epoch": 0.20030816640986132,
      "grad_norm": 2.8916969299316406,
      "learning_rate": 3.082191780821918e-06,
      "loss": 1.8983,
      "step": 195
    },
    {
      "epoch": 0.20133538777606574,
      "grad_norm": 2.9195168018341064,
      "learning_rate": 3.099315068493151e-06,
      "loss": 1.918,
      "step": 196
    },
    {
      "epoch": 0.20236260914227017,
      "grad_norm": 3.235989809036255,
      "learning_rate": 3.1164383561643843e-06,
      "loss": 1.9111,
      "step": 197
    },
    {
      "epoch": 0.2033898305084746,
      "grad_norm": 3.0316455364227295,
      "learning_rate": 3.1335616438356165e-06,
      "loss": 1.8839,
      "step": 198
    },
    {
      "epoch": 0.20441705187467898,
      "grad_norm": 2.963610887527466,
      "learning_rate": 3.1506849315068495e-06,
      "loss": 2.0303,
      "step": 199
    },
    {
      "epoch": 0.2054442732408834,
      "grad_norm": 2.944054365158081,
      "learning_rate": 3.167808219178082e-06,
      "loss": 1.8822,
      "step": 200
    },
    {
      "epoch": 0.2054442732408834,
      "eval_loss": 2.1433050632476807,
      "eval_runtime": 45.8205,
      "eval_samples_per_second": 21.824,
      "eval_steps_per_second": 0.917,
      "step": 200
    },
    {
      "epoch": 0.20647149460708783,
      "grad_norm": 2.8648695945739746,
      "learning_rate": 3.184931506849315e-06,
      "loss": 1.8841,
      "step": 201
    },
    {
      "epoch": 0.20749871597329225,
      "grad_norm": 3.2838797569274902,
      "learning_rate": 3.2020547945205483e-06,
      "loss": 1.8623,
      "step": 202
    },
    {
      "epoch": 0.20852593733949668,
      "grad_norm": 2.7965173721313477,
      "learning_rate": 3.2191780821917813e-06,
      "loss": 1.8521,
      "step": 203
    },
    {
      "epoch": 0.20955315870570107,
      "grad_norm": 3.3449349403381348,
      "learning_rate": 3.236301369863014e-06,
      "loss": 1.84,
      "step": 204
    },
    {
      "epoch": 0.2105803800719055,
      "grad_norm": 3.4888951778411865,
      "learning_rate": 3.253424657534247e-06,
      "loss": 1.824,
      "step": 205
    },
    {
      "epoch": 0.21160760143810992,
      "grad_norm": 2.991349220275879,
      "learning_rate": 3.2705479452054796e-06,
      "loss": 1.9101,
      "step": 206
    },
    {
      "epoch": 0.21263482280431434,
      "grad_norm": 3.313509702682495,
      "learning_rate": 3.2876712328767123e-06,
      "loss": 1.8912,
      "step": 207
    },
    {
      "epoch": 0.21366204417051873,
      "grad_norm": 2.8260746002197266,
      "learning_rate": 3.3047945205479453e-06,
      "loss": 1.8555,
      "step": 208
    },
    {
      "epoch": 0.21468926553672316,
      "grad_norm": 2.7131688594818115,
      "learning_rate": 3.3219178082191784e-06,
      "loss": 1.8693,
      "step": 209
    },
    {
      "epoch": 0.21571648690292758,
      "grad_norm": 2.5836338996887207,
      "learning_rate": 3.3390410958904114e-06,
      "loss": 1.8965,
      "step": 210
    },
    {
      "epoch": 0.21571648690292758,
      "eval_loss": 2.1232542991638184,
      "eval_runtime": 42.3352,
      "eval_samples_per_second": 23.621,
      "eval_steps_per_second": 0.992,
      "step": 210
    },
    {
      "epoch": 0.216743708269132,
      "grad_norm": 2.8341355323791504,
      "learning_rate": 3.356164383561644e-06,
      "loss": 1.9131,
      "step": 211
    },
    {
      "epoch": 0.21777092963533642,
      "grad_norm": 2.490853786468506,
      "learning_rate": 3.373287671232877e-06,
      "loss": 1.9626,
      "step": 212
    },
    {
      "epoch": 0.21879815100154082,
      "grad_norm": 2.597956895828247,
      "learning_rate": 3.39041095890411e-06,
      "loss": 1.9203,
      "step": 213
    },
    {
      "epoch": 0.21982537236774524,
      "grad_norm": 3.1104283332824707,
      "learning_rate": 3.4075342465753424e-06,
      "loss": 1.9442,
      "step": 214
    },
    {
      "epoch": 0.22085259373394966,
      "grad_norm": 2.5698931217193604,
      "learning_rate": 3.4246575342465754e-06,
      "loss": 1.8385,
      "step": 215
    },
    {
      "epoch": 0.2218798151001541,
      "grad_norm": 3.1637446880340576,
      "learning_rate": 3.4417808219178085e-06,
      "loss": 1.9005,
      "step": 216
    },
    {
      "epoch": 0.2229070364663585,
      "grad_norm": 2.764070749282837,
      "learning_rate": 3.458904109589041e-06,
      "loss": 1.8886,
      "step": 217
    },
    {
      "epoch": 0.2239342578325629,
      "grad_norm": 3.303781032562256,
      "learning_rate": 3.476027397260274e-06,
      "loss": 1.9085,
      "step": 218
    },
    {
      "epoch": 0.22496147919876733,
      "grad_norm": 2.9543044567108154,
      "learning_rate": 3.4931506849315072e-06,
      "loss": 1.9014,
      "step": 219
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 2.7277028560638428,
      "learning_rate": 3.5102739726027403e-06,
      "loss": 1.9017,
      "step": 220
    },
    {
      "epoch": 0.22598870056497175,
      "eval_loss": 2.1024081707000732,
      "eval_runtime": 45.4966,
      "eval_samples_per_second": 21.98,
      "eval_steps_per_second": 0.923,
      "step": 220
    },
    {
      "epoch": 0.22701592193117617,
      "grad_norm": 2.864140033721924,
      "learning_rate": 3.527397260273973e-06,
      "loss": 1.8935,
      "step": 221
    },
    {
      "epoch": 0.2280431432973806,
      "grad_norm": 3.4133172035217285,
      "learning_rate": 3.5445205479452056e-06,
      "loss": 1.874,
      "step": 222
    },
    {
      "epoch": 0.229070364663585,
      "grad_norm": 3.33343243598938,
      "learning_rate": 3.5616438356164386e-06,
      "loss": 1.8789,
      "step": 223
    },
    {
      "epoch": 0.2300975860297894,
      "grad_norm": 3.5947320461273193,
      "learning_rate": 3.5787671232876712e-06,
      "loss": 1.9529,
      "step": 224
    },
    {
      "epoch": 0.23112480739599384,
      "grad_norm": 3.2194948196411133,
      "learning_rate": 3.5958904109589043e-06,
      "loss": 1.9205,
      "step": 225
    },
    {
      "epoch": 0.23215202876219826,
      "grad_norm": 3.3137149810791016,
      "learning_rate": 3.6130136986301373e-06,
      "loss": 1.8584,
      "step": 226
    },
    {
      "epoch": 0.23317925012840268,
      "grad_norm": 3.3358561992645264,
      "learning_rate": 3.6301369863013704e-06,
      "loss": 1.8817,
      "step": 227
    },
    {
      "epoch": 0.23420647149460708,
      "grad_norm": 3.8612711429595947,
      "learning_rate": 3.647260273972603e-06,
      "loss": 1.9189,
      "step": 228
    },
    {
      "epoch": 0.2352336928608115,
      "grad_norm": 3.0039336681365967,
      "learning_rate": 3.664383561643836e-06,
      "loss": 1.92,
      "step": 229
    },
    {
      "epoch": 0.23626091422701592,
      "grad_norm": 3.8983118534088135,
      "learning_rate": 3.6815068493150687e-06,
      "loss": 1.8512,
      "step": 230
    },
    {
      "epoch": 0.23626091422701592,
      "eval_loss": 2.1237711906433105,
      "eval_runtime": 45.6126,
      "eval_samples_per_second": 21.924,
      "eval_steps_per_second": 0.921,
      "step": 230
    },
    {
      "epoch": 0.23728813559322035,
      "grad_norm": 3.061300039291382,
      "learning_rate": 3.6986301369863014e-06,
      "loss": 1.8772,
      "step": 231
    },
    {
      "epoch": 0.23831535695942477,
      "grad_norm": 3.3102450370788574,
      "learning_rate": 3.7157534246575344e-06,
      "loss": 1.8395,
      "step": 232
    },
    {
      "epoch": 0.23934257832562916,
      "grad_norm": 2.9634461402893066,
      "learning_rate": 3.7328767123287675e-06,
      "loss": 1.9447,
      "step": 233
    },
    {
      "epoch": 0.24036979969183359,
      "grad_norm": 3.0937695503234863,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 1.8628,
      "step": 234
    },
    {
      "epoch": 0.241397021058038,
      "grad_norm": 2.8129842281341553,
      "learning_rate": 3.767123287671233e-06,
      "loss": 1.8891,
      "step": 235
    },
    {
      "epoch": 0.24242424242424243,
      "grad_norm": 2.9616780281066895,
      "learning_rate": 3.784246575342466e-06,
      "loss": 1.9112,
      "step": 236
    },
    {
      "epoch": 0.24345146379044685,
      "grad_norm": 2.837721109390259,
      "learning_rate": 3.8013698630136993e-06,
      "loss": 1.8514,
      "step": 237
    },
    {
      "epoch": 0.24447868515665125,
      "grad_norm": 3.137784004211426,
      "learning_rate": 3.818493150684932e-06,
      "loss": 1.8764,
      "step": 238
    },
    {
      "epoch": 0.24550590652285567,
      "grad_norm": 2.9692037105560303,
      "learning_rate": 3.8356164383561645e-06,
      "loss": 1.8201,
      "step": 239
    },
    {
      "epoch": 0.2465331278890601,
      "grad_norm": 2.6718621253967285,
      "learning_rate": 3.852739726027397e-06,
      "loss": 1.9309,
      "step": 240
    },
    {
      "epoch": 0.2465331278890601,
      "eval_loss": 2.101331949234009,
      "eval_runtime": 45.6346,
      "eval_samples_per_second": 21.913,
      "eval_steps_per_second": 0.92,
      "step": 240
    },
    {
      "epoch": 0.24756034925526452,
      "grad_norm": 3.411193609237671,
      "learning_rate": 3.869863013698631e-06,
      "loss": 1.9171,
      "step": 241
    },
    {
      "epoch": 0.24858757062146894,
      "grad_norm": 2.8848962783813477,
      "learning_rate": 3.886986301369863e-06,
      "loss": 1.8587,
      "step": 242
    },
    {
      "epoch": 0.24961479198767333,
      "grad_norm": 2.756298065185547,
      "learning_rate": 3.904109589041096e-06,
      "loss": 1.8614,
      "step": 243
    },
    {
      "epoch": 0.25064201335387776,
      "grad_norm": 2.8048956394195557,
      "learning_rate": 3.921232876712329e-06,
      "loss": 1.8225,
      "step": 244
    },
    {
      "epoch": 0.2516692347200822,
      "grad_norm": 2.9872403144836426,
      "learning_rate": 3.938356164383562e-06,
      "loss": 1.8367,
      "step": 245
    },
    {
      "epoch": 0.2526964560862866,
      "grad_norm": 2.710156202316284,
      "learning_rate": 3.9554794520547955e-06,
      "loss": 1.809,
      "step": 246
    },
    {
      "epoch": 0.253723677452491,
      "grad_norm": 3.2177000045776367,
      "learning_rate": 3.972602739726027e-06,
      "loss": 1.8883,
      "step": 247
    },
    {
      "epoch": 0.25475089881869545,
      "grad_norm": 3.160964250564575,
      "learning_rate": 3.989726027397261e-06,
      "loss": 1.8267,
      "step": 248
    },
    {
      "epoch": 0.25577812018489987,
      "grad_norm": 2.853498935699463,
      "learning_rate": 4.006849315068493e-06,
      "loss": 1.8852,
      "step": 249
    },
    {
      "epoch": 0.25680534155110424,
      "grad_norm": 2.571742296218872,
      "learning_rate": 4.023972602739726e-06,
      "loss": 1.8833,
      "step": 250
    },
    {
      "epoch": 0.25680534155110424,
      "eval_loss": 2.0988597869873047,
      "eval_runtime": 47.7045,
      "eval_samples_per_second": 20.962,
      "eval_steps_per_second": 0.88,
      "step": 250
    },
    {
      "epoch": 0.25783256291730866,
      "grad_norm": 2.776742458343506,
      "learning_rate": 4.0410958904109595e-06,
      "loss": 1.8662,
      "step": 251
    },
    {
      "epoch": 0.2588597842835131,
      "grad_norm": 2.8038573265075684,
      "learning_rate": 4.058219178082192e-06,
      "loss": 1.8528,
      "step": 252
    },
    {
      "epoch": 0.2598870056497175,
      "grad_norm": 2.557623863220215,
      "learning_rate": 4.075342465753426e-06,
      "loss": 1.8765,
      "step": 253
    },
    {
      "epoch": 0.26091422701592193,
      "grad_norm": 3.0477073192596436,
      "learning_rate": 4.092465753424658e-06,
      "loss": 1.8434,
      "step": 254
    },
    {
      "epoch": 0.26194144838212635,
      "grad_norm": 2.6221649646759033,
      "learning_rate": 4.109589041095891e-06,
      "loss": 1.8348,
      "step": 255
    },
    {
      "epoch": 0.2629686697483308,
      "grad_norm": 3.0849292278289795,
      "learning_rate": 4.1267123287671235e-06,
      "loss": 1.9057,
      "step": 256
    },
    {
      "epoch": 0.2639958911145352,
      "grad_norm": 2.795184373855591,
      "learning_rate": 4.143835616438356e-06,
      "loss": 1.8528,
      "step": 257
    },
    {
      "epoch": 0.2650231124807396,
      "grad_norm": 2.887193441390991,
      "learning_rate": 4.16095890410959e-06,
      "loss": 1.9176,
      "step": 258
    },
    {
      "epoch": 0.26605033384694404,
      "grad_norm": 2.776801347732544,
      "learning_rate": 4.178082191780822e-06,
      "loss": 1.8911,
      "step": 259
    },
    {
      "epoch": 0.2670775552131484,
      "grad_norm": 2.980426788330078,
      "learning_rate": 4.195205479452055e-06,
      "loss": 1.8288,
      "step": 260
    },
    {
      "epoch": 0.2670775552131484,
      "eval_loss": 2.0636370182037354,
      "eval_runtime": 49.3081,
      "eval_samples_per_second": 20.281,
      "eval_steps_per_second": 0.852,
      "step": 260
    },
    {
      "epoch": 0.26810477657935283,
      "grad_norm": 2.7921340465545654,
      "learning_rate": 4.212328767123288e-06,
      "loss": 1.8405,
      "step": 261
    },
    {
      "epoch": 0.26913199794555726,
      "grad_norm": 2.67714262008667,
      "learning_rate": 4.229452054794521e-06,
      "loss": 1.8342,
      "step": 262
    },
    {
      "epoch": 0.2701592193117617,
      "grad_norm": 2.819868326187134,
      "learning_rate": 4.246575342465754e-06,
      "loss": 1.8466,
      "step": 263
    },
    {
      "epoch": 0.2711864406779661,
      "grad_norm": 2.611250638961792,
      "learning_rate": 4.263698630136986e-06,
      "loss": 1.8314,
      "step": 264
    },
    {
      "epoch": 0.2722136620441705,
      "grad_norm": 3.0406076908111572,
      "learning_rate": 4.28082191780822e-06,
      "loss": 1.7924,
      "step": 265
    },
    {
      "epoch": 0.27324088341037495,
      "grad_norm": 3.212790012359619,
      "learning_rate": 4.297945205479452e-06,
      "loss": 1.9479,
      "step": 266
    },
    {
      "epoch": 0.27426810477657937,
      "grad_norm": 2.4767045974731445,
      "learning_rate": 4.315068493150685e-06,
      "loss": 1.835,
      "step": 267
    },
    {
      "epoch": 0.2752953261427838,
      "grad_norm": 3.191835641860962,
      "learning_rate": 4.3321917808219185e-06,
      "loss": 1.8261,
      "step": 268
    },
    {
      "epoch": 0.2763225475089882,
      "grad_norm": 2.9970273971557617,
      "learning_rate": 4.349315068493151e-06,
      "loss": 1.8427,
      "step": 269
    },
    {
      "epoch": 0.2773497688751926,
      "grad_norm": 2.888843297958374,
      "learning_rate": 4.3664383561643846e-06,
      "loss": 1.819,
      "step": 270
    },
    {
      "epoch": 0.2773497688751926,
      "eval_loss": 2.054966926574707,
      "eval_runtime": 45.9212,
      "eval_samples_per_second": 21.776,
      "eval_steps_per_second": 0.915,
      "step": 270
    },
    {
      "epoch": 0.278376990241397,
      "grad_norm": 2.7771849632263184,
      "learning_rate": 4.383561643835616e-06,
      "loss": 1.8178,
      "step": 271
    },
    {
      "epoch": 0.2794042116076014,
      "grad_norm": 2.9749014377593994,
      "learning_rate": 4.40068493150685e-06,
      "loss": 1.8982,
      "step": 272
    },
    {
      "epoch": 0.28043143297380585,
      "grad_norm": 3.076021432876587,
      "learning_rate": 4.4178082191780825e-06,
      "loss": 1.8575,
      "step": 273
    },
    {
      "epoch": 0.2814586543400103,
      "grad_norm": 3.2113568782806396,
      "learning_rate": 4.434931506849315e-06,
      "loss": 1.8241,
      "step": 274
    },
    {
      "epoch": 0.2824858757062147,
      "grad_norm": 3.322063684463501,
      "learning_rate": 4.4520547945205486e-06,
      "loss": 1.7922,
      "step": 275
    },
    {
      "epoch": 0.2835130970724191,
      "grad_norm": 3.2778918743133545,
      "learning_rate": 4.469178082191781e-06,
      "loss": 1.8412,
      "step": 276
    },
    {
      "epoch": 0.28454031843862354,
      "grad_norm": 3.1802618503570557,
      "learning_rate": 4.486301369863014e-06,
      "loss": 1.8283,
      "step": 277
    },
    {
      "epoch": 0.28556753980482796,
      "grad_norm": 2.9214258193969727,
      "learning_rate": 4.503424657534247e-06,
      "loss": 1.8817,
      "step": 278
    },
    {
      "epoch": 0.28659476117103233,
      "grad_norm": 2.8809854984283447,
      "learning_rate": 4.52054794520548e-06,
      "loss": 1.7662,
      "step": 279
    },
    {
      "epoch": 0.28762198253723675,
      "grad_norm": 2.925537586212158,
      "learning_rate": 4.537671232876713e-06,
      "loss": 1.8147,
      "step": 280
    },
    {
      "epoch": 0.28762198253723675,
      "eval_loss": 2.054513454437256,
      "eval_runtime": 51.5036,
      "eval_samples_per_second": 19.416,
      "eval_steps_per_second": 0.815,
      "step": 280
    },
    {
      "epoch": 0.2886492039034412,
      "grad_norm": 2.9421887397766113,
      "learning_rate": 4.554794520547945e-06,
      "loss": 1.8581,
      "step": 281
    },
    {
      "epoch": 0.2896764252696456,
      "grad_norm": 2.9733567237854004,
      "learning_rate": 4.571917808219179e-06,
      "loss": 1.8703,
      "step": 282
    },
    {
      "epoch": 0.29070364663585,
      "grad_norm": 2.5352156162261963,
      "learning_rate": 4.589041095890411e-06,
      "loss": 1.8505,
      "step": 283
    },
    {
      "epoch": 0.29173086800205444,
      "grad_norm": 2.773847818374634,
      "learning_rate": 4.606164383561644e-06,
      "loss": 1.8114,
      "step": 284
    },
    {
      "epoch": 0.29275808936825887,
      "grad_norm": 2.709632635116577,
      "learning_rate": 4.6232876712328774e-06,
      "loss": 1.815,
      "step": 285
    },
    {
      "epoch": 0.2937853107344633,
      "grad_norm": 3.1234357357025146,
      "learning_rate": 4.64041095890411e-06,
      "loss": 1.8391,
      "step": 286
    },
    {
      "epoch": 0.2948125321006677,
      "grad_norm": 2.9376144409179688,
      "learning_rate": 4.657534246575343e-06,
      "loss": 1.7998,
      "step": 287
    },
    {
      "epoch": 0.29583975346687214,
      "grad_norm": 3.0812032222747803,
      "learning_rate": 4.674657534246575e-06,
      "loss": 1.8462,
      "step": 288
    },
    {
      "epoch": 0.2968669748330765,
      "grad_norm": 2.922722578048706,
      "learning_rate": 4.691780821917809e-06,
      "loss": 1.8263,
      "step": 289
    },
    {
      "epoch": 0.2978941961992809,
      "grad_norm": 2.9484992027282715,
      "learning_rate": 4.7089041095890414e-06,
      "loss": 1.8754,
      "step": 290
    },
    {
      "epoch": 0.2978941961992809,
      "eval_loss": 2.032902240753174,
      "eval_runtime": 47.8711,
      "eval_samples_per_second": 20.889,
      "eval_steps_per_second": 0.877,
      "step": 290
    },
    {
      "epoch": 0.29892141756548535,
      "grad_norm": 3.0068976879119873,
      "learning_rate": 4.726027397260274e-06,
      "loss": 1.8256,
      "step": 291
    },
    {
      "epoch": 0.29994863893168977,
      "grad_norm": 2.6469006538391113,
      "learning_rate": 4.7431506849315075e-06,
      "loss": 1.8354,
      "step": 292
    },
    {
      "epoch": 0.3009758602978942,
      "grad_norm": 3.06986927986145,
      "learning_rate": 4.76027397260274e-06,
      "loss": 1.8402,
      "step": 293
    },
    {
      "epoch": 0.3020030816640986,
      "grad_norm": 2.8409981727600098,
      "learning_rate": 4.777397260273973e-06,
      "loss": 1.7915,
      "step": 294
    },
    {
      "epoch": 0.30303030303030304,
      "grad_norm": 3.1027376651763916,
      "learning_rate": 4.7945205479452054e-06,
      "loss": 1.8153,
      "step": 295
    },
    {
      "epoch": 0.30405752439650746,
      "grad_norm": 2.7221434116363525,
      "learning_rate": 4.811643835616439e-06,
      "loss": 1.8098,
      "step": 296
    },
    {
      "epoch": 0.3050847457627119,
      "grad_norm": 3.0559370517730713,
      "learning_rate": 4.8287671232876716e-06,
      "loss": 1.7504,
      "step": 297
    },
    {
      "epoch": 0.3061119671289163,
      "grad_norm": 2.9628236293792725,
      "learning_rate": 4.845890410958904e-06,
      "loss": 1.8019,
      "step": 298
    },
    {
      "epoch": 0.3071391884951207,
      "grad_norm": 2.6248221397399902,
      "learning_rate": 4.863013698630138e-06,
      "loss": 1.8001,
      "step": 299
    },
    {
      "epoch": 0.3081664098613251,
      "grad_norm": 3.0477702617645264,
      "learning_rate": 4.88013698630137e-06,
      "loss": 1.7915,
      "step": 300
    },
    {
      "epoch": 0.3081664098613251,
      "eval_loss": 2.0522429943084717,
      "eval_runtime": 46.796,
      "eval_samples_per_second": 21.369,
      "eval_steps_per_second": 0.898,
      "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
}