{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.32986970146792016,
  "eval_steps": 10,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006597394029358403,
      "grad_norm": 1.2868798971176147,
      "learning_rate": 3.2894736842105265e-06,
      "loss": 4.6934,
      "step": 10
    },
    {
      "epoch": 0.006597394029358403,
      "eval_loss": 4.687362194061279,
      "eval_runtime": 282.9655,
      "eval_samples_per_second": 18.045,
      "eval_steps_per_second": 0.565,
      "step": 10
    },
    {
      "epoch": 0.013194788058716806,
      "grad_norm": 1.302221417427063,
      "learning_rate": 6.578947368421053e-06,
      "loss": 4.6651,
      "step": 20
    },
    {
      "epoch": 0.013194788058716806,
      "eval_loss": 4.648743152618408,
      "eval_runtime": 282.9326,
      "eval_samples_per_second": 18.047,
      "eval_steps_per_second": 0.566,
      "step": 20
    },
    {
      "epoch": 0.01979218208807521,
      "grad_norm": 1.4535945653915405,
      "learning_rate": 9.868421052631579e-06,
      "loss": 4.6063,
      "step": 30
    },
    {
      "epoch": 0.01979218208807521,
      "eval_loss": 4.54951286315918,
      "eval_runtime": 282.3584,
      "eval_samples_per_second": 18.083,
      "eval_steps_per_second": 0.567,
      "step": 30
    },
    {
      "epoch": 0.026389576117433613,
      "grad_norm": 1.714498519897461,
      "learning_rate": 1.3157894736842106e-05,
      "loss": 4.4527,
      "step": 40
    },
    {
      "epoch": 0.026389576117433613,
      "eval_loss": 4.304062366485596,
      "eval_runtime": 282.5935,
      "eval_samples_per_second": 18.068,
      "eval_steps_per_second": 0.566,
      "step": 40
    },
    {
      "epoch": 0.03298697014679202,
      "grad_norm": 1.832472324371338,
      "learning_rate": 1.6447368421052635e-05,
      "loss": 4.1216,
      "step": 50
    },
    {
      "epoch": 0.03298697014679202,
      "eval_loss": 3.8426761627197266,
      "eval_runtime": 281.3902,
      "eval_samples_per_second": 18.146,
      "eval_steps_per_second": 0.569,
      "step": 50
    },
    {
      "epoch": 0.03958436417615042,
      "grad_norm": 1.1160222291946411,
      "learning_rate": 1.9736842105263158e-05,
      "loss": 3.6561,
      "step": 60
    },
    {
      "epoch": 0.03958436417615042,
      "eval_loss": 3.4654476642608643,
      "eval_runtime": 282.2746,
      "eval_samples_per_second": 18.089,
      "eval_steps_per_second": 0.567,
      "step": 60
    },
    {
      "epoch": 0.04618175820550882,
      "grad_norm": 1.1160507202148438,
      "learning_rate": 2.3026315789473685e-05,
      "loss": 3.2993,
      "step": 70
    },
    {
      "epoch": 0.04618175820550882,
      "eval_loss": 3.0560474395751953,
      "eval_runtime": 282.4864,
      "eval_samples_per_second": 18.075,
      "eval_steps_per_second": 0.566,
      "step": 70
    },
    {
      "epoch": 0.052779152234867226,
      "grad_norm": 0.7468234896659851,
      "learning_rate": 2.6315789473684212e-05,
      "loss": 2.8777,
      "step": 80
    },
    {
      "epoch": 0.052779152234867226,
      "eval_loss": 2.7082414627075195,
      "eval_runtime": 282.279,
      "eval_samples_per_second": 18.088,
      "eval_steps_per_second": 0.567,
      "step": 80
    },
    {
      "epoch": 0.05937654626422563,
      "grad_norm": 0.7456527948379517,
      "learning_rate": 2.9605263157894735e-05,
      "loss": 2.5844,
      "step": 90
    },
    {
      "epoch": 0.05937654626422563,
      "eval_loss": 2.400399923324585,
      "eval_runtime": 282.4234,
      "eval_samples_per_second": 18.079,
      "eval_steps_per_second": 0.567,
      "step": 90
    },
    {
      "epoch": 0.06597394029358404,
      "grad_norm": 0.7843755483627319,
      "learning_rate": 3.289473684210527e-05,
      "loss": 2.2405,
      "step": 100
    },
    {
      "epoch": 0.06597394029358404,
      "eval_loss": 2.043464422225952,
      "eval_runtime": 282.4971,
      "eval_samples_per_second": 18.075,
      "eval_steps_per_second": 0.566,
      "step": 100
    },
    {
      "epoch": 0.07257133432294244,
      "grad_norm": 0.7848460078239441,
      "learning_rate": 3.618421052631579e-05,
      "loss": 1.8797,
      "step": 110
    },
    {
      "epoch": 0.07257133432294244,
      "eval_loss": 1.6749211549758911,
      "eval_runtime": 282.4596,
      "eval_samples_per_second": 18.077,
      "eval_steps_per_second": 0.566,
      "step": 110
    },
    {
      "epoch": 0.07916872835230084,
      "grad_norm": 0.8517773151397705,
      "learning_rate": 3.9473684210526316e-05,
      "loss": 1.5041,
      "step": 120
    },
    {
      "epoch": 0.07916872835230084,
      "eval_loss": 1.322484016418457,
      "eval_runtime": 282.425,
      "eval_samples_per_second": 18.079,
      "eval_steps_per_second": 0.567,
      "step": 120
    },
    {
      "epoch": 0.08576612238165925,
      "grad_norm": 0.924010694026947,
      "learning_rate": 4.2763157894736847e-05,
      "loss": 1.1712,
      "step": 130
    },
    {
      "epoch": 0.08576612238165925,
      "eval_loss": 1.0092010498046875,
      "eval_runtime": 282.4135,
      "eval_samples_per_second": 18.08,
      "eval_steps_per_second": 0.567,
      "step": 130
    },
    {
      "epoch": 0.09236351641101764,
      "grad_norm": 0.599291205406189,
      "learning_rate": 4.605263157894737e-05,
      "loss": 0.9068,
      "step": 140
    },
    {
      "epoch": 0.09236351641101764,
      "eval_loss": 0.8262147307395935,
      "eval_runtime": 282.3089,
      "eval_samples_per_second": 18.087,
      "eval_steps_per_second": 0.567,
      "step": 140
    },
    {
      "epoch": 0.09896091044037605,
      "grad_norm": 0.4690685570240021,
      "learning_rate": 4.9342105263157894e-05,
      "loss": 0.7821,
      "step": 150
    },
    {
      "epoch": 0.09896091044037605,
      "eval_loss": 0.7165087461471558,
      "eval_runtime": 282.1805,
      "eval_samples_per_second": 18.095,
      "eval_steps_per_second": 0.567,
      "step": 150
    },
    {
      "epoch": 0.10555830446973445,
      "grad_norm": 0.5129504203796387,
      "learning_rate": 4.9706529713866475e-05,
      "loss": 0.6867,
      "step": 160
    },
    {
      "epoch": 0.10555830446973445,
      "eval_loss": 0.6483914256095886,
      "eval_runtime": 282.207,
      "eval_samples_per_second": 18.093,
      "eval_steps_per_second": 0.567,
      "step": 160
    },
    {
      "epoch": 0.11215569849909286,
      "grad_norm": 0.4116060435771942,
      "learning_rate": 4.933969185619956e-05,
      "loss": 0.6315,
      "step": 170
    },
    {
      "epoch": 0.11215569849909286,
      "eval_loss": 0.6029236912727356,
      "eval_runtime": 282.3594,
      "eval_samples_per_second": 18.083,
      "eval_steps_per_second": 0.567,
      "step": 170
    },
    {
      "epoch": 0.11875309252845126,
      "grad_norm": 0.4301941990852356,
      "learning_rate": 4.8972853998532655e-05,
      "loss": 0.5833,
      "step": 180
    },
    {
      "epoch": 0.11875309252845126,
      "eval_loss": 0.5720704197883606,
      "eval_runtime": 282.0439,
      "eval_samples_per_second": 18.104,
      "eval_steps_per_second": 0.567,
      "step": 180
    },
    {
      "epoch": 0.12535048655780967,
      "grad_norm": 0.5514675378799438,
      "learning_rate": 4.860601614086574e-05,
      "loss": 0.5667,
      "step": 190
    },
    {
      "epoch": 0.12535048655780967,
      "eval_loss": 0.5490744709968567,
      "eval_runtime": 282.3239,
      "eval_samples_per_second": 18.086,
      "eval_steps_per_second": 0.567,
      "step": 190
    },
    {
      "epoch": 0.13194788058716808,
      "grad_norm": 0.4441012144088745,
      "learning_rate": 4.823917828319883e-05,
      "loss": 0.5303,
      "step": 200
    },
    {
      "epoch": 0.13194788058716808,
      "eval_loss": 0.5291892886161804,
      "eval_runtime": 282.4233,
      "eval_samples_per_second": 18.079,
      "eval_steps_per_second": 0.567,
      "step": 200
    },
    {
      "epoch": 0.13854527461652646,
      "grad_norm": 0.4900895059108734,
      "learning_rate": 4.787234042553192e-05,
      "loss": 0.5109,
      "step": 210
    },
    {
      "epoch": 0.13854527461652646,
      "eval_loss": 0.5132142901420593,
      "eval_runtime": 282.4262,
      "eval_samples_per_second": 18.079,
      "eval_steps_per_second": 0.567,
      "step": 210
    },
    {
      "epoch": 0.14514266864588488,
      "grad_norm": 0.4287125766277313,
      "learning_rate": 4.750550256786501e-05,
      "loss": 0.5109,
      "step": 220
    },
    {
      "epoch": 0.14514266864588488,
      "eval_loss": 0.4994109869003296,
      "eval_runtime": 282.5477,
      "eval_samples_per_second": 18.071,
      "eval_steps_per_second": 0.566,
      "step": 220
    },
    {
      "epoch": 0.1517400626752433,
      "grad_norm": 0.4390946626663208,
      "learning_rate": 4.713866471019809e-05,
      "loss": 0.4952,
      "step": 230
    },
    {
      "epoch": 0.1517400626752433,
      "eval_loss": 0.4881007969379425,
      "eval_runtime": 282.5158,
      "eval_samples_per_second": 18.073,
      "eval_steps_per_second": 0.566,
      "step": 230
    },
    {
      "epoch": 0.15833745670460167,
      "grad_norm": 0.5645927786827087,
      "learning_rate": 4.677182685253118e-05,
      "loss": 0.488,
      "step": 240
    },
    {
      "epoch": 0.15833745670460167,
      "eval_loss": 0.4788074791431427,
      "eval_runtime": 282.6337,
      "eval_samples_per_second": 18.066,
      "eval_steps_per_second": 0.566,
      "step": 240
    },
    {
      "epoch": 0.16493485073396008,
      "grad_norm": 0.5930696129798889,
      "learning_rate": 4.6404988994864274e-05,
      "loss": 0.4833,
      "step": 250
    },
    {
      "epoch": 0.16493485073396008,
      "eval_loss": 0.4700024425983429,
      "eval_runtime": 282.5674,
      "eval_samples_per_second": 18.07,
      "eval_steps_per_second": 0.566,
      "step": 250
    },
    {
      "epoch": 0.1715322447633185,
      "grad_norm": 0.408792644739151,
      "learning_rate": 4.6038151137197364e-05,
      "loss": 0.4696,
      "step": 260
    },
    {
      "epoch": 0.1715322447633185,
      "eval_loss": 0.46224626898765564,
      "eval_runtime": 282.2108,
      "eval_samples_per_second": 18.093,
      "eval_steps_per_second": 0.567,
      "step": 260
    },
    {
      "epoch": 0.1781296387926769,
      "grad_norm": 0.5276111960411072,
      "learning_rate": 4.567131327953045e-05,
      "loss": 0.4579,
      "step": 270
    },
    {
      "epoch": 0.1781296387926769,
      "eval_loss": 0.455151230096817,
      "eval_runtime": 282.6419,
      "eval_samples_per_second": 18.065,
      "eval_steps_per_second": 0.566,
      "step": 270
    },
    {
      "epoch": 0.1847270328220353,
      "grad_norm": 0.5726278424263,
      "learning_rate": 4.530447542186354e-05,
      "loss": 0.4547,
      "step": 280
    },
    {
      "epoch": 0.1847270328220353,
      "eval_loss": 0.44886669516563416,
      "eval_runtime": 282.6094,
      "eval_samples_per_second": 18.067,
      "eval_steps_per_second": 0.566,
      "step": 280
    },
    {
      "epoch": 0.1913244268513937,
      "grad_norm": 0.4161057770252228,
      "learning_rate": 4.493763756419663e-05,
      "loss": 0.4513,
      "step": 290
    },
    {
      "epoch": 0.1913244268513937,
      "eval_loss": 0.44479382038116455,
      "eval_runtime": 282.5015,
      "eval_samples_per_second": 18.074,
      "eval_steps_per_second": 0.566,
      "step": 290
    },
    {
      "epoch": 0.1979218208807521,
      "grad_norm": 0.4173205494880676,
      "learning_rate": 4.457079970652971e-05,
      "loss": 0.4364,
      "step": 300
    },
    {
      "epoch": 0.1979218208807521,
      "eval_loss": 0.4391051232814789,
      "eval_runtime": 282.6206,
      "eval_samples_per_second": 18.067,
      "eval_steps_per_second": 0.566,
      "step": 300
    },
    {
      "epoch": 0.20451921491011052,
      "grad_norm": 0.4726370871067047,
      "learning_rate": 4.420396184886281e-05,
      "loss": 0.4413,
      "step": 310
    },
    {
      "epoch": 0.20451921491011052,
      "eval_loss": 0.43503668904304504,
      "eval_runtime": 282.4681,
      "eval_samples_per_second": 18.076,
      "eval_steps_per_second": 0.566,
      "step": 310
    },
    {
      "epoch": 0.2111166089394689,
      "grad_norm": 0.528791069984436,
      "learning_rate": 4.383712399119589e-05,
      "loss": 0.4347,
      "step": 320
    },
    {
      "epoch": 0.2111166089394689,
      "eval_loss": 0.4299105107784271,
      "eval_runtime": 282.3837,
      "eval_samples_per_second": 18.082,
      "eval_steps_per_second": 0.567,
      "step": 320
    },
    {
      "epoch": 0.2177140029688273,
      "grad_norm": 0.4637807607650757,
      "learning_rate": 4.347028613352898e-05,
      "loss": 0.4263,
      "step": 330
    },
    {
      "epoch": 0.2177140029688273,
      "eval_loss": 0.42648786306381226,
      "eval_runtime": 282.4045,
      "eval_samples_per_second": 18.08,
      "eval_steps_per_second": 0.567,
      "step": 330
    },
    {
      "epoch": 0.22431139699818572,
      "grad_norm": 0.5652016401290894,
      "learning_rate": 4.3103448275862066e-05,
      "loss": 0.424,
      "step": 340
    },
    {
      "epoch": 0.22431139699818572,
      "eval_loss": 0.42295747995376587,
      "eval_runtime": 282.132,
      "eval_samples_per_second": 18.098,
      "eval_steps_per_second": 0.567,
      "step": 340
    },
    {
      "epoch": 0.2309087910275441,
      "grad_norm": 0.5480278134346008,
      "learning_rate": 4.273661041819516e-05,
      "loss": 0.4246,
      "step": 350
    },
    {
      "epoch": 0.2309087910275441,
      "eval_loss": 0.4191484749317169,
      "eval_runtime": 282.8434,
      "eval_samples_per_second": 18.052,
      "eval_steps_per_second": 0.566,
      "step": 350
    },
    {
      "epoch": 0.23750618505690252,
      "grad_norm": 0.5954585671424866,
      "learning_rate": 4.2369772560528246e-05,
      "loss": 0.4194,
      "step": 360
    },
    {
      "epoch": 0.23750618505690252,
      "eval_loss": 0.4160284399986267,
      "eval_runtime": 282.0609,
      "eval_samples_per_second": 18.102,
      "eval_steps_per_second": 0.567,
      "step": 360
    },
    {
      "epoch": 0.24410357908626093,
      "grad_norm": 0.6444059610366821,
      "learning_rate": 4.2002934702861336e-05,
      "loss": 0.4151,
      "step": 370
    },
    {
      "epoch": 0.24410357908626093,
      "eval_loss": 0.4145909547805786,
      "eval_runtime": 282.2951,
      "eval_samples_per_second": 18.087,
      "eval_steps_per_second": 0.567,
      "step": 370
    },
    {
      "epoch": 0.25070097311561934,
      "grad_norm": 0.5506740212440491,
      "learning_rate": 4.163609684519443e-05,
      "loss": 0.4143,
      "step": 380
    },
    {
      "epoch": 0.25070097311561934,
      "eval_loss": 0.41122376918792725,
      "eval_runtime": 282.3323,
      "eval_samples_per_second": 18.085,
      "eval_steps_per_second": 0.567,
      "step": 380
    },
    {
      "epoch": 0.2572983671449777,
      "grad_norm": 0.5273014307022095,
      "learning_rate": 4.126925898752752e-05,
      "loss": 0.4059,
      "step": 390
    },
    {
      "epoch": 0.2572983671449777,
      "eval_loss": 0.41092923283576965,
      "eval_runtime": 282.2453,
      "eval_samples_per_second": 18.091,
      "eval_steps_per_second": 0.567,
      "step": 390
    },
    {
      "epoch": 0.26389576117433616,
      "grad_norm": 0.5662177205085754,
      "learning_rate": 4.09024211298606e-05,
      "loss": 0.411,
      "step": 400
    },
    {
      "epoch": 0.26389576117433616,
      "eval_loss": 0.40584176778793335,
      "eval_runtime": 282.2166,
      "eval_samples_per_second": 18.092,
      "eval_steps_per_second": 0.567,
      "step": 400
    },
    {
      "epoch": 0.27049315520369455,
      "grad_norm": 0.6541048884391785,
      "learning_rate": 4.05355832721937e-05,
      "loss": 0.4017,
      "step": 410
    },
    {
      "epoch": 0.27049315520369455,
      "eval_loss": 0.4048697054386139,
      "eval_runtime": 282.3287,
      "eval_samples_per_second": 18.085,
      "eval_steps_per_second": 0.567,
      "step": 410
    },
    {
      "epoch": 0.27709054923305293,
      "grad_norm": 0.490032821893692,
      "learning_rate": 4.016874541452678e-05,
      "loss": 0.3986,
      "step": 420
    },
    {
      "epoch": 0.27709054923305293,
      "eval_loss": 0.4038483202457428,
      "eval_runtime": 282.2547,
      "eval_samples_per_second": 18.09,
      "eval_steps_per_second": 0.567,
      "step": 420
    },
    {
      "epoch": 0.28368794326241137,
      "grad_norm": 0.4884147644042969,
      "learning_rate": 3.980190755685987e-05,
      "loss": 0.4003,
      "step": 430
    },
    {
      "epoch": 0.28368794326241137,
      "eval_loss": 0.40054452419281006,
      "eval_runtime": 282.2046,
      "eval_samples_per_second": 18.093,
      "eval_steps_per_second": 0.567,
      "step": 430
    },
    {
      "epoch": 0.29028533729176975,
      "grad_norm": 0.5234985947608948,
      "learning_rate": 3.943506969919296e-05,
      "loss": 0.4005,
      "step": 440
    },
    {
      "epoch": 0.29028533729176975,
      "eval_loss": 0.39862698316574097,
      "eval_runtime": 282.1876,
      "eval_samples_per_second": 18.094,
      "eval_steps_per_second": 0.567,
      "step": 440
    },
    {
      "epoch": 0.29688273132112813,
      "grad_norm": 0.512843668460846,
      "learning_rate": 3.9068231841526045e-05,
      "loss": 0.3952,
      "step": 450
    },
    {
      "epoch": 0.29688273132112813,
      "eval_loss": 0.3970402181148529,
      "eval_runtime": 282.2615,
      "eval_samples_per_second": 18.09,
      "eval_steps_per_second": 0.567,
      "step": 450
    },
    {
      "epoch": 0.3034801253504866,
      "grad_norm": 0.46752044558525085,
      "learning_rate": 3.8701393983859135e-05,
      "loss": 0.3967,
      "step": 460
    },
    {
      "epoch": 0.3034801253504866,
      "eval_loss": 0.39410126209259033,
      "eval_runtime": 282.2669,
      "eval_samples_per_second": 18.089,
      "eval_steps_per_second": 0.567,
      "step": 460
    },
    {
      "epoch": 0.31007751937984496,
      "grad_norm": 0.49608954787254333,
      "learning_rate": 3.8334556126192226e-05,
      "loss": 0.3893,
      "step": 470
    },
    {
      "epoch": 0.31007751937984496,
      "eval_loss": 0.3944699168205261,
      "eval_runtime": 282.3461,
      "eval_samples_per_second": 18.084,
      "eval_steps_per_second": 0.567,
      "step": 470
    },
    {
      "epoch": 0.31667491340920334,
      "grad_norm": 0.4948144853115082,
      "learning_rate": 3.7967718268525316e-05,
      "loss": 0.3883,
      "step": 480
    },
    {
      "epoch": 0.31667491340920334,
      "eval_loss": 0.3926471471786499,
      "eval_runtime": 282.4921,
      "eval_samples_per_second": 18.075,
      "eval_steps_per_second": 0.566,
      "step": 480
    },
    {
      "epoch": 0.3232723074385618,
      "grad_norm": 0.5696155428886414,
      "learning_rate": 3.76008804108584e-05,
      "loss": 0.3921,
      "step": 490
    },
    {
      "epoch": 0.3232723074385618,
      "eval_loss": 0.39166340231895447,
      "eval_runtime": 282.2989,
      "eval_samples_per_second": 18.087,
      "eval_steps_per_second": 0.567,
      "step": 490
    },
    {
      "epoch": 0.32986970146792016,
      "grad_norm": 0.5400599241256714,
      "learning_rate": 3.723404255319149e-05,
      "loss": 0.3927,
      "step": 500
    },
    {
      "epoch": 0.32986970146792016,
      "eval_loss": 0.3899206817150116,
      "eval_runtime": 282.6164,
      "eval_samples_per_second": 18.067,
      "eval_steps_per_second": 0.566,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1515,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1763083231772672e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}