{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 1722,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04065040650406504,
      "grad_norm": 14.707608222961426,
      "learning_rate": 9.000000000000001e-07,
      "loss": 0.9613,
      "step": 10
    },
    {
      "epoch": 0.08130081300813008,
      "grad_norm": 12.035386085510254,
      "learning_rate": 1.9000000000000002e-06,
      "loss": 0.8509,
      "step": 20
    },
    {
      "epoch": 0.12195121951219512,
      "grad_norm": 18.44657325744629,
      "learning_rate": 2.9e-06,
      "loss": 0.9369,
      "step": 30
    },
    {
      "epoch": 0.16260162601626016,
      "grad_norm": 12.941998481750488,
      "learning_rate": 3.900000000000001e-06,
      "loss": 0.896,
      "step": 40
    },
    {
      "epoch": 0.2032520325203252,
      "grad_norm": 15.150432586669922,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.9821,
      "step": 50
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 18.638032913208008,
      "learning_rate": 5.9e-06,
      "loss": 0.9666,
      "step": 60
    },
    {
      "epoch": 0.2845528455284553,
      "grad_norm": 15.954939842224121,
      "learning_rate": 6.9e-06,
      "loss": 0.9019,
      "step": 70
    },
    {
      "epoch": 0.3252032520325203,
      "grad_norm": 11.114273071289062,
      "learning_rate": 7.9e-06,
      "loss": 0.8321,
      "step": 80
    },
    {
      "epoch": 0.36585365853658536,
      "grad_norm": 15.285880088806152,
      "learning_rate": 8.900000000000001e-06,
      "loss": 0.7198,
      "step": 90
    },
    {
      "epoch": 0.4065040650406504,
      "grad_norm": 17.8586483001709,
      "learning_rate": 9.9e-06,
      "loss": 0.7806,
      "step": 100
    },
    {
      "epoch": 0.44715447154471544,
      "grad_norm": 11.217978477478027,
      "learning_rate": 9.961864406779662e-06,
      "loss": 1.0024,
      "step": 110
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 7.002477169036865,
      "learning_rate": 9.91949152542373e-06,
      "loss": 0.8086,
      "step": 120
    },
    {
      "epoch": 0.5284552845528455,
      "grad_norm": 13.211562156677246,
      "learning_rate": 9.877118644067798e-06,
      "loss": 0.8958,
      "step": 130
    },
    {
      "epoch": 0.5691056910569106,
      "grad_norm": 11.169763565063477,
      "learning_rate": 9.834745762711865e-06,
      "loss": 0.8316,
      "step": 140
    },
    {
      "epoch": 0.6097560975609756,
      "grad_norm": 15.369425773620605,
      "learning_rate": 9.792372881355933e-06,
      "loss": 0.675,
      "step": 150
    },
    {
      "epoch": 0.6504065040650406,
      "grad_norm": 11.003032684326172,
      "learning_rate": 9.75e-06,
      "loss": 0.7512,
      "step": 160
    },
    {
      "epoch": 0.6910569105691057,
      "grad_norm": 16.466957092285156,
      "learning_rate": 9.707627118644068e-06,
      "loss": 0.8546,
      "step": 170
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 13.067832946777344,
      "learning_rate": 9.665254237288136e-06,
      "loss": 0.7497,
      "step": 180
    },
    {
      "epoch": 0.7723577235772358,
      "grad_norm": 9.530882835388184,
      "learning_rate": 9.622881355932205e-06,
      "loss": 0.6136,
      "step": 190
    },
    {
      "epoch": 0.8130081300813008,
      "grad_norm": 15.063409805297852,
      "learning_rate": 9.580508474576273e-06,
      "loss": 0.6073,
      "step": 200
    },
    {
      "epoch": 0.8536585365853658,
      "grad_norm": 9.07528305053711,
      "learning_rate": 9.53813559322034e-06,
      "loss": 0.7295,
      "step": 210
    },
    {
      "epoch": 0.8943089430894309,
      "grad_norm": 14.199564933776855,
      "learning_rate": 9.495762711864408e-06,
      "loss": 0.596,
      "step": 220
    },
    {
      "epoch": 0.9349593495934959,
      "grad_norm": 16.03732681274414,
      "learning_rate": 9.453389830508474e-06,
      "loss": 0.6922,
      "step": 230
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 17.533695220947266,
      "learning_rate": 9.411016949152543e-06,
      "loss": 0.7484,
      "step": 240
    },
    {
      "epoch": 1.0,
      "eval_general_loss": 0.754059910774231,
      "eval_general_runtime": 254.3068,
      "eval_general_samples_per_second": 3.598,
      "eval_general_steps_per_second": 0.9,
      "step": 246
    },
    {
      "epoch": 1.0,
      "eval_code_loss": 0.7234187722206116,
      "eval_code_runtime": 296.8568,
      "eval_code_samples_per_second": 3.092,
      "eval_code_steps_per_second": 0.775,
      "step": 246
    },
    {
      "epoch": 1.0,
      "eval_stem_loss": 0.7939386367797852,
      "eval_stem_runtime": 250.6578,
      "eval_stem_samples_per_second": 3.646,
      "eval_stem_steps_per_second": 0.914,
      "step": 246
    },
    {
      "epoch": 1.016260162601626,
      "grad_norm": 16.589147567749023,
      "learning_rate": 9.368644067796611e-06,
      "loss": 0.7309,
      "step": 250
    },
    {
      "epoch": 1.056910569105691,
      "grad_norm": 8.124390602111816,
      "learning_rate": 9.32627118644068e-06,
      "loss": 0.5937,
      "step": 260
    },
    {
      "epoch": 1.0975609756097562,
      "grad_norm": 13.223992347717285,
      "learning_rate": 9.283898305084746e-06,
      "loss": 0.6961,
      "step": 270
    },
    {
      "epoch": 1.1382113821138211,
      "grad_norm": 13.791741371154785,
      "learning_rate": 9.241525423728814e-06,
      "loss": 0.5783,
      "step": 280
    },
    {
      "epoch": 1.1788617886178863,
      "grad_norm": 16.130605697631836,
      "learning_rate": 9.199152542372882e-06,
      "loss": 0.6318,
      "step": 290
    },
    {
      "epoch": 1.2195121951219512,
      "grad_norm": 14.941628456115723,
      "learning_rate": 9.15677966101695e-06,
      "loss": 0.6163,
      "step": 300
    },
    {
      "epoch": 1.2601626016260163,
      "grad_norm": 6.407144546508789,
      "learning_rate": 9.114406779661017e-06,
      "loss": 0.5745,
      "step": 310
    },
    {
      "epoch": 1.3008130081300813,
      "grad_norm": 7.032970905303955,
      "learning_rate": 9.072033898305086e-06,
      "loss": 0.474,
      "step": 320
    },
    {
      "epoch": 1.3414634146341464,
      "grad_norm": 14.255295753479004,
      "learning_rate": 9.029661016949152e-06,
      "loss": 0.6833,
      "step": 330
    },
    {
      "epoch": 1.3821138211382114,
      "grad_norm": 19.13692855834961,
      "learning_rate": 8.98728813559322e-06,
      "loss": 0.5369,
      "step": 340
    },
    {
      "epoch": 1.4227642276422765,
      "grad_norm": 9.524161338806152,
      "learning_rate": 8.944915254237289e-06,
      "loss": 0.6925,
      "step": 350
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 12.59819221496582,
      "learning_rate": 8.902542372881357e-06,
      "loss": 0.572,
      "step": 360
    },
    {
      "epoch": 1.5040650406504064,
      "grad_norm": 7.560878753662109,
      "learning_rate": 8.860169491525424e-06,
      "loss": 0.5101,
      "step": 370
    },
    {
      "epoch": 1.5447154471544715,
      "grad_norm": 10.911989212036133,
      "learning_rate": 8.817796610169492e-06,
      "loss": 0.7357,
      "step": 380
    },
    {
      "epoch": 1.5853658536585367,
      "grad_norm": 13.019627571105957,
      "learning_rate": 8.77542372881356e-06,
      "loss": 0.7094,
      "step": 390
    },
    {
      "epoch": 1.6260162601626016,
      "grad_norm": 5.221607685089111,
      "learning_rate": 8.733050847457629e-06,
      "loss": 0.5762,
      "step": 400
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 9.154648780822754,
      "learning_rate": 8.690677966101695e-06,
      "loss": 0.6516,
      "step": 410
    },
    {
      "epoch": 1.7073170731707317,
      "grad_norm": 8.04185962677002,
      "learning_rate": 8.648305084745763e-06,
      "loss": 0.5457,
      "step": 420
    },
    {
      "epoch": 1.7479674796747968,
      "grad_norm": 12.428257942199707,
      "learning_rate": 8.60593220338983e-06,
      "loss": 0.6458,
      "step": 430
    },
    {
      "epoch": 1.7886178861788617,
      "grad_norm": 6.699453353881836,
      "learning_rate": 8.563559322033898e-06,
      "loss": 0.6026,
      "step": 440
    },
    {
      "epoch": 1.8292682926829267,
      "grad_norm": 5.6174774169921875,
      "learning_rate": 8.521186440677967e-06,
      "loss": 0.6756,
      "step": 450
    },
    {
      "epoch": 1.8699186991869918,
      "grad_norm": 12.72862720489502,
      "learning_rate": 8.478813559322035e-06,
      "loss": 0.5932,
      "step": 460
    },
    {
      "epoch": 1.910569105691057,
      "grad_norm": 4.651763439178467,
      "learning_rate": 8.436440677966102e-06,
      "loss": 0.418,
      "step": 470
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 16.044872283935547,
      "learning_rate": 8.39406779661017e-06,
      "loss": 0.5756,
      "step": 480
    },
    {
      "epoch": 1.9918699186991868,
      "grad_norm": 10.388751029968262,
      "learning_rate": 8.351694915254238e-06,
      "loss": 0.6304,
      "step": 490
    },
    {
      "epoch": 2.0,
      "eval_general_loss": 0.6887519359588623,
      "eval_general_runtime": 255.0576,
      "eval_general_samples_per_second": 3.587,
      "eval_general_steps_per_second": 0.898,
      "step": 492
    },
    {
      "epoch": 2.0,
      "eval_code_loss": 0.5912412405014038,
      "eval_code_runtime": 297.8316,
      "eval_code_samples_per_second": 3.082,
      "eval_code_steps_per_second": 0.772,
      "step": 492
    },
    {
      "epoch": 2.0,
      "eval_stem_loss": 0.7283160090446472,
      "eval_stem_runtime": 251.4929,
      "eval_stem_samples_per_second": 3.634,
      "eval_stem_steps_per_second": 0.911,
      "step": 492
    },
    {
      "epoch": 2.032520325203252,
      "grad_norm": 13.620870590209961,
      "learning_rate": 8.309322033898306e-06,
      "loss": 0.5292,
      "step": 500
    },
    {
      "epoch": 2.073170731707317,
      "grad_norm": 11.176264762878418,
      "learning_rate": 8.266949152542375e-06,
      "loss": 0.4926,
      "step": 510
    },
    {
      "epoch": 2.113821138211382,
      "grad_norm": 4.5993852615356445,
      "learning_rate": 8.224576271186441e-06,
      "loss": 0.476,
      "step": 520
    },
    {
      "epoch": 2.154471544715447,
      "grad_norm": 16.03154182434082,
      "learning_rate": 8.182203389830508e-06,
      "loss": 0.492,
      "step": 530
    },
    {
      "epoch": 2.1951219512195124,
      "grad_norm": 3.7860374450683594,
      "learning_rate": 8.139830508474576e-06,
      "loss": 0.4376,
      "step": 540
    },
    {
      "epoch": 2.2357723577235773,
      "grad_norm": 14.141989707946777,
      "learning_rate": 8.097457627118644e-06,
      "loss": 0.5422,
      "step": 550
    },
    {
      "epoch": 2.2764227642276422,
      "grad_norm": 11.716277122497559,
      "learning_rate": 8.055084745762713e-06,
      "loss": 0.4781,
      "step": 560
    },
    {
      "epoch": 2.317073170731707,
      "grad_norm": 16.112192153930664,
      "learning_rate": 8.012711864406781e-06,
      "loss": 0.5243,
      "step": 570
    },
    {
      "epoch": 2.3577235772357725,
      "grad_norm": 5.857080936431885,
      "learning_rate": 7.970338983050848e-06,
      "loss": 0.4588,
      "step": 580
    },
    {
      "epoch": 2.3983739837398375,
      "grad_norm": 9.052570343017578,
      "learning_rate": 7.927966101694916e-06,
      "loss": 0.5717,
      "step": 590
    },
    {
      "epoch": 2.4390243902439024,
      "grad_norm": 17.8330078125,
      "learning_rate": 7.885593220338984e-06,
      "loss": 0.4547,
      "step": 600
    },
    {
      "epoch": 2.4796747967479673,
      "grad_norm": 13.779817581176758,
      "learning_rate": 7.843220338983052e-06,
      "loss": 0.4584,
      "step": 610
    },
    {
      "epoch": 2.5203252032520327,
      "grad_norm": 18.924348831176758,
      "learning_rate": 7.800847457627119e-06,
      "loss": 0.4788,
      "step": 620
    },
    {
      "epoch": 2.5609756097560976,
      "grad_norm": 12.157154083251953,
      "learning_rate": 7.758474576271187e-06,
      "loss": 0.4762,
      "step": 630
    },
    {
      "epoch": 2.6016260162601625,
      "grad_norm": 14.143574714660645,
      "learning_rate": 7.716101694915254e-06,
      "loss": 0.7017,
      "step": 640
    },
    {
      "epoch": 2.642276422764228,
      "grad_norm": 11.326656341552734,
      "learning_rate": 7.673728813559322e-06,
      "loss": 0.4524,
      "step": 650
    },
    {
      "epoch": 2.682926829268293,
      "grad_norm": 5.236691474914551,
      "learning_rate": 7.63135593220339e-06,
      "loss": 0.5228,
      "step": 660
    },
    {
      "epoch": 2.7235772357723578,
      "grad_norm": 17.48626708984375,
      "learning_rate": 7.588983050847458e-06,
      "loss": 0.4414,
      "step": 670
    },
    {
      "epoch": 2.7642276422764227,
      "grad_norm": 13.257789611816406,
      "learning_rate": 7.546610169491526e-06,
      "loss": 0.5442,
      "step": 680
    },
    {
      "epoch": 2.8048780487804876,
      "grad_norm": 20.655475616455078,
      "learning_rate": 7.504237288135594e-06,
      "loss": 0.5451,
      "step": 690
    },
    {
      "epoch": 2.845528455284553,
      "grad_norm": 10.467672348022461,
      "learning_rate": 7.461864406779662e-06,
      "loss": 0.4601,
      "step": 700
    },
    {
      "epoch": 2.886178861788618,
      "grad_norm": 13.194644927978516,
      "learning_rate": 7.41949152542373e-06,
      "loss": 0.502,
      "step": 710
    },
    {
      "epoch": 2.926829268292683,
      "grad_norm": 9.131794929504395,
      "learning_rate": 7.377118644067798e-06,
      "loss": 0.5583,
      "step": 720
    },
    {
      "epoch": 2.9674796747967482,
      "grad_norm": 8.837148666381836,
      "learning_rate": 7.334745762711864e-06,
      "loss": 0.4668,
      "step": 730
    },
    {
      "epoch": 3.0,
      "eval_general_loss": 0.6758893728256226,
      "eval_general_runtime": 255.2921,
      "eval_general_samples_per_second": 3.584,
      "eval_general_steps_per_second": 0.897,
      "step": 738
    },
    {
      "epoch": 3.0,
      "eval_code_loss": 0.5598136782646179,
      "eval_code_runtime": 297.7838,
      "eval_code_samples_per_second": 3.083,
      "eval_code_steps_per_second": 0.772,
      "step": 738
    },
    {
      "epoch": 3.0,
      "eval_stem_loss": 0.7172386050224304,
      "eval_stem_runtime": 251.2967,
      "eval_stem_samples_per_second": 3.637,
      "eval_stem_steps_per_second": 0.911,
      "step": 738
    },
    {
      "epoch": 3.008130081300813,
      "grad_norm": 8.791101455688477,
      "learning_rate": 7.292372881355933e-06,
      "loss": 0.3545,
      "step": 740
    },
    {
      "epoch": 3.048780487804878,
      "grad_norm": 7.602899074554443,
      "learning_rate": 7.25e-06,
      "loss": 0.4633,
      "step": 750
    },
    {
      "epoch": 3.089430894308943,
      "grad_norm": 10.939055442810059,
      "learning_rate": 7.207627118644068e-06,
      "loss": 0.3989,
      "step": 760
    },
    {
      "epoch": 3.130081300813008,
      "grad_norm": 9.168066024780273,
      "learning_rate": 7.165254237288136e-06,
      "loss": 0.5555,
      "step": 770
    },
    {
      "epoch": 3.1707317073170733,
      "grad_norm": 17.25099754333496,
      "learning_rate": 7.122881355932204e-06,
      "loss": 0.5326,
      "step": 780
    },
    {
      "epoch": 3.2113821138211383,
      "grad_norm": 13.0396146774292,
      "learning_rate": 7.080508474576272e-06,
      "loss": 0.3831,
      "step": 790
    },
    {
      "epoch": 3.252032520325203,
      "grad_norm": 11.217447280883789,
      "learning_rate": 7.03813559322034e-06,
      "loss": 0.4142,
      "step": 800
    },
    {
      "epoch": 3.292682926829268,
      "grad_norm": 8.102045059204102,
      "learning_rate": 6.995762711864408e-06,
      "loss": 0.4414,
      "step": 810
    },
    {
      "epoch": 3.3333333333333335,
      "grad_norm": 11.761209487915039,
      "learning_rate": 6.953389830508475e-06,
      "loss": 0.501,
      "step": 820
    },
    {
      "epoch": 3.3739837398373984,
      "grad_norm": 7.058698654174805,
      "learning_rate": 6.911016949152542e-06,
      "loss": 0.3771,
      "step": 830
    },
    {
      "epoch": 3.4146341463414633,
      "grad_norm": 7.728908061981201,
      "learning_rate": 6.86864406779661e-06,
      "loss": 0.3867,
      "step": 840
    },
    {
      "epoch": 3.4552845528455283,
      "grad_norm": 12.833827018737793,
      "learning_rate": 6.826271186440679e-06,
      "loss": 0.4132,
      "step": 850
    },
    {
      "epoch": 3.4959349593495936,
      "grad_norm": 9.884450912475586,
      "learning_rate": 6.783898305084746e-06,
      "loss": 0.3674,
      "step": 860
    },
    {
      "epoch": 3.5365853658536586,
      "grad_norm": 10.731056213378906,
      "learning_rate": 6.741525423728814e-06,
      "loss": 0.422,
      "step": 870
    },
    {
      "epoch": 3.5772357723577235,
      "grad_norm": 6.745728015899658,
      "learning_rate": 6.699152542372882e-06,
      "loss": 0.499,
      "step": 880
    },
    {
      "epoch": 3.617886178861789,
      "grad_norm": 9.808424949645996,
      "learning_rate": 6.65677966101695e-06,
      "loss": 0.2978,
      "step": 890
    },
    {
      "epoch": 3.658536585365854,
      "grad_norm": 8.444202423095703,
      "learning_rate": 6.614406779661018e-06,
      "loss": 0.3698,
      "step": 900
    },
    {
      "epoch": 3.6991869918699187,
      "grad_norm": 10.285717964172363,
      "learning_rate": 6.572033898305086e-06,
      "loss": 0.4677,
      "step": 910
    },
    {
      "epoch": 3.7398373983739837,
      "grad_norm": 6.763285160064697,
      "learning_rate": 6.5296610169491525e-06,
      "loss": 0.4449,
      "step": 920
    },
    {
      "epoch": 3.7804878048780486,
      "grad_norm": 20.608469009399414,
      "learning_rate": 6.487288135593221e-06,
      "loss": 0.5297,
      "step": 930
    },
    {
      "epoch": 3.821138211382114,
      "grad_norm": 9.06677532196045,
      "learning_rate": 6.444915254237288e-06,
      "loss": 0.4292,
      "step": 940
    },
    {
      "epoch": 3.861788617886179,
      "grad_norm": 6.93435525894165,
      "learning_rate": 6.4025423728813565e-06,
      "loss": 0.3877,
      "step": 950
    },
    {
      "epoch": 3.902439024390244,
      "grad_norm": 11.75598430633545,
      "learning_rate": 6.360169491525424e-06,
      "loss": 0.4032,
      "step": 960
    },
    {
      "epoch": 3.943089430894309,
      "grad_norm": 6.338623046875,
      "learning_rate": 6.317796610169492e-06,
      "loss": 0.4228,
      "step": 970
    },
    {
      "epoch": 3.983739837398374,
      "grad_norm": 6.302221775054932,
      "learning_rate": 6.27542372881356e-06,
      "loss": 0.4054,
      "step": 980
    },
    {
      "epoch": 4.0,
      "eval_general_loss": 0.6872960329055786,
      "eval_general_runtime": 254.991,
      "eval_general_samples_per_second": 3.588,
      "eval_general_steps_per_second": 0.898,
      "step": 984
    },
    {
      "epoch": 4.0,
      "eval_code_loss": 0.5443978309631348,
      "eval_code_runtime": 297.6318,
      "eval_code_samples_per_second": 3.084,
      "eval_code_steps_per_second": 0.773,
      "step": 984
    },
    {
      "epoch": 4.0,
      "eval_stem_loss": 0.7525980472564697,
      "eval_stem_runtime": 251.3515,
      "eval_stem_samples_per_second": 3.636,
      "eval_stem_steps_per_second": 0.911,
      "step": 984
    },
    {
      "epoch": 4.024390243902439,
      "grad_norm": 11.085492134094238,
      "learning_rate": 6.233050847457628e-06,
      "loss": 0.2924,
      "step": 990
    },
    {
      "epoch": 4.065040650406504,
      "grad_norm": 9.018081665039062,
      "learning_rate": 6.190677966101695e-06,
      "loss": 0.3824,
      "step": 1000
    },
    {
      "epoch": 4.105691056910569,
      "grad_norm": 5.635726451873779,
      "learning_rate": 6.148305084745764e-06,
      "loss": 0.3209,
      "step": 1010
    },
    {
      "epoch": 4.146341463414634,
      "grad_norm": 17.105005264282227,
      "learning_rate": 6.10593220338983e-06,
      "loss": 0.3092,
      "step": 1020
    },
    {
      "epoch": 4.186991869918699,
      "grad_norm": 9.317548751831055,
      "learning_rate": 6.0635593220338986e-06,
      "loss": 0.3398,
      "step": 1030
    },
    {
      "epoch": 4.227642276422764,
      "grad_norm": 12.000333786010742,
      "learning_rate": 6.021186440677966e-06,
      "loss": 0.3214,
      "step": 1040
    },
    {
      "epoch": 4.2682926829268295,
      "grad_norm": 18.374374389648438,
      "learning_rate": 5.978813559322034e-06,
      "loss": 0.4008,
      "step": 1050
    },
    {
      "epoch": 4.308943089430894,
      "grad_norm": 8.767024993896484,
      "learning_rate": 5.936440677966102e-06,
      "loss": 0.4476,
      "step": 1060
    },
    {
      "epoch": 4.349593495934959,
      "grad_norm": 12.842947006225586,
      "learning_rate": 5.89406779661017e-06,
      "loss": 0.3627,
      "step": 1070
    },
    {
      "epoch": 4.390243902439025,
      "grad_norm": 11.248525619506836,
      "learning_rate": 5.851694915254238e-06,
      "loss": 0.3427,
      "step": 1080
    },
    {
      "epoch": 4.430894308943089,
      "grad_norm": 18.474157333374023,
      "learning_rate": 5.809322033898306e-06,
      "loss": 0.2842,
      "step": 1090
    },
    {
      "epoch": 4.471544715447155,
      "grad_norm": 10.508559226989746,
      "learning_rate": 5.766949152542374e-06,
      "loss": 0.4153,
      "step": 1100
    },
    {
      "epoch": 4.512195121951219,
      "grad_norm": 20.686229705810547,
      "learning_rate": 5.7245762711864415e-06,
      "loss": 0.3661,
      "step": 1110
    },
    {
      "epoch": 4.5528455284552845,
      "grad_norm": 7.763411998748779,
      "learning_rate": 5.682203389830508e-06,
      "loss": 0.3325,
      "step": 1120
    },
    {
      "epoch": 4.59349593495935,
      "grad_norm": 6.85905647277832,
      "learning_rate": 5.639830508474576e-06,
      "loss": 0.4229,
      "step": 1130
    },
    {
      "epoch": 4.634146341463414,
      "grad_norm": 17.94886589050293,
      "learning_rate": 5.597457627118645e-06,
      "loss": 0.3009,
      "step": 1140
    },
    {
      "epoch": 4.67479674796748,
      "grad_norm": 20.208101272583008,
      "learning_rate": 5.555084745762712e-06,
      "loss": 0.3604,
      "step": 1150
    },
    {
      "epoch": 4.715447154471545,
      "grad_norm": 8.471419334411621,
      "learning_rate": 5.51271186440678e-06,
      "loss": 0.3724,
      "step": 1160
    },
    {
      "epoch": 4.7560975609756095,
      "grad_norm": 9.207096099853516,
      "learning_rate": 5.470338983050848e-06,
      "loss": 0.3979,
      "step": 1170
    },
    {
      "epoch": 4.796747967479675,
      "grad_norm": 18.151241302490234,
      "learning_rate": 5.427966101694916e-06,
      "loss": 0.3412,
      "step": 1180
    },
    {
      "epoch": 4.83739837398374,
      "grad_norm": 11.33778190612793,
      "learning_rate": 5.3855932203389836e-06,
      "loss": 0.3582,
      "step": 1190
    },
    {
      "epoch": 4.878048780487805,
      "grad_norm": 3.6720833778381348,
      "learning_rate": 5.343220338983052e-06,
      "loss": 0.3269,
      "step": 1200
    },
    {
      "epoch": 4.91869918699187,
      "grad_norm": 15.8824462890625,
      "learning_rate": 5.300847457627119e-06,
      "loss": 0.4141,
      "step": 1210
    },
    {
      "epoch": 4.959349593495935,
      "grad_norm": 8.455586433410645,
      "learning_rate": 5.258474576271187e-06,
      "loss": 0.3515,
      "step": 1220
    },
    {
      "epoch": 5.0,
      "grad_norm": 13.756336212158203,
      "learning_rate": 5.216101694915254e-06,
      "loss": 0.3621,
      "step": 1230
    },
    {
      "epoch": 5.0,
      "eval_general_loss": 0.7001935839653015,
      "eval_general_runtime": 255.6611,
      "eval_general_samples_per_second": 3.579,
      "eval_general_steps_per_second": 0.896,
      "step": 1230
    },
    {
      "epoch": 5.0,
      "eval_code_loss": 0.5433691740036011,
      "eval_code_runtime": 297.6204,
      "eval_code_samples_per_second": 3.084,
      "eval_code_steps_per_second": 0.773,
      "step": 1230
    },
    {
      "epoch": 5.0,
      "eval_stem_loss": 0.8110136389732361,
      "eval_stem_runtime": 251.3377,
      "eval_stem_samples_per_second": 3.637,
      "eval_stem_steps_per_second": 0.911,
      "step": 1230
    },
    {
      "epoch": 5.040650406504065,
      "grad_norm": 8.500140190124512,
      "learning_rate": 5.1737288135593225e-06,
      "loss": 0.2453,
      "step": 1240
    },
    {
      "epoch": 5.08130081300813,
      "grad_norm": 23.405906677246094,
      "learning_rate": 5.13135593220339e-06,
      "loss": 0.2729,
      "step": 1250
    },
    {
      "epoch": 5.121951219512195,
      "grad_norm": 15.196890830993652,
      "learning_rate": 5.088983050847458e-06,
      "loss": 0.2626,
      "step": 1260
    },
    {
      "epoch": 5.16260162601626,
      "grad_norm": 12.534261703491211,
      "learning_rate": 5.046610169491526e-06,
      "loss": 0.2891,
      "step": 1270
    },
    {
      "epoch": 5.203252032520325,
      "grad_norm": 16.788536071777344,
      "learning_rate": 5.004237288135594e-06,
      "loss": 0.3668,
      "step": 1280
    },
    {
      "epoch": 5.2439024390243905,
      "grad_norm": 7.071691513061523,
      "learning_rate": 4.961864406779661e-06,
      "loss": 0.2995,
      "step": 1290
    },
    {
      "epoch": 5.284552845528455,
      "grad_norm": 23.835960388183594,
      "learning_rate": 4.919491525423729e-06,
      "loss": 0.4169,
      "step": 1300
    },
    {
      "epoch": 5.32520325203252,
      "grad_norm": 6.12783145904541,
      "learning_rate": 4.877118644067797e-06,
      "loss": 0.3055,
      "step": 1310
    },
    {
      "epoch": 5.365853658536586,
      "grad_norm": 11.301496505737305,
      "learning_rate": 4.8347457627118645e-06,
      "loss": 0.1926,
      "step": 1320
    },
    {
      "epoch": 5.40650406504065,
      "grad_norm": 11.58179759979248,
      "learning_rate": 4.792372881355933e-06,
      "loss": 0.3254,
      "step": 1330
    },
    {
      "epoch": 5.4471544715447155,
      "grad_norm": 18.70044708251953,
      "learning_rate": 4.75e-06,
      "loss": 0.3081,
      "step": 1340
    },
    {
      "epoch": 5.487804878048781,
      "grad_norm": 22.241409301757812,
      "learning_rate": 4.707627118644068e-06,
      "loss": 0.2969,
      "step": 1350
    },
    {
      "epoch": 5.528455284552845,
      "grad_norm": 17.672147750854492,
      "learning_rate": 4.665254237288136e-06,
      "loss": 0.3348,
      "step": 1360
    },
    {
      "epoch": 5.569105691056911,
      "grad_norm": 9.32618522644043,
      "learning_rate": 4.622881355932204e-06,
      "loss": 0.2523,
      "step": 1370
    },
    {
      "epoch": 5.609756097560975,
      "grad_norm": 6.630079746246338,
      "learning_rate": 4.580508474576272e-06,
      "loss": 0.2889,
      "step": 1380
    },
    {
      "epoch": 5.650406504065041,
      "grad_norm": 21.26811408996582,
      "learning_rate": 4.538135593220339e-06,
      "loss": 0.3947,
      "step": 1390
    },
    {
      "epoch": 5.691056910569106,
      "grad_norm": 20.458436965942383,
      "learning_rate": 4.4957627118644075e-06,
      "loss": 0.3509,
      "step": 1400
    },
    {
      "epoch": 5.7317073170731705,
      "grad_norm": 8.210813522338867,
      "learning_rate": 4.453389830508475e-06,
      "loss": 0.2976,
      "step": 1410
    },
    {
      "epoch": 5.772357723577236,
      "grad_norm": 16.646589279174805,
      "learning_rate": 4.411016949152543e-06,
      "loss": 0.2757,
      "step": 1420
    },
    {
      "epoch": 5.8130081300813,
      "grad_norm": 14.104079246520996,
      "learning_rate": 4.368644067796611e-06,
      "loss": 0.3213,
      "step": 1430
    },
    {
      "epoch": 5.853658536585366,
      "grad_norm": 10.447735786437988,
      "learning_rate": 4.326271186440678e-06,
      "loss": 0.2845,
      "step": 1440
    },
    {
      "epoch": 5.894308943089431,
      "grad_norm": 22.94976043701172,
      "learning_rate": 4.283898305084746e-06,
      "loss": 0.3306,
      "step": 1450
    },
    {
      "epoch": 5.934959349593496,
      "grad_norm": 8.621337890625,
      "learning_rate": 4.241525423728814e-06,
      "loss": 0.267,
      "step": 1460
    },
    {
      "epoch": 5.975609756097561,
      "grad_norm": 20.209896087646484,
      "learning_rate": 4.199152542372882e-06,
      "loss": 0.2916,
      "step": 1470
    },
    {
      "epoch": 6.0,
      "eval_general_loss": 0.7351013422012329,
      "eval_general_runtime": 254.9676,
      "eval_general_samples_per_second": 3.589,
      "eval_general_steps_per_second": 0.898,
      "step": 1476
    },
    {
      "epoch": 6.0,
      "eval_code_loss": 0.5539229512214661,
      "eval_code_runtime": 297.3043,
      "eval_code_samples_per_second": 3.088,
      "eval_code_steps_per_second": 0.774,
      "step": 1476
    },
    {
      "epoch": 6.0,
      "eval_stem_loss": 0.8781471252441406,
      "eval_stem_runtime": 250.9123,
      "eval_stem_samples_per_second": 3.643,
      "eval_stem_steps_per_second": 0.913,
      "step": 1476
    },
    {
      "epoch": 6.016260162601626,
      "grad_norm": 23.147737503051758,
      "learning_rate": 4.1567796610169495e-06,
      "loss": 0.298,
      "step": 1480
    },
    {
      "epoch": 6.056910569105691,
      "grad_norm": 13.436469078063965,
      "learning_rate": 4.114406779661017e-06,
      "loss": 0.2302,
      "step": 1490
    },
    {
      "epoch": 6.097560975609756,
      "grad_norm": 7.810673236846924,
      "learning_rate": 4.072033898305085e-06,
      "loss": 0.3332,
      "step": 1500
    },
    {
      "epoch": 6.138211382113822,
      "grad_norm": 18.086008071899414,
      "learning_rate": 4.029661016949153e-06,
      "loss": 0.2208,
      "step": 1510
    },
    {
      "epoch": 6.178861788617886,
      "grad_norm": 15.756752967834473,
      "learning_rate": 3.987288135593221e-06,
      "loss": 0.2687,
      "step": 1520
    },
    {
      "epoch": 6.219512195121951,
      "grad_norm": 4.063956260681152,
      "learning_rate": 3.9449152542372884e-06,
      "loss": 0.1873,
      "step": 1530
    },
    {
      "epoch": 6.260162601626016,
      "grad_norm": 22.55267333984375,
      "learning_rate": 3.902542372881356e-06,
      "loss": 0.309,
      "step": 1540
    },
    {
      "epoch": 6.300813008130081,
      "grad_norm": 3.895887613296509,
      "learning_rate": 3.860169491525424e-06,
      "loss": 0.2664,
      "step": 1550
    },
    {
      "epoch": 6.341463414634147,
      "grad_norm": 7.404182434082031,
      "learning_rate": 3.817796610169492e-06,
      "loss": 0.2889,
      "step": 1560
    },
    {
      "epoch": 6.382113821138211,
      "grad_norm": 9.983993530273438,
      "learning_rate": 3.77542372881356e-06,
      "loss": 0.2803,
      "step": 1570
    },
    {
      "epoch": 6.4227642276422765,
      "grad_norm": 7.133581638336182,
      "learning_rate": 3.7330508474576277e-06,
      "loss": 0.2078,
      "step": 1580
    },
    {
      "epoch": 6.463414634146342,
      "grad_norm": 4.602142333984375,
      "learning_rate": 3.690677966101695e-06,
      "loss": 0.2432,
      "step": 1590
    },
    {
      "epoch": 6.504065040650406,
      "grad_norm": 20.32489585876465,
      "learning_rate": 3.648305084745763e-06,
      "loss": 0.2643,
      "step": 1600
    },
    {
      "epoch": 6.544715447154472,
      "grad_norm": 2.3672261238098145,
      "learning_rate": 3.605932203389831e-06,
      "loss": 0.2641,
      "step": 1610
    },
    {
      "epoch": 6.585365853658536,
      "grad_norm": 3.9571468830108643,
      "learning_rate": 3.5635593220338988e-06,
      "loss": 0.2888,
      "step": 1620
    },
    {
      "epoch": 6.626016260162602,
      "grad_norm": 7.1855902671813965,
      "learning_rate": 3.5211864406779667e-06,
      "loss": 0.2808,
      "step": 1630
    },
    {
      "epoch": 6.666666666666667,
      "grad_norm": 17.62175750732422,
      "learning_rate": 3.478813559322034e-06,
      "loss": 0.1877,
      "step": 1640
    },
    {
      "epoch": 6.7073170731707314,
      "grad_norm": 23.9554443359375,
      "learning_rate": 3.436440677966102e-06,
      "loss": 0.2536,
      "step": 1650
    },
    {
      "epoch": 6.747967479674797,
      "grad_norm": 18.637380599975586,
      "learning_rate": 3.39406779661017e-06,
      "loss": 0.2285,
      "step": 1660
    },
    {
      "epoch": 6.788617886178862,
      "grad_norm": 4.296135902404785,
      "learning_rate": 3.3516949152542377e-06,
      "loss": 0.2408,
      "step": 1670
    },
    {
      "epoch": 6.829268292682927,
      "grad_norm": 13.094096183776855,
      "learning_rate": 3.309322033898305e-06,
      "loss": 0.2354,
      "step": 1680
    },
    {
      "epoch": 6.869918699186992,
      "grad_norm": 21.35910987854004,
      "learning_rate": 3.266949152542373e-06,
      "loss": 0.2929,
      "step": 1690
    },
    {
      "epoch": 6.9105691056910565,
      "grad_norm": 11.566039085388184,
      "learning_rate": 3.224576271186441e-06,
      "loss": 0.2473,
      "step": 1700
    },
    {
      "epoch": 6.951219512195122,
      "grad_norm": 33.27814865112305,
      "learning_rate": 3.1822033898305087e-06,
      "loss": 0.2745,
      "step": 1710
    },
    {
      "epoch": 6.991869918699187,
      "grad_norm": 28.20252799987793,
      "learning_rate": 3.1398305084745766e-06,
      "loss": 0.2758,
      "step": 1720
    },
    {
      "epoch": 7.0,
      "eval_general_loss": 0.7735296487808228,
      "eval_general_runtime": 254.8206,
      "eval_general_samples_per_second": 3.591,
      "eval_general_steps_per_second": 0.899,
      "step": 1722
    },
    {
      "epoch": 7.0,
      "eval_code_loss": 0.5828394889831543,
      "eval_code_runtime": 297.9571,
      "eval_code_samples_per_second": 3.081,
      "eval_code_steps_per_second": 0.772,
      "step": 1722
    },
    {
      "epoch": 7.0,
      "eval_stem_loss": 0.9436448216438293,
      "eval_stem_runtime": 251.491,
      "eval_stem_samples_per_second": 3.634,
      "eval_stem_steps_per_second": 0.911,
      "step": 1722
    }
  ],
  "logging_steps": 10,
  "max_steps": 2460,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 4.2623031165647585e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}