{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.22255605630668224,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.7622424783185124,
      "epoch": 0.004451121126133645,
      "grad_norm": 1888.0,
      "learning_rate": 1.8e-07,
      "loss": 36.8185,
      "mean_token_accuracy": 0.6663544788956642,
      "num_tokens": 63133.0,
      "step": 10
    },
    {
      "entropy": 0.8160548411309719,
      "epoch": 0.00890224225226729,
      "grad_norm": 1728.0,
      "learning_rate": 3.8e-07,
      "loss": 36.6381,
      "mean_token_accuracy": 0.649208546616137,
      "num_tokens": 128968.0,
      "step": 20
    },
    {
      "entropy": 0.8332255953922868,
      "epoch": 0.013353363378400934,
      "grad_norm": 948.0,
      "learning_rate": 5.800000000000001e-07,
      "loss": 34.7797,
      "mean_token_accuracy": 0.6578839531168341,
      "num_tokens": 193314.0,
      "step": 30
    },
    {
      "entropy": 0.9456521481275558,
      "epoch": 0.01780448450453458,
      "grad_norm": 716.0,
      "learning_rate": 7.8e-07,
      "loss": 34.1076,
      "mean_token_accuracy": 0.6613732609897852,
      "num_tokens": 257189.0,
      "step": 40
    },
    {
      "entropy": 0.9749895730987191,
      "epoch": 0.022255605630668224,
      "grad_norm": 660.0,
      "learning_rate": 9.800000000000001e-07,
      "loss": 29.937,
      "mean_token_accuracy": 0.6729008939117194,
      "num_tokens": 324224.0,
      "step": 50
    },
    {
      "entropy": 1.0305172327905894,
      "epoch": 0.026706726756801868,
      "grad_norm": 492.0,
      "learning_rate": 1.1800000000000001e-06,
      "loss": 28.3561,
      "mean_token_accuracy": 0.680633837915957,
      "num_tokens": 394654.0,
      "step": 60
    },
    {
      "entropy": 1.0123192116618156,
      "epoch": 0.031157847882935515,
      "grad_norm": 404.0,
      "learning_rate": 1.3800000000000001e-06,
      "loss": 26.0449,
      "mean_token_accuracy": 0.6903208963572979,
      "num_tokens": 461658.0,
      "step": 70
    },
    {
      "entropy": 1.024911842495203,
      "epoch": 0.03560896900906916,
      "grad_norm": 250.0,
      "learning_rate": 1.5800000000000001e-06,
      "loss": 23.6986,
      "mean_token_accuracy": 0.6996766375377774,
      "num_tokens": 528285.0,
      "step": 80
    },
    {
      "entropy": 1.0939506959170102,
      "epoch": 0.04006009013520281,
      "grad_norm": 227.0,
      "learning_rate": 1.7800000000000001e-06,
      "loss": 23.2949,
      "mean_token_accuracy": 0.6969541085883975,
      "num_tokens": 595336.0,
      "step": 90
    },
    {
      "entropy": 1.0676697574555873,
      "epoch": 0.04451121126133645,
      "grad_norm": 278.0,
      "learning_rate": 1.98e-06,
      "loss": 21.5533,
      "mean_token_accuracy": 0.7063678905367852,
      "num_tokens": 663126.0,
      "step": 100
    },
    {
      "epoch": 0.04451121126133645,
      "eval_biology_entropy": 1.5063953498601914,
      "eval_biology_loss": 1.9373619556427002,
      "eval_biology_mean_token_accuracy": 0.6030384682416916,
      "eval_biology_num_tokens": 663126.0,
      "eval_biology_runtime": 37.2317,
      "eval_biology_samples_per_second": 13.429,
      "eval_biology_steps_per_second": 13.429,
      "step": 100
    },
    {
      "epoch": 0.04451121126133645,
      "eval_chemistry_entropy": 1.0538504299521447,
      "eval_chemistry_loss": 1.2949438095092773,
      "eval_chemistry_mean_token_accuracy": 0.7114702309370041,
      "eval_chemistry_num_tokens": 663126.0,
      "eval_chemistry_runtime": 41.1049,
      "eval_chemistry_samples_per_second": 12.164,
      "eval_chemistry_steps_per_second": 12.164,
      "step": 100
    },
    {
      "epoch": 0.04451121126133645,
      "eval_math_entropy": 0.8524410739541054,
      "eval_math_loss": 1.2029013633728027,
      "eval_math_mean_token_accuracy": 0.7322385207414627,
      "eval_math_num_tokens": 663126.0,
      "eval_math_runtime": 41.5152,
      "eval_math_samples_per_second": 12.044,
      "eval_math_steps_per_second": 12.044,
      "step": 100
    },
    {
      "epoch": 0.04451121126133645,
      "eval_physics_entropy": 0.9442882173061371,
      "eval_physics_loss": 1.1572656631469727,
      "eval_physics_mean_token_accuracy": 0.7343679416179657,
      "eval_physics_num_tokens": 663126.0,
      "eval_physics_runtime": 45.8024,
      "eval_physics_samples_per_second": 10.916,
      "eval_physics_steps_per_second": 10.916,
      "step": 100
    },
    {
      "entropy": 1.0567705381661654,
      "epoch": 0.048962332387470095,
      "grad_norm": 202.0,
      "learning_rate": 2.1800000000000003e-06,
      "loss": 20.0858,
      "mean_token_accuracy": 0.7180810730904341,
      "num_tokens": 731060.0,
      "step": 110
    },
    {
      "entropy": 1.0101547280326486,
      "epoch": 0.053413453513603736,
      "grad_norm": 202.0,
      "learning_rate": 2.38e-06,
      "loss": 18.8763,
      "mean_token_accuracy": 0.7310481067746878,
      "num_tokens": 801635.0,
      "step": 120
    },
    {
      "entropy": 1.0049639470875262,
      "epoch": 0.05786457463973738,
      "grad_norm": 154.0,
      "learning_rate": 2.5800000000000003e-06,
      "loss": 19.1729,
      "mean_token_accuracy": 0.7293503576889634,
      "num_tokens": 867260.0,
      "step": 130
    },
    {
      "entropy": 1.0176106113940477,
      "epoch": 0.06231569576587103,
      "grad_norm": 144.0,
      "learning_rate": 2.7800000000000005e-06,
      "loss": 18.97,
      "mean_token_accuracy": 0.7298020845279097,
      "num_tokens": 931344.0,
      "step": 140
    },
    {
      "entropy": 1.0698495015501976,
      "epoch": 0.06676681689200467,
      "grad_norm": 169.0,
      "learning_rate": 2.9800000000000003e-06,
      "loss": 17.4943,
      "mean_token_accuracy": 0.7370716020464897,
      "num_tokens": 993586.0,
      "step": 150
    },
    {
      "entropy": 1.0634983357042074,
      "epoch": 0.07121793801813832,
      "grad_norm": 123.0,
      "learning_rate": 3.1800000000000005e-06,
      "loss": 16.9373,
      "mean_token_accuracy": 0.7367568526417017,
      "num_tokens": 1060812.0,
      "step": 160
    },
    {
      "entropy": 1.0108168195933103,
      "epoch": 0.07566905914427197,
      "grad_norm": 125.0,
      "learning_rate": 3.3800000000000007e-06,
      "loss": 15.569,
      "mean_token_accuracy": 0.7519758876413107,
      "num_tokens": 1131832.0,
      "step": 170
    },
    {
      "entropy": 0.9829567475244403,
      "epoch": 0.08012018027040561,
      "grad_norm": 99.0,
      "learning_rate": 3.58e-06,
      "loss": 15.2082,
      "mean_token_accuracy": 0.7475447814911604,
      "num_tokens": 1200650.0,
      "step": 180
    },
    {
      "entropy": 0.9538513226434588,
      "epoch": 0.08457130139653925,
      "grad_norm": 119.0,
      "learning_rate": 3.7800000000000002e-06,
      "loss": 15.0014,
      "mean_token_accuracy": 0.7515964422374963,
      "num_tokens": 1265107.0,
      "step": 190
    },
    {
      "entropy": 0.9125228714197874,
      "epoch": 0.0890224225226729,
      "grad_norm": 117.0,
      "learning_rate": 3.980000000000001e-06,
      "loss": 14.4833,
      "mean_token_accuracy": 0.7538308618590236,
      "num_tokens": 1327380.0,
      "step": 200
    },
    {
      "epoch": 0.0890224225226729,
      "eval_biology_entropy": 1.280277446448803,
      "eval_biology_loss": 1.453066349029541,
      "eval_biology_mean_token_accuracy": 0.6518876985907555,
      "eval_biology_num_tokens": 1327380.0,
      "eval_biology_runtime": 36.821,
      "eval_biology_samples_per_second": 13.579,
      "eval_biology_steps_per_second": 13.579,
      "step": 200
    },
    {
      "epoch": 0.0890224225226729,
      "eval_chemistry_entropy": 0.8954760466217995,
      "eval_chemistry_loss": 0.9106767177581787,
      "eval_chemistry_mean_token_accuracy": 0.7551076735854149,
      "eval_chemistry_num_tokens": 1327380.0,
      "eval_chemistry_runtime": 40.4689,
      "eval_chemistry_samples_per_second": 12.355,
      "eval_chemistry_steps_per_second": 12.355,
      "step": 200
    },
    {
      "epoch": 0.0890224225226729,
      "eval_math_entropy": 0.7658050524294376,
      "eval_math_loss": 0.9040815234184265,
      "eval_math_mean_token_accuracy": 0.7642563463449478,
      "eval_math_num_tokens": 1327380.0,
      "eval_math_runtime": 41.4556,
      "eval_math_samples_per_second": 12.061,
      "eval_math_steps_per_second": 12.061,
      "step": 200
    },
    {
      "epoch": 0.0890224225226729,
      "eval_physics_entropy": 0.8174435417056084,
      "eval_physics_loss": 0.8484614491462708,
      "eval_physics_mean_token_accuracy": 0.7708570960760116,
      "eval_physics_num_tokens": 1327380.0,
      "eval_physics_runtime": 45.875,
      "eval_physics_samples_per_second": 10.899,
      "eval_physics_steps_per_second": 10.899,
      "step": 200
    },
    {
      "entropy": 0.9408239619806409,
      "epoch": 0.09347354364880654,
      "grad_norm": 126.5,
      "learning_rate": 4.18e-06,
      "loss": 15.2387,
      "mean_token_accuracy": 0.7457781180739402,
      "num_tokens": 1393379.0,
      "step": 210
    },
    {
      "entropy": 0.8950148992240429,
      "epoch": 0.09792466477494019,
      "grad_norm": 95.0,
      "learning_rate": 4.38e-06,
      "loss": 14.2337,
      "mean_token_accuracy": 0.7587446294724941,
      "num_tokens": 1460130.0,
      "step": 220
    },
    {
      "entropy": 0.859116705879569,
      "epoch": 0.10237578590107384,
      "grad_norm": 94.0,
      "learning_rate": 4.58e-06,
      "loss": 13.7082,
      "mean_token_accuracy": 0.76347241923213,
      "num_tokens": 1529183.0,
      "step": 230
    },
    {
      "entropy": 0.8980951353907585,
      "epoch": 0.10682690702720747,
      "grad_norm": 118.5,
      "learning_rate": 4.78e-06,
      "loss": 14.5897,
      "mean_token_accuracy": 0.7553087200969457,
      "num_tokens": 1597405.0,
      "step": 240
    },
    {
      "entropy": 0.9019628280773759,
      "epoch": 0.11127802815334112,
      "grad_norm": 98.5,
      "learning_rate": 4.980000000000001e-06,
      "loss": 14.5049,
      "mean_token_accuracy": 0.7539074700325727,
      "num_tokens": 1661767.0,
      "step": 250
    },
    {
      "entropy": 0.9095736019313335,
      "epoch": 0.11572914927947477,
      "grad_norm": 80.0,
      "learning_rate": 5.18e-06,
      "loss": 14.553,
      "mean_token_accuracy": 0.7567780796438456,
      "num_tokens": 1728207.0,
      "step": 260
    },
    {
      "entropy": 0.855735239200294,
      "epoch": 0.12018027040560841,
      "grad_norm": 99.0,
      "learning_rate": 5.380000000000001e-06,
      "loss": 13.731,
      "mean_token_accuracy": 0.7652106903493404,
      "num_tokens": 1796055.0,
      "step": 270
    },
    {
      "entropy": 0.830021676234901,
      "epoch": 0.12463139153174206,
      "grad_norm": 97.5,
      "learning_rate": 5.580000000000001e-06,
      "loss": 13.2554,
      "mean_token_accuracy": 0.7721017152070999,
      "num_tokens": 1859684.0,
      "step": 280
    },
    {
      "entropy": 0.8921441739425063,
      "epoch": 0.1290825126578757,
      "grad_norm": 106.5,
      "learning_rate": 5.78e-06,
      "loss": 14.4012,
      "mean_token_accuracy": 0.7561684042215348,
      "num_tokens": 1921704.0,
      "step": 290
    },
    {
      "entropy": 0.8731818461790681,
      "epoch": 0.13353363378400934,
      "grad_norm": 87.5,
      "learning_rate": 5.98e-06,
      "loss": 13.9502,
      "mean_token_accuracy": 0.7628704030066729,
      "num_tokens": 1985766.0,
      "step": 300
    },
    {
      "epoch": 0.13353363378400934,
      "eval_biology_entropy": 1.2637426958680154,
      "eval_biology_loss": 1.3796980381011963,
      "eval_biology_mean_token_accuracy": 0.6648430502414704,
      "eval_biology_num_tokens": 1985766.0,
      "eval_biology_runtime": 37.0397,
      "eval_biology_samples_per_second": 13.499,
      "eval_biology_steps_per_second": 13.499,
      "step": 300
    },
    {
      "epoch": 0.13353363378400934,
      "eval_chemistry_entropy": 0.8489444836974144,
      "eval_chemistry_loss": 0.8385273814201355,
      "eval_chemistry_mean_token_accuracy": 0.7699487572312355,
      "eval_chemistry_num_tokens": 1985766.0,
      "eval_chemistry_runtime": 40.8665,
      "eval_chemistry_samples_per_second": 12.235,
      "eval_chemistry_steps_per_second": 12.235,
      "step": 300
    },
    {
      "epoch": 0.13353363378400934,
      "eval_math_entropy": 0.7357360773980618,
      "eval_math_loss": 0.8767910599708557,
      "eval_math_mean_token_accuracy": 0.7708948514461518,
      "eval_math_num_tokens": 1985766.0,
      "eval_math_runtime": 41.8192,
      "eval_math_samples_per_second": 11.956,
      "eval_math_steps_per_second": 11.956,
      "step": 300
    },
    {
      "epoch": 0.13353363378400934,
      "eval_physics_entropy": 0.7905060887336731,
      "eval_physics_loss": 0.7890318632125854,
      "eval_physics_mean_token_accuracy": 0.7825853993296623,
      "eval_physics_num_tokens": 1985766.0,
      "eval_physics_runtime": 46.1418,
      "eval_physics_samples_per_second": 10.836,
      "eval_physics_steps_per_second": 10.836,
      "step": 300
    },
    {
      "entropy": 0.8452363438904286,
      "epoch": 0.137984754910143,
      "grad_norm": 96.0,
      "learning_rate": 6.18e-06,
      "loss": 13.634,
      "mean_token_accuracy": 0.7645608998835087,
      "num_tokens": 2049041.0,
      "step": 310
    },
    {
      "entropy": 0.8076417898759246,
      "epoch": 0.14243587603627664,
      "grad_norm": 80.5,
      "learning_rate": 6.380000000000001e-06,
      "loss": 12.8943,
      "mean_token_accuracy": 0.7760006580501795,
      "num_tokens": 2118068.0,
      "step": 320
    },
    {
      "entropy": 0.8085115062072873,
      "epoch": 0.14688699716241027,
      "grad_norm": 106.5,
      "learning_rate": 6.5800000000000005e-06,
      "loss": 12.7928,
      "mean_token_accuracy": 0.7790838234126568,
      "num_tokens": 2186387.0,
      "step": 330
    },
    {
      "entropy": 0.824213713593781,
      "epoch": 0.15133811828854393,
      "grad_norm": 82.5,
      "learning_rate": 6.780000000000001e-06,
      "loss": 13.389,
      "mean_token_accuracy": 0.7689453203231096,
      "num_tokens": 2252650.0,
      "step": 340
    },
    {
      "entropy": 0.797634300775826,
      "epoch": 0.15578923941467757,
      "grad_norm": 85.5,
      "learning_rate": 6.98e-06,
      "loss": 12.8088,
      "mean_token_accuracy": 0.7797435287386179,
      "num_tokens": 2320358.0,
      "step": 350
    },
    {
      "entropy": 0.7920836627483367,
      "epoch": 0.16024036054081123,
      "grad_norm": 88.0,
      "learning_rate": 7.180000000000001e-06,
      "loss": 12.6336,
      "mean_token_accuracy": 0.7806293956935406,
      "num_tokens": 2388824.0,
      "step": 360
    },
    {
      "entropy": 0.7749077206477523,
      "epoch": 0.16469148166694486,
      "grad_norm": 80.5,
      "learning_rate": 7.3800000000000005e-06,
      "loss": 12.3995,
      "mean_token_accuracy": 0.7864189695566892,
      "num_tokens": 2456144.0,
      "step": 370
    },
    {
      "entropy": 0.8578483302146196,
      "epoch": 0.1691426027930785,
      "grad_norm": 81.0,
      "learning_rate": 7.58e-06,
      "loss": 13.8496,
      "mean_token_accuracy": 0.7662820883095265,
      "num_tokens": 2515325.0,
      "step": 380
    },
    {
      "entropy": 0.7971056224778295,
      "epoch": 0.17359372391921216,
      "grad_norm": 68.0,
      "learning_rate": 7.78e-06,
      "loss": 12.6922,
      "mean_token_accuracy": 0.7778837148100137,
      "num_tokens": 2580490.0,
      "step": 390
    },
    {
      "entropy": 0.7984419580549001,
      "epoch": 0.1780448450453458,
      "grad_norm": 70.5,
      "learning_rate": 7.980000000000002e-06,
      "loss": 12.8255,
      "mean_token_accuracy": 0.7773921977728605,
      "num_tokens": 2644330.0,
      "step": 400
    },
    {
      "epoch": 0.1780448450453458,
      "eval_biology_entropy": 1.2305693982243537,
      "eval_biology_loss": 1.3490314483642578,
      "eval_biology_mean_token_accuracy": 0.6716532117724419,
      "eval_biology_num_tokens": 2644330.0,
      "eval_biology_runtime": 36.6001,
      "eval_biology_samples_per_second": 13.661,
      "eval_biology_steps_per_second": 13.661,
      "step": 400
    },
    {
      "epoch": 0.1780448450453458,
      "eval_chemistry_entropy": 0.7882854393720626,
      "eval_chemistry_loss": 0.7991188764572144,
      "eval_chemistry_mean_token_accuracy": 0.778610565006733,
      "eval_chemistry_num_tokens": 2644330.0,
      "eval_chemistry_runtime": 40.3843,
      "eval_chemistry_samples_per_second": 12.381,
      "eval_chemistry_steps_per_second": 12.381,
      "step": 400
    },
    {
      "epoch": 0.1780448450453458,
      "eval_math_entropy": 0.6974474709928036,
      "eval_math_loss": 0.8647986054420471,
      "eval_math_mean_token_accuracy": 0.7742947788238526,
      "eval_math_num_tokens": 2644330.0,
      "eval_math_runtime": 41.8502,
      "eval_math_samples_per_second": 11.947,
      "eval_math_steps_per_second": 11.947,
      "step": 400
    },
    {
      "epoch": 0.1780448450453458,
      "eval_physics_entropy": 0.740912606716156,
      "eval_physics_loss": 0.7630434632301331,
      "eval_physics_mean_token_accuracy": 0.7882855938673019,
      "eval_physics_num_tokens": 2644330.0,
      "eval_physics_runtime": 46.1492,
      "eval_physics_samples_per_second": 10.834,
      "eval_physics_steps_per_second": 10.834,
      "step": 400
    },
    {
      "entropy": 0.7443430663086474,
      "epoch": 0.18249596617147945,
      "grad_norm": 72.5,
      "learning_rate": 8.18e-06,
      "loss": 11.7994,
      "mean_token_accuracy": 0.7938185524195432,
      "num_tokens": 2713234.0,
      "step": 410
    },
    {
      "entropy": 0.7856309018097818,
      "epoch": 0.18694708729761308,
      "grad_norm": 78.0,
      "learning_rate": 8.380000000000001e-06,
      "loss": 12.9567,
      "mean_token_accuracy": 0.7781453486531973,
      "num_tokens": 2783261.0,
      "step": 420
    },
    {
      "entropy": 0.799421458132565,
      "epoch": 0.19139820842374672,
      "grad_norm": 61.25,
      "learning_rate": 8.580000000000001e-06,
      "loss": 12.6392,
      "mean_token_accuracy": 0.7806750666350126,
      "num_tokens": 2850170.0,
      "step": 430
    },
    {
      "entropy": 0.7786322007887065,
      "epoch": 0.19584932954988038,
      "grad_norm": 80.5,
      "learning_rate": 8.78e-06,
      "loss": 12.4988,
      "mean_token_accuracy": 0.7827117882668972,
      "num_tokens": 2913700.0,
      "step": 440
    },
    {
      "entropy": 0.763565490860492,
      "epoch": 0.200300450676014,
      "grad_norm": 81.0,
      "learning_rate": 8.98e-06,
      "loss": 12.4779,
      "mean_token_accuracy": 0.7831043265759945,
      "num_tokens": 2981212.0,
      "step": 450
    },
    {
      "entropy": 0.7708647299557925,
      "epoch": 0.20475157180214767,
      "grad_norm": 85.0,
      "learning_rate": 9.180000000000002e-06,
      "loss": 12.1503,
      "mean_token_accuracy": 0.7912418570369482,
      "num_tokens": 3048973.0,
      "step": 460
    },
    {
      "entropy": 0.769937212113291,
      "epoch": 0.2092026929282813,
      "grad_norm": 62.0,
      "learning_rate": 9.38e-06,
      "loss": 12.6137,
      "mean_token_accuracy": 0.7829986553639173,
      "num_tokens": 3117033.0,
      "step": 470
    },
    {
      "entropy": 0.7863288868218661,
      "epoch": 0.21365381405441494,
      "grad_norm": 74.5,
      "learning_rate": 9.58e-06,
      "loss": 12.3857,
      "mean_token_accuracy": 0.7842021461576223,
      "num_tokens": 3185255.0,
      "step": 480
    },
    {
      "entropy": 0.7699232887476682,
      "epoch": 0.2181049351805486,
      "grad_norm": 74.5,
      "learning_rate": 9.780000000000001e-06,
      "loss": 12.4166,
      "mean_token_accuracy": 0.7846909243613481,
      "num_tokens": 3253121.0,
      "step": 490
    },
    {
      "entropy": 0.7251296367496252,
      "epoch": 0.22255605630668224,
      "grad_norm": 75.0,
      "learning_rate": 9.980000000000001e-06,
      "loss": 11.4498,
      "mean_token_accuracy": 0.7972834445536137,
      "num_tokens": 3322823.0,
      "step": 500
    },
    {
      "epoch": 0.22255605630668224,
      "eval_biology_entropy": 1.1898637573719024,
      "eval_biology_loss": 1.338150978088379,
      "eval_biology_mean_token_accuracy": 0.6746688461303711,
      "eval_biology_num_tokens": 3322823.0,
      "eval_biology_runtime": 37.4484,
      "eval_biology_samples_per_second": 13.352,
      "eval_biology_steps_per_second": 13.352,
      "step": 500
    },
    {
      "epoch": 0.22255605630668224,
      "eval_chemistry_entropy": 0.7506220785379409,
      "eval_chemistry_loss": 0.7758934497833252,
      "eval_chemistry_mean_token_accuracy": 0.7828538768291473,
      "eval_chemistry_num_tokens": 3322823.0,
      "eval_chemistry_runtime": 40.7375,
      "eval_chemistry_samples_per_second": 12.274,
      "eval_chemistry_steps_per_second": 12.274,
      "step": 500
    },
    {
      "epoch": 0.22255605630668224,
      "eval_math_entropy": 0.6889803909361363,
      "eval_math_loss": 0.8622512817382812,
      "eval_math_mean_token_accuracy": 0.7754237843751908,
      "eval_math_num_tokens": 3322823.0,
      "eval_math_runtime": 41.9238,
      "eval_math_samples_per_second": 11.926,
      "eval_math_steps_per_second": 11.926,
      "step": 500
    },
    {
      "epoch": 0.22255605630668224,
      "eval_physics_entropy": 0.7242196025848389,
      "eval_physics_loss": 0.7506964802742004,
      "eval_physics_mean_token_accuracy": 0.7921671935915947,
      "eval_physics_num_tokens": 3322823.0,
      "eval_physics_runtime": 45.9692,
      "eval_physics_samples_per_second": 10.877,
      "eval_physics_steps_per_second": 10.877,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 2.2280979081801686e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}