{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.4832931827753781,
      "epoch": 0.016,
      "grad_norm": 145.0,
      "learning_rate": 6.000000000000001e-07,
      "loss": 35.8107,
      "mean_token_accuracy": 0.5946215284988284,
      "num_tokens": 338352.0,
      "step": 10
    },
    {
      "entropy": 1.4921929031610488,
      "epoch": 0.032,
      "grad_norm": 139.0,
      "learning_rate": 1.2666666666666669e-06,
      "loss": 35.6429,
      "mean_token_accuracy": 0.5987227037549019,
      "num_tokens": 671193.0,
      "step": 20
    },
    {
      "entropy": 1.5176027774810792,
      "epoch": 0.048,
      "grad_norm": 120.0,
      "learning_rate": 1.9333333333333336e-06,
      "loss": 34.7928,
      "mean_token_accuracy": 0.6018522759899497,
      "num_tokens": 1001008.0,
      "step": 30
    },
    {
      "entropy": 1.6286215644329787,
      "epoch": 0.064,
      "grad_norm": 94.0,
      "learning_rate": 2.6e-06,
      "loss": 34.3313,
      "mean_token_accuracy": 0.5992800608277321,
      "num_tokens": 1331208.0,
      "step": 40
    },
    {
      "entropy": 1.6960565708577633,
      "epoch": 0.08,
      "grad_norm": 70.0,
      "learning_rate": 3.266666666666667e-06,
      "loss": 31.8029,
      "mean_token_accuracy": 0.6178880449384451,
      "num_tokens": 1667532.0,
      "step": 50
    },
    {
      "entropy": 1.6291456781327724,
      "epoch": 0.096,
      "grad_norm": 46.25,
      "learning_rate": 3.9333333333333335e-06,
      "loss": 28.5587,
      "mean_token_accuracy": 0.6474138081073761,
      "num_tokens": 2007176.0,
      "step": 60
    },
    {
      "entropy": 1.6484372481703757,
      "epoch": 0.112,
      "grad_norm": 38.75,
      "learning_rate": 4.600000000000001e-06,
      "loss": 27.1023,
      "mean_token_accuracy": 0.6544294429942965,
      "num_tokens": 2342259.0,
      "step": 70
    },
    {
      "entropy": 1.6191057547926904,
      "epoch": 0.128,
      "grad_norm": 31.625,
      "learning_rate": 5.2666666666666665e-06,
      "loss": 25.9215,
      "mean_token_accuracy": 0.6600364238023758,
      "num_tokens": 2663987.0,
      "step": 80
    },
    {
      "entropy": 1.4830621395260095,
      "epoch": 0.144,
      "grad_norm": 23.25,
      "learning_rate": 5.933333333333335e-06,
      "loss": 23.6014,
      "mean_token_accuracy": 0.6834562920033932,
      "num_tokens": 2997824.0,
      "step": 90
    },
    {
      "entropy": 1.426737917587161,
      "epoch": 0.16,
      "grad_norm": 21.25,
      "learning_rate": 6.600000000000001e-06,
      "loss": 22.4685,
      "mean_token_accuracy": 0.6952182710170746,
      "num_tokens": 3330597.0,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_biology_entropy": 3.0376483097076417,
      "eval_biology_loss": 3.875791549682617,
      "eval_biology_mean_token_accuracy": 0.41260506939888003,
      "eval_biology_num_tokens": 3330597.0,
      "eval_biology_runtime": 49.8433,
      "eval_biology_samples_per_second": 10.031,
      "eval_biology_steps_per_second": 2.508,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_chemistry_entropy": 1.7663879008293153,
      "eval_chemistry_loss": 1.816375732421875,
      "eval_chemistry_mean_token_accuracy": 0.6312954430580139,
      "eval_chemistry_num_tokens": 3330597.0,
      "eval_chemistry_runtime": 61.8081,
      "eval_chemistry_samples_per_second": 8.09,
      "eval_chemistry_steps_per_second": 2.022,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_math_entropy": 1.1983131990432738,
      "eval_math_loss": 1.485450029373169,
      "eval_math_mean_token_accuracy": 0.6917262263298035,
      "eval_math_num_tokens": 3330597.0,
      "eval_math_runtime": 63.351,
      "eval_math_samples_per_second": 7.893,
      "eval_math_steps_per_second": 1.973,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_physics_entropy": 1.4052113437652587,
      "eval_physics_loss": 1.3870269060134888,
      "eval_physics_mean_token_accuracy": 0.69519624376297,
      "eval_physics_num_tokens": 3330597.0,
      "eval_physics_runtime": 72.2152,
      "eval_physics_samples_per_second": 6.924,
      "eval_physics_steps_per_second": 1.731,
      "step": 100
    },
    {
      "entropy": 1.4028880976140499,
      "epoch": 0.176,
      "grad_norm": 23.125,
      "learning_rate": 7.266666666666668e-06,
      "loss": 21.8268,
      "mean_token_accuracy": 0.6981963120400906,
      "num_tokens": 3658264.0,
      "step": 110
    },
    {
      "entropy": 1.3301444135606288,
      "epoch": 0.192,
      "grad_norm": 17.375,
      "learning_rate": 7.933333333333334e-06,
      "loss": 20.9681,
      "mean_token_accuracy": 0.7033475987613201,
      "num_tokens": 3995568.0,
      "step": 120
    },
    {
      "entropy": 1.2701803509145975,
      "epoch": 0.208,
      "grad_norm": 18.25,
      "learning_rate": 8.6e-06,
      "loss": 19.9173,
      "mean_token_accuracy": 0.7150526810437441,
      "num_tokens": 4321436.0,
      "step": 130
    },
    {
      "entropy": 1.2350537855178119,
      "epoch": 0.224,
      "grad_norm": 16.625,
      "learning_rate": 9.266666666666667e-06,
      "loss": 19.5032,
      "mean_token_accuracy": 0.717908713966608,
      "num_tokens": 4648491.0,
      "step": 140
    },
    {
      "entropy": 1.2139144621789455,
      "epoch": 0.24,
      "grad_norm": 20.0,
      "learning_rate": 9.933333333333334e-06,
      "loss": 19.3976,
      "mean_token_accuracy": 0.7190249029546976,
      "num_tokens": 4986175.0,
      "step": 150
    },
    {
      "entropy": 1.2034844245761633,
      "epoch": 0.256,
      "grad_norm": 18.125,
      "learning_rate": 1.0600000000000002e-05,
      "loss": 19.0035,
      "mean_token_accuracy": 0.7240409322082997,
      "num_tokens": 5329320.0,
      "step": 160
    },
    {
      "entropy": 1.19539747312665,
      "epoch": 0.272,
      "grad_norm": 19.125,
      "learning_rate": 1.1266666666666668e-05,
      "loss": 18.9941,
      "mean_token_accuracy": 0.7230293404310941,
      "num_tokens": 5658796.0,
      "step": 170
    },
    {
      "entropy": 1.1726421393454074,
      "epoch": 0.288,
      "grad_norm": 16.75,
      "learning_rate": 1.1933333333333335e-05,
      "loss": 18.6802,
      "mean_token_accuracy": 0.7282810874283314,
      "num_tokens": 5980201.0,
      "step": 180
    },
    {
      "entropy": 1.16094581335783,
      "epoch": 0.304,
      "grad_norm": 20.5,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 18.4063,
      "mean_token_accuracy": 0.7304705370217561,
      "num_tokens": 6298858.0,
      "step": 190
    },
    {
      "entropy": 1.1420196149498225,
      "epoch": 0.32,
      "grad_norm": 18.375,
      "learning_rate": 1.3266666666666668e-05,
      "loss": 18.2034,
      "mean_token_accuracy": 0.7318542957305908,
      "num_tokens": 6622798.0,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_biology_entropy": 2.920998822212219,
      "eval_biology_loss": 3.363135814666748,
      "eval_biology_mean_token_accuracy": 0.4486829369068146,
      "eval_biology_num_tokens": 6622798.0,
      "eval_biology_runtime": 49.8146,
      "eval_biology_samples_per_second": 10.037,
      "eval_biology_steps_per_second": 2.509,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_chemistry_entropy": 1.4927990851402282,
      "eval_chemistry_loss": 1.5301882028579712,
      "eval_chemistry_mean_token_accuracy": 0.6676614291667938,
      "eval_chemistry_num_tokens": 6622798.0,
      "eval_chemistry_runtime": 61.7412,
      "eval_chemistry_samples_per_second": 8.098,
      "eval_chemistry_steps_per_second": 2.025,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_math_entropy": 1.087874176979065,
      "eval_math_loss": 1.2984504699707031,
      "eval_math_mean_token_accuracy": 0.7132572102546691,
      "eval_math_num_tokens": 6622798.0,
      "eval_math_runtime": 63.3429,
      "eval_math_samples_per_second": 7.894,
      "eval_math_steps_per_second": 1.973,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_physics_entropy": 1.1195718150138856,
      "eval_physics_loss": 1.1357909440994263,
      "eval_physics_mean_token_accuracy": 0.7332857141494751,
      "eval_physics_num_tokens": 6622798.0,
      "eval_physics_runtime": 72.1176,
      "eval_physics_samples_per_second": 6.933,
      "eval_physics_steps_per_second": 1.733,
      "step": 200
    },
    {
      "entropy": 1.1236778676509858,
      "epoch": 0.336,
      "grad_norm": 14.25,
      "learning_rate": 1.3933333333333334e-05,
      "loss": 17.9874,
      "mean_token_accuracy": 0.7355770241469145,
      "num_tokens": 6953611.0,
      "step": 210
    },
    {
      "entropy": 1.0880652230232954,
      "epoch": 0.352,
      "grad_norm": 18.0,
      "learning_rate": 1.46e-05,
      "loss": 17.3415,
      "mean_token_accuracy": 0.7432329464703799,
      "num_tokens": 7290378.0,
      "step": 220
    },
    {
      "entropy": 1.0688236601650716,
      "epoch": 0.368,
      "grad_norm": 17.875,
      "learning_rate": 1.5266666666666667e-05,
      "loss": 17.0985,
      "mean_token_accuracy": 0.7455301389098168,
      "num_tokens": 7621082.0,
      "step": 230
    },
    {
      "entropy": 1.1190654184669255,
      "epoch": 0.384,
      "grad_norm": 17.375,
      "learning_rate": 1.5933333333333336e-05,
      "loss": 17.8397,
      "mean_token_accuracy": 0.7339698273688555,
      "num_tokens": 7955570.0,
      "step": 240
    },
    {
      "entropy": 1.0598117262125015,
      "epoch": 0.4,
      "grad_norm": 18.0,
      "learning_rate": 1.66e-05,
      "loss": 16.9636,
      "mean_token_accuracy": 0.7449962131679058,
      "num_tokens": 8291049.0,
      "step": 250
    },
    {
      "entropy": 1.0420986939221621,
      "epoch": 0.416,
      "grad_norm": 16.625,
      "learning_rate": 1.726666666666667e-05,
      "loss": 16.6593,
      "mean_token_accuracy": 0.7490336105227471,
      "num_tokens": 8627310.0,
      "step": 260
    },
    {
      "entropy": 1.0523861989378929,
      "epoch": 0.432,
      "grad_norm": 19.0,
      "learning_rate": 1.7933333333333333e-05,
      "loss": 16.8565,
      "mean_token_accuracy": 0.7475517597049475,
      "num_tokens": 8958371.0,
      "step": 270
    },
    {
      "entropy": 1.0093163922429085,
      "epoch": 0.448,
      "grad_norm": 16.75,
      "learning_rate": 1.86e-05,
      "loss": 16.2024,
      "mean_token_accuracy": 0.7556655522435903,
      "num_tokens": 9294388.0,
      "step": 280
    },
    {
      "entropy": 1.006963584944606,
      "epoch": 0.464,
      "grad_norm": 17.875,
      "learning_rate": 1.926666666666667e-05,
      "loss": 16.0211,
      "mean_token_accuracy": 0.7555320005863905,
      "num_tokens": 9620366.0,
      "step": 290
    },
    {
      "entropy": 1.0118312349542975,
      "epoch": 0.48,
      "grad_norm": 18.25,
      "learning_rate": 1.9933333333333334e-05,
      "loss": 16.2777,
      "mean_token_accuracy": 0.7526854898780584,
      "num_tokens": 9955431.0,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_biology_entropy": 2.8107905416488648,
      "eval_biology_loss": 3.2179975509643555,
      "eval_biology_mean_token_accuracy": 0.46178966522216797,
      "eval_biology_num_tokens": 9955431.0,
      "eval_biology_runtime": 49.8514,
      "eval_biology_samples_per_second": 10.03,
      "eval_biology_steps_per_second": 2.507,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_chemistry_entropy": 1.406659827709198,
      "eval_chemistry_loss": 1.4287575483322144,
      "eval_chemistry_mean_token_accuracy": 0.6827028579711915,
      "eval_chemistry_num_tokens": 9955431.0,
      "eval_chemistry_runtime": 61.8676,
      "eval_chemistry_samples_per_second": 8.082,
      "eval_chemistry_steps_per_second": 2.02,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_math_entropy": 1.0421963691711427,
      "eval_math_loss": 1.2314904928207397,
      "eval_math_mean_token_accuracy": 0.7236453113555908,
      "eval_math_num_tokens": 9955431.0,
      "eval_math_runtime": 63.3661,
      "eval_math_samples_per_second": 7.891,
      "eval_math_steps_per_second": 1.973,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_physics_entropy": 1.0351716361045837,
      "eval_physics_loss": 1.0356038808822632,
      "eval_physics_mean_token_accuracy": 0.7498980407714844,
      "eval_physics_num_tokens": 9955431.0,
      "eval_physics_runtime": 72.1536,
      "eval_physics_samples_per_second": 6.93,
      "eval_physics_steps_per_second": 1.732,
      "step": 300
    },
    {
      "entropy": 1.0259150266647339,
      "epoch": 0.496,
      "grad_norm": 15.8125,
      "learning_rate": 1.9933333333333334e-05,
      "loss": 16.4439,
      "mean_token_accuracy": 0.7514661472290755,
      "num_tokens": 10289883.0,
      "step": 310
    },
    {
      "entropy": 1.0062489442527294,
      "epoch": 0.512,
      "grad_norm": 19.5,
      "learning_rate": 1.985925925925926e-05,
      "loss": 16.2084,
      "mean_token_accuracy": 0.7547577202320099,
      "num_tokens": 10619468.0,
      "step": 320
    },
    {
      "entropy": 1.0211657840758561,
      "epoch": 0.528,
      "grad_norm": 17.0,
      "learning_rate": 1.9785185185185187e-05,
      "loss": 16.3421,
      "mean_token_accuracy": 0.75145508274436,
      "num_tokens": 10944904.0,
      "step": 330
    },
    {
      "entropy": 1.0024307239800692,
      "epoch": 0.544,
      "grad_norm": 17.375,
      "learning_rate": 1.971111111111111e-05,
      "loss": 16.1168,
      "mean_token_accuracy": 0.7545490644872188,
      "num_tokens": 11266409.0,
      "step": 340
    },
    {
      "entropy": 0.9814366064965725,
      "epoch": 0.56,
      "grad_norm": 15.6875,
      "learning_rate": 1.963703703703704e-05,
      "loss": 15.6974,
      "mean_token_accuracy": 0.759765500202775,
      "num_tokens": 11605544.0,
      "step": 350
    },
    {
      "entropy": 0.974255072697997,
      "epoch": 0.576,
      "grad_norm": 17.625,
      "learning_rate": 1.9562962962962964e-05,
      "loss": 15.6108,
      "mean_token_accuracy": 0.762177936732769,
      "num_tokens": 11931715.0,
      "step": 360
    },
    {
      "entropy": 0.9886789865791797,
      "epoch": 0.592,
      "grad_norm": 17.75,
      "learning_rate": 1.948888888888889e-05,
      "loss": 15.8091,
      "mean_token_accuracy": 0.7574512097984553,
      "num_tokens": 12257243.0,
      "step": 370
    },
    {
      "entropy": 0.9611615493893624,
      "epoch": 0.608,
      "grad_norm": 15.5625,
      "learning_rate": 1.9414814814814817e-05,
      "loss": 15.4695,
      "mean_token_accuracy": 0.7621630631387234,
      "num_tokens": 12583154.0,
      "step": 380
    },
    {
      "entropy": 0.9780517250299454,
      "epoch": 0.624,
      "grad_norm": 16.25,
      "learning_rate": 1.9340740740740743e-05,
      "loss": 15.7482,
      "mean_token_accuracy": 0.7585811104625464,
      "num_tokens": 12905392.0,
      "step": 390
    },
    {
      "entropy": 0.9820186741650104,
      "epoch": 0.64,
      "grad_norm": 15.6875,
      "learning_rate": 1.926666666666667e-05,
      "loss": 15.7619,
      "mean_token_accuracy": 0.7589227013289929,
      "num_tokens": 13232198.0,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_biology_entropy": 2.7366416778564453,
      "eval_biology_loss": 3.0968964099884033,
      "eval_biology_mean_token_accuracy": 0.47410999417304994,
      "eval_biology_num_tokens": 13232198.0,
      "eval_biology_runtime": 49.8326,
      "eval_biology_samples_per_second": 10.034,
      "eval_biology_steps_per_second": 2.508,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_chemistry_entropy": 1.3320539832115172,
      "eval_chemistry_loss": 1.3684444427490234,
      "eval_chemistry_mean_token_accuracy": 0.693352394104004,
      "eval_chemistry_num_tokens": 13232198.0,
      "eval_chemistry_runtime": 61.7471,
      "eval_chemistry_samples_per_second": 8.098,
      "eval_chemistry_steps_per_second": 2.024,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_math_entropy": 0.9903823466300964,
      "eval_math_loss": 1.1989392042160034,
      "eval_math_mean_token_accuracy": 0.7292539710998536,
      "eval_math_num_tokens": 13232198.0,
      "eval_math_runtime": 63.2924,
      "eval_math_samples_per_second": 7.9,
      "eval_math_steps_per_second": 1.975,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_physics_entropy": 0.9698497958183289,
      "eval_physics_loss": 0.9801211357116699,
      "eval_physics_mean_token_accuracy": 0.7597138810157776,
      "eval_physics_num_tokens": 13232198.0,
      "eval_physics_runtime": 72.1491,
      "eval_physics_samples_per_second": 6.93,
      "eval_physics_steps_per_second": 1.733,
      "step": 400
    },
    {
      "entropy": 0.9678926695138216,
      "epoch": 0.656,
      "grad_norm": 17.625,
      "learning_rate": 1.9192592592592593e-05,
      "loss": 15.5332,
      "mean_token_accuracy": 0.7619860425591469,
      "num_tokens": 13575902.0,
      "step": 410
    },
    {
      "entropy": 0.9481775723397732,
      "epoch": 0.672,
      "grad_norm": 18.875,
      "learning_rate": 1.911851851851852e-05,
      "loss": 15.1784,
      "mean_token_accuracy": 0.7657071366906166,
      "num_tokens": 13895997.0,
      "step": 420
    },
    {
      "entropy": 0.9527117524296045,
      "epoch": 0.688,
      "grad_norm": 16.125,
      "learning_rate": 1.9044444444444446e-05,
      "loss": 15.2982,
      "mean_token_accuracy": 0.7649280011653901,
      "num_tokens": 14234888.0,
      "step": 430
    },
    {
      "entropy": 0.9615373708307743,
      "epoch": 0.704,
      "grad_norm": 17.25,
      "learning_rate": 1.8970370370370372e-05,
      "loss": 15.5115,
      "mean_token_accuracy": 0.7601466745138168,
      "num_tokens": 14567908.0,
      "step": 440
    },
    {
      "entropy": 0.9485624451190233,
      "epoch": 0.72,
      "grad_norm": 18.5,
      "learning_rate": 1.8896296296296295e-05,
      "loss": 15.1719,
      "mean_token_accuracy": 0.7653266172856092,
      "num_tokens": 14882927.0,
      "step": 450
    },
    {
      "entropy": 0.9433321110904217,
      "epoch": 0.736,
      "grad_norm": 18.375,
      "learning_rate": 1.8822222222222225e-05,
      "loss": 15.1447,
      "mean_token_accuracy": 0.765366930142045,
      "num_tokens": 15217342.0,
      "step": 460
    },
    {
      "entropy": 0.9253723874688149,
      "epoch": 0.752,
      "grad_norm": 16.75,
      "learning_rate": 1.874814814814815e-05,
      "loss": 14.7655,
      "mean_token_accuracy": 0.7691089898347855,
      "num_tokens": 15547710.0,
      "step": 470
    },
    {
      "entropy": 0.9615132443606853,
      "epoch": 0.768,
      "grad_norm": 17.375,
      "learning_rate": 1.8674074074074075e-05,
      "loss": 15.4996,
      "mean_token_accuracy": 0.7604613497853279,
      "num_tokens": 15877177.0,
      "step": 480
    },
    {
      "entropy": 0.9211561907082796,
      "epoch": 0.784,
      "grad_norm": 14.875,
      "learning_rate": 1.86e-05,
      "loss": 14.8121,
      "mean_token_accuracy": 0.7703294314444065,
      "num_tokens": 16219640.0,
      "step": 490
    },
    {
      "entropy": 0.939649223536253,
      "epoch": 0.8,
      "grad_norm": 16.75,
      "learning_rate": 1.8525925925925928e-05,
      "loss": 15.0708,
      "mean_token_accuracy": 0.7668382901698351,
      "num_tokens": 16548261.0,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_biology_entropy": 2.762967661857605,
      "eval_biology_loss": 3.090928792953491,
      "eval_biology_mean_token_accuracy": 0.47848794198036193,
      "eval_biology_num_tokens": 16548261.0,
      "eval_biology_runtime": 50.0005,
      "eval_biology_samples_per_second": 10.0,
      "eval_biology_steps_per_second": 2.5,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_chemistry_entropy": 1.333887234210968,
      "eval_chemistry_loss": 1.340030550956726,
      "eval_chemistry_mean_token_accuracy": 0.6984462032318115,
      "eval_chemistry_num_tokens": 16548261.0,
      "eval_chemistry_runtime": 61.3452,
      "eval_chemistry_samples_per_second": 8.151,
      "eval_chemistry_steps_per_second": 2.038,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_math_entropy": 0.9834395766258239,
      "eval_math_loss": 1.1809327602386475,
      "eval_math_mean_token_accuracy": 0.7322900333404541,
      "eval_math_num_tokens": 16548261.0,
      "eval_math_runtime": 63.2493,
      "eval_math_samples_per_second": 7.905,
      "eval_math_steps_per_second": 1.976,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_physics_entropy": 0.9553510432243347,
      "eval_physics_loss": 0.948321521282196,
      "eval_physics_mean_token_accuracy": 0.7648878183364868,
      "eval_physics_num_tokens": 16548261.0,
      "eval_physics_runtime": 72.2375,
      "eval_physics_samples_per_second": 6.922,
      "eval_physics_steps_per_second": 1.73,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 3000,
  "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": 1.652179086470234e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}