{
  "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": 1.2553194094449283,
      "epoch": 0.016,
      "grad_norm": 270.0,
      "learning_rate": 6.000000000000001e-07,
      "loss": 41.3914,
      "mean_token_accuracy": 0.5671123253181577,
      "num_tokens": 338352.0,
      "step": 10
    },
    {
      "entropy": 1.266689160466194,
      "epoch": 0.032,
      "grad_norm": 264.0,
      "learning_rate": 1.2666666666666669e-06,
      "loss": 41.0628,
      "mean_token_accuracy": 0.5705239847302437,
      "num_tokens": 671193.0,
      "step": 20
    },
    {
      "entropy": 1.3143046092242003,
      "epoch": 0.048,
      "grad_norm": 210.0,
      "learning_rate": 1.9333333333333336e-06,
      "loss": 39.4998,
      "mean_token_accuracy": 0.5745313983410597,
      "num_tokens": 1001008.0,
      "step": 30
    },
    {
      "entropy": 1.4753582045435905,
      "epoch": 0.064,
      "grad_norm": 155.0,
      "learning_rate": 2.6e-06,
      "loss": 38.0568,
      "mean_token_accuracy": 0.5745376290753483,
      "num_tokens": 1331208.0,
      "step": 40
    },
    {
      "entropy": 1.6769672967493534,
      "epoch": 0.08,
      "grad_norm": 99.5,
      "learning_rate": 3.266666666666667e-06,
      "loss": 34.3871,
      "mean_token_accuracy": 0.5940070981159806,
      "num_tokens": 1667532.0,
      "step": 50
    },
    {
      "entropy": 1.7719040885567665,
      "epoch": 0.096,
      "grad_norm": 55.25,
      "learning_rate": 3.9333333333333335e-06,
      "loss": 30.2468,
      "mean_token_accuracy": 0.6289831601083279,
      "num_tokens": 2007176.0,
      "step": 60
    },
    {
      "entropy": 1.7813668169081212,
      "epoch": 0.112,
      "grad_norm": 45.0,
      "learning_rate": 4.600000000000001e-06,
      "loss": 28.6054,
      "mean_token_accuracy": 0.6419326957315207,
      "num_tokens": 2342259.0,
      "step": 70
    },
    {
      "entropy": 1.7141680859029294,
      "epoch": 0.128,
      "grad_norm": 36.75,
      "learning_rate": 5.2666666666666665e-06,
      "loss": 27.4799,
      "mean_token_accuracy": 0.6465466242283583,
      "num_tokens": 2663987.0,
      "step": 80
    },
    {
      "entropy": 1.5760046038776636,
      "epoch": 0.144,
      "grad_norm": 26.875,
      "learning_rate": 5.933333333333335e-06,
      "loss": 24.8601,
      "mean_token_accuracy": 0.6713848907500506,
      "num_tokens": 2997824.0,
      "step": 90
    },
    {
      "entropy": 1.51325889416039,
      "epoch": 0.16,
      "grad_norm": 24.625,
      "learning_rate": 6.600000000000001e-06,
      "loss": 23.6713,
      "mean_token_accuracy": 0.6833302665501833,
      "num_tokens": 3330597.0,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_biology_entropy": 3.1857855548858645,
      "eval_biology_loss": 4.065364837646484,
      "eval_biology_mean_token_accuracy": 0.4020989770889282,
      "eval_biology_num_tokens": 3330597.0,
      "eval_biology_runtime": 49.9004,
      "eval_biology_samples_per_second": 10.02,
      "eval_biology_steps_per_second": 2.505,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_chemistry_entropy": 1.8894153318405151,
      "eval_chemistry_loss": 1.931850790977478,
      "eval_chemistry_mean_token_accuracy": 0.6162000632286072,
      "eval_chemistry_num_tokens": 3330597.0,
      "eval_chemistry_runtime": 61.8293,
      "eval_chemistry_samples_per_second": 8.087,
      "eval_chemistry_steps_per_second": 2.022,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_math_entropy": 1.3163333106040955,
      "eval_math_loss": 1.5677636861801147,
      "eval_math_mean_token_accuracy": 0.6788510384559632,
      "eval_math_num_tokens": 3330597.0,
      "eval_math_runtime": 63.4108,
      "eval_math_samples_per_second": 7.885,
      "eval_math_steps_per_second": 1.971,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_physics_entropy": 1.495229031085968,
      "eval_physics_loss": 1.4545849561691284,
      "eval_physics_mean_token_accuracy": 0.6851646456718444,
      "eval_physics_num_tokens": 3330597.0,
      "eval_physics_runtime": 72.2177,
      "eval_physics_samples_per_second": 6.924,
      "eval_physics_steps_per_second": 1.731,
      "step": 100
    },
    {
      "entropy": 1.473308515548706,
      "epoch": 0.176,
      "grad_norm": 25.375,
      "learning_rate": 7.266666666666668e-06,
      "loss": 22.9019,
      "mean_token_accuracy": 0.6873474020510912,
      "num_tokens": 3658264.0,
      "step": 110
    },
    {
      "entropy": 1.397306866571307,
      "epoch": 0.192,
      "grad_norm": 19.625,
      "learning_rate": 7.933333333333334e-06,
      "loss": 21.9472,
      "mean_token_accuracy": 0.6935743600130081,
      "num_tokens": 3995568.0,
      "step": 120
    },
    {
      "entropy": 1.3264490943402052,
      "epoch": 0.208,
      "grad_norm": 20.5,
      "learning_rate": 8.6e-06,
      "loss": 20.7584,
      "mean_token_accuracy": 0.7065585050731897,
      "num_tokens": 4321436.0,
      "step": 130
    },
    {
      "entropy": 1.2879054959863425,
      "epoch": 0.224,
      "grad_norm": 18.625,
      "learning_rate": 9.266666666666667e-06,
      "loss": 20.3558,
      "mean_token_accuracy": 0.7094652783125639,
      "num_tokens": 4648491.0,
      "step": 140
    },
    {
      "entropy": 1.262782633677125,
      "epoch": 0.24,
      "grad_norm": 20.875,
      "learning_rate": 9.933333333333334e-06,
      "loss": 20.125,
      "mean_token_accuracy": 0.7121465969830751,
      "num_tokens": 4986175.0,
      "step": 150
    },
    {
      "entropy": 1.249500698968768,
      "epoch": 0.256,
      "grad_norm": 20.75,
      "learning_rate": 1.0600000000000002e-05,
      "loss": 19.7318,
      "mean_token_accuracy": 0.716720923408866,
      "num_tokens": 5329320.0,
      "step": 160
    },
    {
      "entropy": 1.2423948224633932,
      "epoch": 0.272,
      "grad_norm": 21.125,
      "learning_rate": 1.1266666666666668e-05,
      "loss": 19.6803,
      "mean_token_accuracy": 0.7159549534320832,
      "num_tokens": 5658796.0,
      "step": 170
    },
    {
      "entropy": 1.2081249222159385,
      "epoch": 0.288,
      "grad_norm": 18.5,
      "learning_rate": 1.1933333333333335e-05,
      "loss": 19.318,
      "mean_token_accuracy": 0.7217235699295997,
      "num_tokens": 5980201.0,
      "step": 180
    },
    {
      "entropy": 1.2010240752249957,
      "epoch": 0.304,
      "grad_norm": 23.125,
      "learning_rate": 1.2600000000000001e-05,
      "loss": 19.0924,
      "mean_token_accuracy": 0.723386499658227,
      "num_tokens": 6298858.0,
      "step": 190
    },
    {
      "entropy": 1.1805048868060113,
      "epoch": 0.32,
      "grad_norm": 21.5,
      "learning_rate": 1.3266666666666668e-05,
      "loss": 18.8302,
      "mean_token_accuracy": 0.7257850173860788,
      "num_tokens": 6622798.0,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_biology_entropy": 3.0335595417022705,
      "eval_biology_loss": 3.5063252449035645,
      "eval_biology_mean_token_accuracy": 0.43639786744117737,
      "eval_biology_num_tokens": 6622798.0,
      "eval_biology_runtime": 49.8291,
      "eval_biology_samples_per_second": 10.034,
      "eval_biology_steps_per_second": 2.509,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_chemistry_entropy": 1.5769986052513123,
      "eval_chemistry_loss": 1.6105988025665283,
      "eval_chemistry_mean_token_accuracy": 0.6568134782314301,
      "eval_chemistry_num_tokens": 6622798.0,
      "eval_chemistry_runtime": 61.7607,
      "eval_chemistry_samples_per_second": 8.096,
      "eval_chemistry_steps_per_second": 2.024,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_math_entropy": 1.1430701270103454,
      "eval_math_loss": 1.3579970598220825,
      "eval_math_mean_token_accuracy": 0.7044133353233337,
      "eval_math_num_tokens": 6622798.0,
      "eval_math_runtime": 63.3226,
      "eval_math_samples_per_second": 7.896,
      "eval_math_steps_per_second": 1.974,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_physics_entropy": 1.1658131113052368,
      "eval_physics_loss": 1.1756293773651123,
      "eval_physics_mean_token_accuracy": 0.7273708815574647,
      "eval_physics_num_tokens": 6622798.0,
      "eval_physics_runtime": 72.1537,
      "eval_physics_samples_per_second": 6.93,
      "eval_physics_steps_per_second": 1.732,
      "step": 200
    },
    {
      "entropy": 1.1631717231124639,
      "epoch": 0.336,
      "grad_norm": 15.8125,
      "learning_rate": 1.3933333333333334e-05,
      "loss": 18.617,
      "mean_token_accuracy": 0.7290044378489255,
      "num_tokens": 6953611.0,
      "step": 210
    },
    {
      "entropy": 1.1292029924690723,
      "epoch": 0.352,
      "grad_norm": 19.625,
      "learning_rate": 1.46e-05,
      "loss": 17.9563,
      "mean_token_accuracy": 0.7365154311060905,
      "num_tokens": 7290378.0,
      "step": 220
    },
    {
      "entropy": 1.1049898941069842,
      "epoch": 0.368,
      "grad_norm": 17.75,
      "learning_rate": 1.5266666666666667e-05,
      "loss": 17.6986,
      "mean_token_accuracy": 0.7393099017441273,
      "num_tokens": 7621082.0,
      "step": 230
    },
    {
      "entropy": 1.1595781400799752,
      "epoch": 0.384,
      "grad_norm": 19.375,
      "learning_rate": 1.5933333333333336e-05,
      "loss": 18.4615,
      "mean_token_accuracy": 0.727893678098917,
      "num_tokens": 7955570.0,
      "step": 240
    },
    {
      "entropy": 1.0945355758070945,
      "epoch": 0.4,
      "grad_norm": 21.0,
      "learning_rate": 1.66e-05,
      "loss": 17.5388,
      "mean_token_accuracy": 0.7387776046991348,
      "num_tokens": 8291049.0,
      "step": 250
    },
    {
      "entropy": 1.0819710556417703,
      "epoch": 0.416,
      "grad_norm": 18.375,
      "learning_rate": 1.726666666666667e-05,
      "loss": 17.251,
      "mean_token_accuracy": 0.7430898856371642,
      "num_tokens": 8627310.0,
      "step": 260
    },
    {
      "entropy": 1.089613201841712,
      "epoch": 0.432,
      "grad_norm": 20.75,
      "learning_rate": 1.7933333333333333e-05,
      "loss": 17.4707,
      "mean_token_accuracy": 0.7406438160687685,
      "num_tokens": 8958371.0,
      "step": 270
    },
    {
      "entropy": 1.0421824473887682,
      "epoch": 0.448,
      "grad_norm": 18.25,
      "learning_rate": 1.86e-05,
      "loss": 16.7755,
      "mean_token_accuracy": 0.7496135134249926,
      "num_tokens": 9294388.0,
      "step": 280
    },
    {
      "entropy": 1.0451348841190338,
      "epoch": 0.464,
      "grad_norm": 19.625,
      "learning_rate": 1.926666666666667e-05,
      "loss": 16.5784,
      "mean_token_accuracy": 0.7497908163815736,
      "num_tokens": 9620366.0,
      "step": 290
    },
    {
      "entropy": 1.0491984207183123,
      "epoch": 0.48,
      "grad_norm": 21.0,
      "learning_rate": 1.9933333333333334e-05,
      "loss": 16.8506,
      "mean_token_accuracy": 0.7469458010047674,
      "num_tokens": 9955431.0,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_biology_entropy": 2.9388448543548584,
      "eval_biology_loss": 3.3656885623931885,
      "eval_biology_mean_token_accuracy": 0.45114623188972475,
      "eval_biology_num_tokens": 9955431.0,
      "eval_biology_runtime": 49.8383,
      "eval_biology_samples_per_second": 10.032,
      "eval_biology_steps_per_second": 2.508,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_chemistry_entropy": 1.491808822631836,
      "eval_chemistry_loss": 1.5070267915725708,
      "eval_chemistry_mean_token_accuracy": 0.6716848533153534,
      "eval_chemistry_num_tokens": 9955431.0,
      "eval_chemistry_runtime": 61.771,
      "eval_chemistry_samples_per_second": 8.094,
      "eval_chemistry_steps_per_second": 2.024,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_math_entropy": 1.1062884669303894,
      "eval_math_loss": 1.285144567489624,
      "eval_math_mean_token_accuracy": 0.7163918890953064,
      "eval_math_num_tokens": 9955431.0,
      "eval_math_runtime": 63.3221,
      "eval_math_samples_per_second": 7.896,
      "eval_math_steps_per_second": 1.974,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_physics_entropy": 1.0871692457199096,
      "eval_physics_loss": 1.0718116760253906,
      "eval_physics_mean_token_accuracy": 0.7436052026748657,
      "eval_physics_num_tokens": 9955431.0,
      "eval_physics_runtime": 72.1598,
      "eval_physics_samples_per_second": 6.929,
      "eval_physics_steps_per_second": 1.732,
      "step": 300
    },
    {
      "entropy": 1.0622025161981583,
      "epoch": 0.496,
      "grad_norm": 17.625,
      "learning_rate": 1.9933333333333334e-05,
      "loss": 17.0457,
      "mean_token_accuracy": 0.7451069477945567,
      "num_tokens": 10289883.0,
      "step": 310
    },
    {
      "entropy": 1.0407135926187039,
      "epoch": 0.512,
      "grad_norm": 21.375,
      "learning_rate": 1.985925925925926e-05,
      "loss": 16.7612,
      "mean_token_accuracy": 0.7487055193632841,
      "num_tokens": 10619468.0,
      "step": 320
    },
    {
      "entropy": 1.060495626181364,
      "epoch": 0.528,
      "grad_norm": 19.625,
      "learning_rate": 1.9785185185185187e-05,
      "loss": 16.9124,
      "mean_token_accuracy": 0.7458847668021917,
      "num_tokens": 10944904.0,
      "step": 330
    },
    {
      "entropy": 1.0363870609551669,
      "epoch": 0.544,
      "grad_norm": 19.125,
      "learning_rate": 1.971111111111111e-05,
      "loss": 16.6786,
      "mean_token_accuracy": 0.7487504351884127,
      "num_tokens": 11266409.0,
      "step": 340
    },
    {
      "entropy": 1.01834645755589,
      "epoch": 0.56,
      "grad_norm": 17.125,
      "learning_rate": 1.963703703703704e-05,
      "loss": 16.224,
      "mean_token_accuracy": 0.7543694581836462,
      "num_tokens": 11605544.0,
      "step": 350
    },
    {
      "entropy": 1.0103376515209674,
      "epoch": 0.576,
      "grad_norm": 21.75,
      "learning_rate": 1.9562962962962964e-05,
      "loss": 16.1635,
      "mean_token_accuracy": 0.7562580808997155,
      "num_tokens": 11931715.0,
      "step": 360
    },
    {
      "entropy": 1.0192645259201527,
      "epoch": 0.592,
      "grad_norm": 19.625,
      "learning_rate": 1.948888888888889e-05,
      "loss": 16.3501,
      "mean_token_accuracy": 0.7522288095206022,
      "num_tokens": 12257243.0,
      "step": 370
    },
    {
      "entropy": 0.9979648280888795,
      "epoch": 0.608,
      "grad_norm": 17.25,
      "learning_rate": 1.9414814814814817e-05,
      "loss": 16.0193,
      "mean_token_accuracy": 0.7565512597560883,
      "num_tokens": 12583154.0,
      "step": 380
    },
    {
      "entropy": 1.0146858640015126,
      "epoch": 0.624,
      "grad_norm": 18.375,
      "learning_rate": 1.9340740740740743e-05,
      "loss": 16.2917,
      "mean_token_accuracy": 0.7530687287449837,
      "num_tokens": 12905392.0,
      "step": 390
    },
    {
      "entropy": 1.0172333989292384,
      "epoch": 0.64,
      "grad_norm": 18.0,
      "learning_rate": 1.926666666666667e-05,
      "loss": 16.311,
      "mean_token_accuracy": 0.753251226246357,
      "num_tokens": 13232198.0,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_biology_entropy": 2.8556682786941527,
      "eval_biology_loss": 3.2405552864074707,
      "eval_biology_mean_token_accuracy": 0.46047434616088867,
      "eval_biology_num_tokens": 13232198.0,
      "eval_biology_runtime": 49.8137,
      "eval_biology_samples_per_second": 10.037,
      "eval_biology_steps_per_second": 2.509,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_chemistry_entropy": 1.4023492636680603,
      "eval_chemistry_loss": 1.4446464776992798,
      "eval_chemistry_mean_token_accuracy": 0.6815885419845581,
      "eval_chemistry_num_tokens": 13232198.0,
      "eval_chemistry_runtime": 61.7651,
      "eval_chemistry_samples_per_second": 8.095,
      "eval_chemistry_steps_per_second": 2.024,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_math_entropy": 1.0369325885772704,
      "eval_math_loss": 1.2500724792480469,
      "eval_math_mean_token_accuracy": 0.7222203068733215,
      "eval_math_num_tokens": 13232198.0,
      "eval_math_runtime": 63.311,
      "eval_math_samples_per_second": 7.898,
      "eval_math_steps_per_second": 1.974,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_physics_entropy": 1.0061357097625732,
      "eval_physics_loss": 1.0139094591140747,
      "eval_physics_mean_token_accuracy": 0.7539046273231507,
      "eval_physics_num_tokens": 13232198.0,
      "eval_physics_runtime": 72.128,
      "eval_physics_samples_per_second": 6.932,
      "eval_physics_steps_per_second": 1.733,
      "step": 400
    },
    {
      "entropy": 1.0025192126631737,
      "epoch": 0.656,
      "grad_norm": 19.0,
      "learning_rate": 1.9192592592592593e-05,
      "loss": 16.0757,
      "mean_token_accuracy": 0.7558728314936161,
      "num_tokens": 13575902.0,
      "step": 410
    },
    {
      "entropy": 0.9805797968059778,
      "epoch": 0.672,
      "grad_norm": 20.75,
      "learning_rate": 1.911851851851852e-05,
      "loss": 15.6938,
      "mean_token_accuracy": 0.7607984621077776,
      "num_tokens": 13895997.0,
      "step": 420
    },
    {
      "entropy": 0.98455760627985,
      "epoch": 0.688,
      "grad_norm": 17.5,
      "learning_rate": 1.9044444444444446e-05,
      "loss": 15.8079,
      "mean_token_accuracy": 0.7591990135610104,
      "num_tokens": 14234888.0,
      "step": 430
    },
    {
      "entropy": 0.995212909206748,
      "epoch": 0.704,
      "grad_norm": 19.5,
      "learning_rate": 1.8970370370370372e-05,
      "loss": 16.0276,
      "mean_token_accuracy": 0.7551241502165794,
      "num_tokens": 14567908.0,
      "step": 440
    },
    {
      "entropy": 0.9859623953700065,
      "epoch": 0.72,
      "grad_norm": 19.875,
      "learning_rate": 1.8896296296296295e-05,
      "loss": 15.7158,
      "mean_token_accuracy": 0.759292322024703,
      "num_tokens": 14882927.0,
      "step": 450
    },
    {
      "entropy": 0.9759141772985458,
      "epoch": 0.736,
      "grad_norm": 20.625,
      "learning_rate": 1.8822222222222225e-05,
      "loss": 15.6771,
      "mean_token_accuracy": 0.759360334649682,
      "num_tokens": 15217342.0,
      "step": 460
    },
    {
      "entropy": 0.9576828479766846,
      "epoch": 0.752,
      "grad_norm": 19.5,
      "learning_rate": 1.874814814814815e-05,
      "loss": 15.2707,
      "mean_token_accuracy": 0.764180276170373,
      "num_tokens": 15547710.0,
      "step": 470
    },
    {
      "entropy": 0.9969257492572069,
      "epoch": 0.768,
      "grad_norm": 19.625,
      "learning_rate": 1.8674074074074075e-05,
      "loss": 16.0499,
      "mean_token_accuracy": 0.7543311327695846,
      "num_tokens": 15877177.0,
      "step": 480
    },
    {
      "entropy": 0.9526452720165253,
      "epoch": 0.784,
      "grad_norm": 15.8125,
      "learning_rate": 1.86e-05,
      "loss": 15.3172,
      "mean_token_accuracy": 0.7652558576315641,
      "num_tokens": 16219640.0,
      "step": 490
    },
    {
      "entropy": 0.9730141185224056,
      "epoch": 0.8,
      "grad_norm": 19.25,
      "learning_rate": 1.8525925925925928e-05,
      "loss": 15.5783,
      "mean_token_accuracy": 0.7610898818820715,
      "num_tokens": 16548261.0,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_biology_entropy": 2.8879401025772093,
      "eval_biology_loss": 3.2465980052948,
      "eval_biology_mean_token_accuracy": 0.4656795439720154,
      "eval_biology_num_tokens": 16548261.0,
      "eval_biology_runtime": 50.0039,
      "eval_biology_samples_per_second": 9.999,
      "eval_biology_steps_per_second": 2.5,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_chemistry_entropy": 1.4028268342018126,
      "eval_chemistry_loss": 1.4141976833343506,
      "eval_chemistry_mean_token_accuracy": 0.6879124054908753,
      "eval_chemistry_num_tokens": 16548261.0,
      "eval_chemistry_runtime": 61.4753,
      "eval_chemistry_samples_per_second": 8.133,
      "eval_chemistry_steps_per_second": 2.033,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_math_entropy": 1.036446961402893,
      "eval_math_loss": 1.2320657968521118,
      "eval_math_mean_token_accuracy": 0.7248759384155273,
      "eval_math_num_tokens": 16548261.0,
      "eval_math_runtime": 63.2484,
      "eval_math_samples_per_second": 7.905,
      "eval_math_steps_per_second": 1.976,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_physics_entropy": 0.9860591797828674,
      "eval_physics_loss": 0.9807776808738708,
      "eval_physics_mean_token_accuracy": 0.7594618821144103,
      "eval_physics_num_tokens": 16548261.0,
      "eval_physics_runtime": 72.1552,
      "eval_physics_samples_per_second": 6.93,
      "eval_physics_steps_per_second": 1.732,
      "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
}