{
  "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": 1.000200616195798,
      "epoch": 0.016,
      "grad_norm": 1776.0,
      "learning_rate": 4.5000000000000003e-07,
      "loss": 69.8616,
      "mean_token_accuracy": 0.460323916003108,
      "num_tokens": 195524.0,
      "step": 10
    },
    {
      "entropy": 0.9949515227228403,
      "epoch": 0.032,
      "grad_norm": 1624.0,
      "learning_rate": 9.500000000000001e-07,
      "loss": 68.3351,
      "mean_token_accuracy": 0.4633398361504078,
      "num_tokens": 390903.0,
      "step": 20
    },
    {
      "entropy": 1.0845801826566457,
      "epoch": 0.048,
      "grad_norm": 1728.0,
      "learning_rate": 1.45e-06,
      "loss": 63.0644,
      "mean_token_accuracy": 0.46960638258606197,
      "num_tokens": 589868.0,
      "step": 30
    },
    {
      "entropy": 1.247272988036275,
      "epoch": 0.064,
      "grad_norm": 488.0,
      "learning_rate": 1.9500000000000004e-06,
      "loss": 55.5844,
      "mean_token_accuracy": 0.480246701836586,
      "num_tokens": 791190.0,
      "step": 40
    },
    {
      "entropy": 1.4826370410621166,
      "epoch": 0.08,
      "grad_norm": 288.0,
      "learning_rate": 2.4500000000000003e-06,
      "loss": 50.1588,
      "mean_token_accuracy": 0.48712102621793746,
      "num_tokens": 989860.0,
      "step": 50
    },
    {
      "entropy": 1.814505684375763,
      "epoch": 0.096,
      "grad_norm": 131.0,
      "learning_rate": 2.95e-06,
      "loss": 45.3237,
      "mean_token_accuracy": 0.48977465480566024,
      "num_tokens": 1181777.0,
      "step": 60
    },
    {
      "entropy": 2.17904861420393,
      "epoch": 0.112,
      "grad_norm": 67.5,
      "learning_rate": 3.45e-06,
      "loss": 40.572,
      "mean_token_accuracy": 0.5055354550480843,
      "num_tokens": 1385513.0,
      "step": 70
    },
    {
      "entropy": 2.317786781489849,
      "epoch": 0.128,
      "grad_norm": 55.25,
      "learning_rate": 3.95e-06,
      "loss": 38.0783,
      "mean_token_accuracy": 0.5195932997390628,
      "num_tokens": 1582368.0,
      "step": 80
    },
    {
      "entropy": 2.2404811814427377,
      "epoch": 0.144,
      "grad_norm": 40.75,
      "learning_rate": 4.450000000000001e-06,
      "loss": 35.7283,
      "mean_token_accuracy": 0.5399348795413971,
      "num_tokens": 1773764.0,
      "step": 90
    },
    {
      "entropy": 2.1976587153971194,
      "epoch": 0.16,
      "grad_norm": 38.0,
      "learning_rate": 4.95e-06,
      "loss": 34.5297,
      "mean_token_accuracy": 0.5478190431371331,
      "num_tokens": 1970077.0,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_biology_entropy": 2.1061868534088135,
      "eval_biology_loss": 2.0133121013641357,
      "eval_biology_mean_token_accuracy": 0.5668603234291076,
      "eval_biology_num_tokens": 1970077.0,
      "eval_biology_runtime": 47.9413,
      "eval_biology_samples_per_second": 10.429,
      "eval_biology_steps_per_second": 2.607,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_chemistry_entropy": 1.8679178915023804,
      "eval_chemistry_loss": 1.844948410987854,
      "eval_chemistry_mean_token_accuracy": 0.5880863065719605,
      "eval_chemistry_num_tokens": 1970077.0,
      "eval_chemistry_runtime": 59.3684,
      "eval_chemistry_samples_per_second": 8.422,
      "eval_chemistry_steps_per_second": 2.105,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_math_entropy": 1.6290378885269166,
      "eval_math_loss": 2.072597026824951,
      "eval_math_mean_token_accuracy": 0.5653720505237579,
      "eval_math_num_tokens": 1970077.0,
      "eval_math_runtime": 60.948,
      "eval_math_samples_per_second": 8.204,
      "eval_math_steps_per_second": 2.051,
      "step": 100
    },
    {
      "epoch": 0.16,
      "eval_physics_entropy": 1.907263669013977,
      "eval_physics_loss": 2.105146884918213,
      "eval_physics_mean_token_accuracy": 0.5574561676979065,
      "eval_physics_num_tokens": 1970077.0,
      "eval_physics_runtime": 69.3465,
      "eval_physics_samples_per_second": 7.21,
      "eval_physics_steps_per_second": 1.803,
      "step": 100
    },
    {
      "entropy": 2.0820947512984276,
      "epoch": 0.176,
      "grad_norm": 33.5,
      "learning_rate": 5.450000000000001e-06,
      "loss": 32.4406,
      "mean_token_accuracy": 0.5621457317844033,
      "num_tokens": 2168354.0,
      "step": 110
    },
    {
      "entropy": 2.0283117063343523,
      "epoch": 0.192,
      "grad_norm": 32.25,
      "learning_rate": 5.950000000000001e-06,
      "loss": 31.491,
      "mean_token_accuracy": 0.5688053227961063,
      "num_tokens": 2365822.0,
      "step": 120
    },
    {
      "entropy": 1.973121351003647,
      "epoch": 0.208,
      "grad_norm": 33.75,
      "learning_rate": 6.450000000000001e-06,
      "loss": 30.9217,
      "mean_token_accuracy": 0.5753367917612195,
      "num_tokens": 2558762.0,
      "step": 130
    },
    {
      "entropy": 1.9165778771042823,
      "epoch": 0.224,
      "grad_norm": 30.625,
      "learning_rate": 6.95e-06,
      "loss": 30.1267,
      "mean_token_accuracy": 0.583262656442821,
      "num_tokens": 2755347.0,
      "step": 140
    },
    {
      "entropy": 1.8870679274201394,
      "epoch": 0.24,
      "grad_norm": 31.5,
      "learning_rate": 7.450000000000001e-06,
      "loss": 29.6484,
      "mean_token_accuracy": 0.5872904889285564,
      "num_tokens": 2947346.0,
      "step": 150
    },
    {
      "entropy": 1.8710497491061688,
      "epoch": 0.256,
      "grad_norm": 29.875,
      "learning_rate": 7.950000000000002e-06,
      "loss": 29.4624,
      "mean_token_accuracy": 0.5887285262346268,
      "num_tokens": 3139957.0,
      "step": 160
    },
    {
      "entropy": 1.808907500654459,
      "epoch": 0.272,
      "grad_norm": 29.125,
      "learning_rate": 8.45e-06,
      "loss": 28.7075,
      "mean_token_accuracy": 0.5965064790099859,
      "num_tokens": 3335951.0,
      "step": 170
    },
    {
      "entropy": 1.774143099039793,
      "epoch": 0.288,
      "grad_norm": 28.125,
      "learning_rate": 8.95e-06,
      "loss": 28.1007,
      "mean_token_accuracy": 0.5996631737798452,
      "num_tokens": 3539731.0,
      "step": 180
    },
    {
      "entropy": 1.7740100547671318,
      "epoch": 0.304,
      "grad_norm": 27.75,
      "learning_rate": 9.450000000000001e-06,
      "loss": 28.1122,
      "mean_token_accuracy": 0.6012205760926008,
      "num_tokens": 3733488.0,
      "step": 190
    },
    {
      "entropy": 1.7725927896797657,
      "epoch": 0.32,
      "grad_norm": 35.25,
      "learning_rate": 9.950000000000001e-06,
      "loss": 28.1299,
      "mean_token_accuracy": 0.5997324202209711,
      "num_tokens": 3920545.0,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_biology_entropy": 1.6843824968338013,
      "eval_biology_loss": 1.6854687929153442,
      "eval_biology_mean_token_accuracy": 0.6137065634727478,
      "eval_biology_num_tokens": 3920545.0,
      "eval_biology_runtime": 47.8268,
      "eval_biology_samples_per_second": 10.454,
      "eval_biology_steps_per_second": 2.614,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_chemistry_entropy": 1.441379102230072,
      "eval_chemistry_loss": 1.4537148475646973,
      "eval_chemistry_mean_token_accuracy": 0.6551240344047546,
      "eval_chemistry_num_tokens": 3920545.0,
      "eval_chemistry_runtime": 59.3401,
      "eval_chemistry_samples_per_second": 8.426,
      "eval_chemistry_steps_per_second": 2.106,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_math_entropy": 1.3251727666854858,
      "eval_math_loss": 1.6510798931121826,
      "eval_math_mean_token_accuracy": 0.6343780555725098,
      "eval_math_num_tokens": 3920545.0,
      "eval_math_runtime": 60.8747,
      "eval_math_samples_per_second": 8.214,
      "eval_math_steps_per_second": 2.053,
      "step": 200
    },
    {
      "epoch": 0.32,
      "eval_physics_entropy": 1.4914224824905395,
      "eval_physics_loss": 1.6194021701812744,
      "eval_physics_mean_token_accuracy": 0.6387534441947937,
      "eval_physics_num_tokens": 3920545.0,
      "eval_physics_runtime": 69.3484,
      "eval_physics_samples_per_second": 7.21,
      "eval_physics_steps_per_second": 1.802,
      "step": 200
    },
    {
      "entropy": 1.7085595309734345,
      "epoch": 0.336,
      "grad_norm": 30.375,
      "learning_rate": 1.045e-05,
      "loss": 27.2575,
      "mean_token_accuracy": 0.6091335583478212,
      "num_tokens": 4114077.0,
      "step": 210
    },
    {
      "entropy": 1.7301082991063594,
      "epoch": 0.352,
      "grad_norm": 31.0,
      "learning_rate": 1.095e-05,
      "loss": 27.6337,
      "mean_token_accuracy": 0.6071538373827934,
      "num_tokens": 4306949.0,
      "step": 220
    },
    {
      "entropy": 1.695884221047163,
      "epoch": 0.368,
      "grad_norm": 27.75,
      "learning_rate": 1.145e-05,
      "loss": 27.0338,
      "mean_token_accuracy": 0.6128786243498325,
      "num_tokens": 4504001.0,
      "step": 230
    },
    {
      "entropy": 1.6912743583321572,
      "epoch": 0.384,
      "grad_norm": 31.0,
      "learning_rate": 1.195e-05,
      "loss": 27.0143,
      "mean_token_accuracy": 0.6135674986988306,
      "num_tokens": 4693812.0,
      "step": 240
    },
    {
      "entropy": 1.6936707220971585,
      "epoch": 0.4,
      "grad_norm": 24.5,
      "learning_rate": 1.2450000000000003e-05,
      "loss": 26.8651,
      "mean_token_accuracy": 0.6143408048897981,
      "num_tokens": 4887094.0,
      "step": 250
    },
    {
      "entropy": 1.678075761348009,
      "epoch": 0.416,
      "grad_norm": 27.875,
      "learning_rate": 1.295e-05,
      "loss": 27.047,
      "mean_token_accuracy": 0.6129864633083344,
      "num_tokens": 5085369.0,
      "step": 260
    },
    {
      "entropy": 1.6657070152461528,
      "epoch": 0.432,
      "grad_norm": 29.75,
      "learning_rate": 1.3450000000000002e-05,
      "loss": 26.7844,
      "mean_token_accuracy": 0.6148818587884307,
      "num_tokens": 5271275.0,
      "step": 270
    },
    {
      "entropy": 1.6670012198388577,
      "epoch": 0.448,
      "grad_norm": 31.375,
      "learning_rate": 1.3950000000000002e-05,
      "loss": 26.617,
      "mean_token_accuracy": 0.6159537024796009,
      "num_tokens": 5460559.0,
      "step": 280
    },
    {
      "entropy": 1.6152651645243168,
      "epoch": 0.464,
      "grad_norm": 32.25,
      "learning_rate": 1.4450000000000002e-05,
      "loss": 25.6477,
      "mean_token_accuracy": 0.6256863068789243,
      "num_tokens": 5653809.0,
      "step": 290
    },
    {
      "entropy": 1.624342393130064,
      "epoch": 0.48,
      "grad_norm": 25.75,
      "learning_rate": 1.4950000000000003e-05,
      "loss": 26.2019,
      "mean_token_accuracy": 0.6199633304029704,
      "num_tokens": 5850176.0,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_biology_entropy": 1.5827035818099975,
      "eval_biology_loss": 1.570924997329712,
      "eval_biology_mean_token_accuracy": 0.6328578324317932,
      "eval_biology_num_tokens": 5850176.0,
      "eval_biology_runtime": 47.7211,
      "eval_biology_samples_per_second": 10.478,
      "eval_biology_steps_per_second": 2.619,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_chemistry_entropy": 1.3193063869476318,
      "eval_chemistry_loss": 1.3243473768234253,
      "eval_chemistry_mean_token_accuracy": 0.6796774597167968,
      "eval_chemistry_num_tokens": 5850176.0,
      "eval_chemistry_runtime": 59.1912,
      "eval_chemistry_samples_per_second": 8.447,
      "eval_chemistry_steps_per_second": 2.112,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_math_entropy": 1.2024567556381225,
      "eval_math_loss": 1.5285311937332153,
      "eval_math_mean_token_accuracy": 0.6541934962272644,
      "eval_math_num_tokens": 5850176.0,
      "eval_math_runtime": 60.6728,
      "eval_math_samples_per_second": 8.241,
      "eval_math_steps_per_second": 2.06,
      "step": 300
    },
    {
      "epoch": 0.48,
      "eval_physics_entropy": 1.3696330366134644,
      "eval_physics_loss": 1.4624738693237305,
      "eval_physics_mean_token_accuracy": 0.6671717586517334,
      "eval_physics_num_tokens": 5850176.0,
      "eval_physics_runtime": 69.1435,
      "eval_physics_samples_per_second": 7.231,
      "eval_physics_steps_per_second": 1.808,
      "step": 300
    },
    {
      "entropy": 1.543294757604599,
      "epoch": 0.496,
      "grad_norm": 24.125,
      "learning_rate": 1.545e-05,
      "loss": 24.7301,
      "mean_token_accuracy": 0.6344853390008212,
      "num_tokens": 6046503.0,
      "step": 310
    },
    {
      "entropy": 1.6137450806796552,
      "epoch": 0.512,
      "grad_norm": 30.0,
      "learning_rate": 1.595e-05,
      "loss": 25.8005,
      "mean_token_accuracy": 0.624148428812623,
      "num_tokens": 6240456.0,
      "step": 320
    },
    {
      "entropy": 1.5901939049363136,
      "epoch": 0.528,
      "grad_norm": 26.75,
      "learning_rate": 1.645e-05,
      "loss": 25.5556,
      "mean_token_accuracy": 0.6283756781369447,
      "num_tokens": 6430555.0,
      "step": 330
    },
    {
      "entropy": 1.5919260658323764,
      "epoch": 0.544,
      "grad_norm": 25.375,
      "learning_rate": 1.6950000000000002e-05,
      "loss": 25.5888,
      "mean_token_accuracy": 0.6276101280003786,
      "num_tokens": 6626006.0,
      "step": 340
    },
    {
      "entropy": 1.5667011991143227,
      "epoch": 0.56,
      "grad_norm": 27.375,
      "learning_rate": 1.7450000000000004e-05,
      "loss": 25.1583,
      "mean_token_accuracy": 0.6304543860256672,
      "num_tokens": 6820754.0,
      "step": 350
    },
    {
      "entropy": 1.548937487602234,
      "epoch": 0.576,
      "grad_norm": 25.0,
      "learning_rate": 1.795e-05,
      "loss": 24.8095,
      "mean_token_accuracy": 0.6340219389647246,
      "num_tokens": 7021844.0,
      "step": 360
    },
    {
      "entropy": 1.5519795384258033,
      "epoch": 0.592,
      "grad_norm": 25.75,
      "learning_rate": 1.845e-05,
      "loss": 25.0794,
      "mean_token_accuracy": 0.6325468828901648,
      "num_tokens": 7213951.0,
      "step": 370
    },
    {
      "entropy": 1.5391070768237114,
      "epoch": 0.608,
      "grad_norm": 28.25,
      "learning_rate": 1.8950000000000003e-05,
      "loss": 24.6819,
      "mean_token_accuracy": 0.636061006039381,
      "num_tokens": 7416773.0,
      "step": 380
    },
    {
      "entropy": 1.5429081372916698,
      "epoch": 0.624,
      "grad_norm": 27.5,
      "learning_rate": 1.9450000000000002e-05,
      "loss": 24.8187,
      "mean_token_accuracy": 0.634391113743186,
      "num_tokens": 7612843.0,
      "step": 390
    },
    {
      "entropy": 1.5399384461343288,
      "epoch": 0.64,
      "grad_norm": 25.875,
      "learning_rate": 1.9950000000000004e-05,
      "loss": 24.8584,
      "mean_token_accuracy": 0.6340381380170583,
      "num_tokens": 7801633.0,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_biology_entropy": 1.4887315626144408,
      "eval_biology_loss": 1.4859997034072876,
      "eval_biology_mean_token_accuracy": 0.6469658589363099,
      "eval_biology_num_tokens": 7801633.0,
      "eval_biology_runtime": 47.815,
      "eval_biology_samples_per_second": 10.457,
      "eval_biology_steps_per_second": 2.614,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_chemistry_entropy": 1.216160174369812,
      "eval_chemistry_loss": 1.23386549949646,
      "eval_chemistry_mean_token_accuracy": 0.6968556141853333,
      "eval_chemistry_num_tokens": 7801633.0,
      "eval_chemistry_runtime": 59.3099,
      "eval_chemistry_samples_per_second": 8.43,
      "eval_chemistry_steps_per_second": 2.108,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_math_entropy": 1.0936446270942688,
      "eval_math_loss": 1.4483542442321777,
      "eval_math_mean_token_accuracy": 0.6711465301513672,
      "eval_math_num_tokens": 7801633.0,
      "eval_math_runtime": 60.6,
      "eval_math_samples_per_second": 8.251,
      "eval_math_steps_per_second": 2.063,
      "step": 400
    },
    {
      "epoch": 0.64,
      "eval_physics_entropy": 1.2649442830085755,
      "eval_physics_loss": 1.3500477075576782,
      "eval_physics_mean_token_accuracy": 0.6875980172157288,
      "eval_physics_num_tokens": 7801633.0,
      "eval_physics_runtime": 68.83,
      "eval_physics_samples_per_second": 7.264,
      "eval_physics_steps_per_second": 1.816,
      "step": 400
    },
    {
      "entropy": 1.5343165121972562,
      "epoch": 0.656,
      "grad_norm": 26.375,
      "learning_rate": 1.9950000000000004e-05,
      "loss": 24.7076,
      "mean_token_accuracy": 0.6344317115843296,
      "num_tokens": 7995843.0,
      "step": 410
    },
    {
      "entropy": 1.5481104589998722,
      "epoch": 0.672,
      "grad_norm": 24.75,
      "learning_rate": 1.9894444444444446e-05,
      "loss": 24.7524,
      "mean_token_accuracy": 0.6355006828904152,
      "num_tokens": 8183103.0,
      "step": 420
    },
    {
      "entropy": 1.5163978930562734,
      "epoch": 0.688,
      "grad_norm": 22.75,
      "learning_rate": 1.983888888888889e-05,
      "loss": 24.5063,
      "mean_token_accuracy": 0.6392664317041635,
      "num_tokens": 8385976.0,
      "step": 430
    },
    {
      "entropy": 1.5027333579957485,
      "epoch": 0.704,
      "grad_norm": 21.875,
      "learning_rate": 1.9783333333333334e-05,
      "loss": 24.2448,
      "mean_token_accuracy": 0.641432274878025,
      "num_tokens": 8578431.0,
      "step": 440
    },
    {
      "entropy": 1.4510110400617122,
      "epoch": 0.72,
      "grad_norm": 22.625,
      "learning_rate": 1.972777777777778e-05,
      "loss": 23.3137,
      "mean_token_accuracy": 0.6509528819471597,
      "num_tokens": 8781342.0,
      "step": 450
    },
    {
      "entropy": 1.471246886998415,
      "epoch": 0.736,
      "grad_norm": 22.0,
      "learning_rate": 1.9672222222222222e-05,
      "loss": 23.5955,
      "mean_token_accuracy": 0.6463174737989903,
      "num_tokens": 8977918.0,
      "step": 460
    },
    {
      "entropy": 1.4814870670437812,
      "epoch": 0.752,
      "grad_norm": 22.25,
      "learning_rate": 1.9616666666666668e-05,
      "loss": 23.9505,
      "mean_token_accuracy": 0.6442026626318693,
      "num_tokens": 9169322.0,
      "step": 470
    },
    {
      "entropy": 1.4392801743000745,
      "epoch": 0.768,
      "grad_norm": 24.125,
      "learning_rate": 1.9561111111111114e-05,
      "loss": 23.1521,
      "mean_token_accuracy": 0.6515602272003889,
      "num_tokens": 9368141.0,
      "step": 480
    },
    {
      "entropy": 1.4612651772797107,
      "epoch": 0.784,
      "grad_norm": 25.875,
      "learning_rate": 1.9505555555555556e-05,
      "loss": 23.5729,
      "mean_token_accuracy": 0.6485392026603222,
      "num_tokens": 9565236.0,
      "step": 490
    },
    {
      "entropy": 1.4798763774335384,
      "epoch": 0.8,
      "grad_norm": 24.0,
      "learning_rate": 1.9450000000000002e-05,
      "loss": 23.9628,
      "mean_token_accuracy": 0.6433830507099628,
      "num_tokens": 9761227.0,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_biology_entropy": 1.4178470463752746,
      "eval_biology_loss": 1.4294027090072632,
      "eval_biology_mean_token_accuracy": 0.6571813192367554,
      "eval_biology_num_tokens": 9761227.0,
      "eval_biology_runtime": 47.9552,
      "eval_biology_samples_per_second": 10.426,
      "eval_biology_steps_per_second": 2.607,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_chemistry_entropy": 1.1406473817825318,
      "eval_chemistry_loss": 1.1737452745437622,
      "eval_chemistry_mean_token_accuracy": 0.7092447648048401,
      "eval_chemistry_num_tokens": 9761227.0,
      "eval_chemistry_runtime": 58.9872,
      "eval_chemistry_samples_per_second": 8.476,
      "eval_chemistry_steps_per_second": 2.119,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_math_entropy": 1.0307734375,
      "eval_math_loss": 1.3721623420715332,
      "eval_math_mean_token_accuracy": 0.6881859846115113,
      "eval_math_num_tokens": 9761227.0,
      "eval_math_runtime": 60.7077,
      "eval_math_samples_per_second": 8.236,
      "eval_math_steps_per_second": 2.059,
      "step": 500
    },
    {
      "epoch": 0.8,
      "eval_physics_entropy": 1.1864667072296142,
      "eval_physics_loss": 1.28458571434021,
      "eval_physics_mean_token_accuracy": 0.701751223564148,
      "eval_physics_num_tokens": 9761227.0,
      "eval_physics_runtime": 69.206,
      "eval_physics_samples_per_second": 7.225,
      "eval_physics_steps_per_second": 1.806,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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": 1.0976936565348991e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}