{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.037024793388429754,
  "eval_steps": 500,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005289256198347108,
      "grad_norm": 14983.798828125,
      "learning_rate": 2.4e-07,
      "loss": 17.1865,
      "step": 10
    },
    {
      "epoch": 0.0010578512396694215,
      "grad_norm": 2818.19287109375,
      "learning_rate": 1.04e-06,
      "loss": 16.2669,
      "step": 20
    },
    {
      "epoch": 0.0015867768595041322,
      "grad_norm": 2148.98486328125,
      "learning_rate": 1.84e-06,
      "loss": 15.5605,
      "step": 30
    },
    {
      "epoch": 0.002115702479338843,
      "grad_norm": 2309.862548828125,
      "learning_rate": 2.64e-06,
      "loss": 15.2203,
      "step": 40
    },
    {
      "epoch": 0.002644628099173554,
      "grad_norm": 2205.408935546875,
      "learning_rate": 3.44e-06,
      "loss": 14.9347,
      "step": 50
    },
    {
      "epoch": 0.0031735537190082643,
      "grad_norm": 2530.3701171875,
      "learning_rate": 4.24e-06,
      "loss": 14.8024,
      "step": 60
    },
    {
      "epoch": 0.0037024793388429752,
      "grad_norm": 1678.7281494140625,
      "learning_rate": 5.04e-06,
      "loss": 14.6196,
      "step": 70
    },
    {
      "epoch": 0.004231404958677686,
      "grad_norm": 2254.43798828125,
      "learning_rate": 5.84e-06,
      "loss": 14.4786,
      "step": 80
    },
    {
      "epoch": 0.004760330578512397,
      "grad_norm": 2226.012939453125,
      "learning_rate": 6.640000000000001e-06,
      "loss": 14.3674,
      "step": 90
    },
    {
      "epoch": 0.005289256198347108,
      "grad_norm": 2211.912353515625,
      "learning_rate": 7.44e-06,
      "loss": 14.1906,
      "step": 100
    },
    {
      "epoch": 0.005818181818181818,
      "grad_norm": 3070.8232421875,
      "learning_rate": 8.24e-06,
      "loss": 14.1344,
      "step": 110
    },
    {
      "epoch": 0.006347107438016529,
      "grad_norm": 2257.41455078125,
      "learning_rate": 9.04e-06,
      "loss": 14.0681,
      "step": 120
    },
    {
      "epoch": 0.00687603305785124,
      "grad_norm": 2274.346435546875,
      "learning_rate": 9.84e-06,
      "loss": 13.9746,
      "step": 130
    },
    {
      "epoch": 0.0074049586776859504,
      "grad_norm": 2632.0341796875,
      "learning_rate": 1.064e-05,
      "loss": 13.9974,
      "step": 140
    },
    {
      "epoch": 0.007933884297520661,
      "grad_norm": 1979.03857421875,
      "learning_rate": 1.144e-05,
      "loss": 13.6573,
      "step": 150
    },
    {
      "epoch": 0.008462809917355372,
      "grad_norm": 1911.6646728515625,
      "learning_rate": 1.216e-05,
      "loss": 13.5115,
      "step": 160
    },
    {
      "epoch": 0.008991735537190083,
      "grad_norm": 1221.2379150390625,
      "learning_rate": 1.296e-05,
      "loss": 13.4189,
      "step": 170
    },
    {
      "epoch": 0.009520661157024794,
      "grad_norm": 1295.5301513671875,
      "learning_rate": 1.376e-05,
      "loss": 13.1649,
      "step": 180
    },
    {
      "epoch": 0.010049586776859505,
      "grad_norm": 1181.076904296875,
      "learning_rate": 1.4480000000000002e-05,
      "loss": 13.0769,
      "step": 190
    },
    {
      "epoch": 0.010578512396694216,
      "grad_norm": 1546.213623046875,
      "learning_rate": 1.528e-05,
      "loss": 12.981,
      "step": 200
    },
    {
      "epoch": 0.011107438016528925,
      "grad_norm": 1649.0814208984375,
      "learning_rate": 1.6080000000000002e-05,
      "loss": 12.9791,
      "step": 210
    },
    {
      "epoch": 0.011636363636363636,
      "grad_norm": 1149.5986328125,
      "learning_rate": 1.688e-05,
      "loss": 12.9944,
      "step": 220
    },
    {
      "epoch": 0.012165289256198347,
      "grad_norm": 1094.528564453125,
      "learning_rate": 1.7680000000000004e-05,
      "loss": 12.712,
      "step": 230
    },
    {
      "epoch": 0.012694214876033057,
      "grad_norm": 1151.943603515625,
      "learning_rate": 1.848e-05,
      "loss": 12.7007,
      "step": 240
    },
    {
      "epoch": 0.013223140495867768,
      "grad_norm": 756.9489135742188,
      "learning_rate": 1.9280000000000002e-05,
      "loss": 12.6777,
      "step": 250
    },
    {
      "epoch": 0.01375206611570248,
      "grad_norm": 1089.9005126953125,
      "learning_rate": 2.008e-05,
      "loss": 12.551,
      "step": 260
    },
    {
      "epoch": 0.01428099173553719,
      "grad_norm": 1578.2489013671875,
      "learning_rate": 2.0880000000000003e-05,
      "loss": 12.6069,
      "step": 270
    },
    {
      "epoch": 0.014809917355371901,
      "grad_norm": 622.3321533203125,
      "learning_rate": 2.168e-05,
      "loss": 12.4807,
      "step": 280
    },
    {
      "epoch": 0.015338842975206612,
      "grad_norm": 653.3980712890625,
      "learning_rate": 2.248e-05,
      "loss": 12.2924,
      "step": 290
    },
    {
      "epoch": 0.015867768595041323,
      "grad_norm": 580.5093994140625,
      "learning_rate": 2.328e-05,
      "loss": 12.2673,
      "step": 300
    },
    {
      "epoch": 0.016396694214876033,
      "grad_norm": 870.7935791015625,
      "learning_rate": 2.408e-05,
      "loss": 11.8822,
      "step": 310
    },
    {
      "epoch": 0.016925619834710744,
      "grad_norm": 451.5616760253906,
      "learning_rate": 2.488e-05,
      "loss": 11.7939,
      "step": 320
    },
    {
      "epoch": 0.017454545454545455,
      "grad_norm": 1039.074462890625,
      "learning_rate": 2.5679999999999998e-05,
      "loss": 11.7623,
      "step": 330
    },
    {
      "epoch": 0.017983471074380166,
      "grad_norm": 826.6625366210938,
      "learning_rate": 2.648e-05,
      "loss": 11.5301,
      "step": 340
    },
    {
      "epoch": 0.018512396694214877,
      "grad_norm": 375.2585144042969,
      "learning_rate": 2.728e-05,
      "loss": 11.6941,
      "step": 350
    },
    {
      "epoch": 0.019041322314049588,
      "grad_norm": 535.522705078125,
      "learning_rate": 2.8080000000000002e-05,
      "loss": 11.3719,
      "step": 360
    },
    {
      "epoch": 0.0195702479338843,
      "grad_norm": 608.0570678710938,
      "learning_rate": 2.888e-05,
      "loss": 11.2682,
      "step": 370
    },
    {
      "epoch": 0.02009917355371901,
      "grad_norm": 678.4328002929688,
      "learning_rate": 2.9680000000000004e-05,
      "loss": 11.3097,
      "step": 380
    },
    {
      "epoch": 0.02062809917355372,
      "grad_norm": 567.5283203125,
      "learning_rate": 3.0480000000000003e-05,
      "loss": 11.2014,
      "step": 390
    },
    {
      "epoch": 0.02115702479338843,
      "grad_norm": 382.2688293457031,
      "learning_rate": 3.1280000000000005e-05,
      "loss": 10.9673,
      "step": 400
    },
    {
      "epoch": 0.021685950413223142,
      "grad_norm": 599.6221923828125,
      "learning_rate": 3.208e-05,
      "loss": 10.981,
      "step": 410
    },
    {
      "epoch": 0.02221487603305785,
      "grad_norm": 382.1618957519531,
      "learning_rate": 3.288e-05,
      "loss": 10.9526,
      "step": 420
    },
    {
      "epoch": 0.02274380165289256,
      "grad_norm": 1082.0447998046875,
      "learning_rate": 3.368e-05,
      "loss": 10.9535,
      "step": 430
    },
    {
      "epoch": 0.02327272727272727,
      "grad_norm": 360.10101318359375,
      "learning_rate": 3.448e-05,
      "loss": 10.7087,
      "step": 440
    },
    {
      "epoch": 0.023801652892561982,
      "grad_norm": 460.0298156738281,
      "learning_rate": 3.528e-05,
      "loss": 10.8773,
      "step": 450
    },
    {
      "epoch": 0.024330578512396693,
      "grad_norm": 389.6498107910156,
      "learning_rate": 3.608e-05,
      "loss": 10.7515,
      "step": 460
    },
    {
      "epoch": 0.024859504132231404,
      "grad_norm": 511.04937744140625,
      "learning_rate": 3.6880000000000006e-05,
      "loss": 10.4311,
      "step": 470
    },
    {
      "epoch": 0.025388429752066115,
      "grad_norm": 277.2391052246094,
      "learning_rate": 3.7680000000000005e-05,
      "loss": 10.3949,
      "step": 480
    },
    {
      "epoch": 0.025917355371900826,
      "grad_norm": 345.6590270996094,
      "learning_rate": 3.848e-05,
      "loss": 10.3248,
      "step": 490
    },
    {
      "epoch": 0.026446280991735537,
      "grad_norm": 354.5246887207031,
      "learning_rate": 3.9280000000000003e-05,
      "loss": 10.4081,
      "step": 500
    },
    {
      "epoch": 0.026975206611570247,
      "grad_norm": 383.70745849609375,
      "learning_rate": 4.008e-05,
      "loss": 10.3949,
      "step": 510
    },
    {
      "epoch": 0.02750413223140496,
      "grad_norm": 661.0210571289062,
      "learning_rate": 4.088e-05,
      "loss": 10.3027,
      "step": 520
    },
    {
      "epoch": 0.02803305785123967,
      "grad_norm": 417.7251892089844,
      "learning_rate": 4.168e-05,
      "loss": 10.1894,
      "step": 530
    },
    {
      "epoch": 0.02856198347107438,
      "grad_norm": 282.77117919921875,
      "learning_rate": 4.248e-05,
      "loss": 10.0761,
      "step": 540
    },
    {
      "epoch": 0.02909090909090909,
      "grad_norm": 271.8935546875,
      "learning_rate": 4.3280000000000006e-05,
      "loss": 10.083,
      "step": 550
    },
    {
      "epoch": 0.029619834710743802,
      "grad_norm": 308.1956787109375,
      "learning_rate": 4.4080000000000005e-05,
      "loss": 10.0744,
      "step": 560
    },
    {
      "epoch": 0.030148760330578513,
      "grad_norm": 331.1837463378906,
      "learning_rate": 4.488e-05,
      "loss": 9.9295,
      "step": 570
    },
    {
      "epoch": 0.030677685950413223,
      "grad_norm": 341.76824951171875,
      "learning_rate": 4.568e-05,
      "loss": 10.005,
      "step": 580
    },
    {
      "epoch": 0.031206611570247934,
      "grad_norm": 403.6604919433594,
      "learning_rate": 4.648e-05,
      "loss": 9.9016,
      "step": 590
    },
    {
      "epoch": 0.031735537190082645,
      "grad_norm": 246.0824432373047,
      "learning_rate": 4.728e-05,
      "loss": 10.0205,
      "step": 600
    },
    {
      "epoch": 0.032264462809917356,
      "grad_norm": 259.1653137207031,
      "learning_rate": 4.808e-05,
      "loss": 9.9739,
      "step": 610
    },
    {
      "epoch": 0.03279338842975207,
      "grad_norm": 222.7213592529297,
      "learning_rate": 4.8880000000000006e-05,
      "loss": 9.8544,
      "step": 620
    },
    {
      "epoch": 0.03332231404958678,
      "grad_norm": 314.3382568359375,
      "learning_rate": 4.9680000000000005e-05,
      "loss": 9.7755,
      "step": 630
    },
    {
      "epoch": 0.03385123966942149,
      "grad_norm": 287.65570068359375,
      "learning_rate": 5.0480000000000005e-05,
      "loss": 9.7856,
      "step": 640
    },
    {
      "epoch": 0.0343801652892562,
      "grad_norm": 273.3498229980469,
      "learning_rate": 5.1280000000000004e-05,
      "loss": 9.6916,
      "step": 650
    },
    {
      "epoch": 0.03490909090909091,
      "grad_norm": 196.19595336914062,
      "learning_rate": 5.208000000000001e-05,
      "loss": 9.7167,
      "step": 660
    },
    {
      "epoch": 0.03543801652892562,
      "grad_norm": 370.2161865234375,
      "learning_rate": 5.288000000000001e-05,
      "loss": 9.4405,
      "step": 670
    },
    {
      "epoch": 0.03596694214876033,
      "grad_norm": 235.0204620361328,
      "learning_rate": 5.368000000000001e-05,
      "loss": 9.7401,
      "step": 680
    },
    {
      "epoch": 0.03649586776859504,
      "grad_norm": 250.4844207763672,
      "learning_rate": 5.448e-05,
      "loss": 9.5492,
      "step": 690
    },
    {
      "epoch": 0.037024793388429754,
      "grad_norm": 209.03860473632812,
      "learning_rate": 5.528e-05,
      "loss": 9.4078,
      "step": 700
    }
  ],
  "logging_steps": 10,
  "max_steps": 10000000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 529,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.17434646368256e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}