{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.14698934327261273,
  "eval_steps": 500,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002099847761037325,
      "grad_norm": 19872.2890625,
      "learning_rate": 3e-07,
      "loss": 8.7939,
      "step": 10
    },
    {
      "epoch": 0.00419969552207465,
      "grad_norm": 1458.198974609375,
      "learning_rate": 1.2999999999999998e-06,
      "loss": 8.1117,
      "step": 20
    },
    {
      "epoch": 0.006299543283111974,
      "grad_norm": 297.6234130859375,
      "learning_rate": 2.2999999999999996e-06,
      "loss": 7.3977,
      "step": 30
    },
    {
      "epoch": 0.0083993910441493,
      "grad_norm": 426.92987060546875,
      "learning_rate": 3.2999999999999993e-06,
      "loss": 7.2069,
      "step": 40
    },
    {
      "epoch": 0.010499238805186623,
      "grad_norm": 474.7532653808594,
      "learning_rate": 4.2999999999999995e-06,
      "loss": 7.08,
      "step": 50
    },
    {
      "epoch": 0.012599086566223949,
      "grad_norm": 1569.4381103515625,
      "learning_rate": 5.3e-06,
      "loss": 7.0092,
      "step": 60
    },
    {
      "epoch": 0.014698934327261274,
      "grad_norm": 1407.21142578125,
      "learning_rate": 6.3e-06,
      "loss": 6.9929,
      "step": 70
    },
    {
      "epoch": 0.0167987820882986,
      "grad_norm": 500.49493408203125,
      "learning_rate": 7.299999999999999e-06,
      "loss": 6.9501,
      "step": 80
    },
    {
      "epoch": 0.018898629849335925,
      "grad_norm": 442.69537353515625,
      "learning_rate": 8.299999999999998e-06,
      "loss": 6.9001,
      "step": 90
    },
    {
      "epoch": 0.020998477610373247,
      "grad_norm": 1423.2950439453125,
      "learning_rate": 9.299999999999999e-06,
      "loss": 6.9037,
      "step": 100
    },
    {
      "epoch": 0.023098325371410572,
      "grad_norm": 448.7774963378906,
      "learning_rate": 1.03e-05,
      "loss": 6.8732,
      "step": 110
    },
    {
      "epoch": 0.025198173132447897,
      "grad_norm": 711.8992919921875,
      "learning_rate": 1.1299999999999999e-05,
      "loss": 6.8381,
      "step": 120
    },
    {
      "epoch": 0.027298020893485223,
      "grad_norm": 884.006591796875,
      "learning_rate": 1.2299999999999999e-05,
      "loss": 6.8462,
      "step": 130
    },
    {
      "epoch": 0.029397868654522548,
      "grad_norm": 96.5859375,
      "learning_rate": 1.33e-05,
      "loss": 6.8433,
      "step": 140
    },
    {
      "epoch": 0.03149771641555987,
      "grad_norm": 91.52490997314453,
      "learning_rate": 1.43e-05,
      "loss": 6.8171,
      "step": 150
    },
    {
      "epoch": 0.0335975641765972,
      "grad_norm": 354.9374084472656,
      "learning_rate": 1.53e-05,
      "loss": 6.7899,
      "step": 160
    },
    {
      "epoch": 0.035697411937634524,
      "grad_norm": 189.09506225585938,
      "learning_rate": 1.6299999999999996e-05,
      "loss": 6.7456,
      "step": 170
    },
    {
      "epoch": 0.03779725969867185,
      "grad_norm": 170.39376831054688,
      "learning_rate": 1.7299999999999997e-05,
      "loss": 6.7505,
      "step": 180
    },
    {
      "epoch": 0.03989710745970917,
      "grad_norm": 193.9166259765625,
      "learning_rate": 1.8299999999999998e-05,
      "loss": 6.752,
      "step": 190
    },
    {
      "epoch": 0.04199695522074649,
      "grad_norm": 336.08624267578125,
      "learning_rate": 1.93e-05,
      "loss": 6.7015,
      "step": 200
    },
    {
      "epoch": 0.04409680298178382,
      "grad_norm": 307.40557861328125,
      "learning_rate": 2.03e-05,
      "loss": 6.7024,
      "step": 210
    },
    {
      "epoch": 0.046196650742821144,
      "grad_norm": 175.94061279296875,
      "learning_rate": 2.1299999999999996e-05,
      "loss": 6.6639,
      "step": 220
    },
    {
      "epoch": 0.04829649850385847,
      "grad_norm": 496.3529052734375,
      "learning_rate": 2.23e-05,
      "loss": 6.6309,
      "step": 230
    },
    {
      "epoch": 0.050396346264895794,
      "grad_norm": 112.63114929199219,
      "learning_rate": 2.3299999999999997e-05,
      "loss": 6.6146,
      "step": 240
    },
    {
      "epoch": 0.05249619402593312,
      "grad_norm": 141.9170379638672,
      "learning_rate": 2.4299999999999998e-05,
      "loss": 6.6386,
      "step": 250
    },
    {
      "epoch": 0.054596041786970445,
      "grad_norm": 120.92185974121094,
      "learning_rate": 2.53e-05,
      "loss": 6.6323,
      "step": 260
    },
    {
      "epoch": 0.05669588954800777,
      "grad_norm": 241.84129333496094,
      "learning_rate": 2.63e-05,
      "loss": 6.598,
      "step": 270
    },
    {
      "epoch": 0.058795737309045096,
      "grad_norm": 115.57807159423828,
      "learning_rate": 2.7299999999999996e-05,
      "loss": 6.5549,
      "step": 280
    },
    {
      "epoch": 0.06089558507008242,
      "grad_norm": 99.67350769042969,
      "learning_rate": 2.83e-05,
      "loss": 6.5484,
      "step": 290
    },
    {
      "epoch": 0.06299543283111975,
      "grad_norm": 105.20110321044922,
      "learning_rate": 2.9299999999999997e-05,
      "loss": 6.5416,
      "step": 300
    },
    {
      "epoch": 0.06509528059215706,
      "grad_norm": 207.86203002929688,
      "learning_rate": 3.0299999999999998e-05,
      "loss": 6.5463,
      "step": 310
    },
    {
      "epoch": 0.0671951283531944,
      "grad_norm": 125.6773910522461,
      "learning_rate": 3.1299999999999995e-05,
      "loss": 6.4848,
      "step": 320
    },
    {
      "epoch": 0.06929497611423172,
      "grad_norm": 121.31608581542969,
      "learning_rate": 3.229999999999999e-05,
      "loss": 6.4763,
      "step": 330
    },
    {
      "epoch": 0.07139482387526905,
      "grad_norm": 86.57124328613281,
      "learning_rate": 3.3299999999999996e-05,
      "loss": 6.4579,
      "step": 340
    },
    {
      "epoch": 0.07349467163630637,
      "grad_norm": 105.74996948242188,
      "learning_rate": 3.4299999999999993e-05,
      "loss": 6.408,
      "step": 350
    },
    {
      "epoch": 0.0755945193973437,
      "grad_norm": 68.95454406738281,
      "learning_rate": 3.53e-05,
      "loss": 6.3928,
      "step": 360
    },
    {
      "epoch": 0.07769436715838102,
      "grad_norm": 107.94305419921875,
      "learning_rate": 3.6299999999999995e-05,
      "loss": 6.3853,
      "step": 370
    },
    {
      "epoch": 0.07979421491941834,
      "grad_norm": 136.39556884765625,
      "learning_rate": 3.73e-05,
      "loss": 6.3639,
      "step": 380
    },
    {
      "epoch": 0.08189406268045567,
      "grad_norm": 152.05712890625,
      "learning_rate": 3.83e-05,
      "loss": 6.348,
      "step": 390
    },
    {
      "epoch": 0.08399391044149299,
      "grad_norm": 139.25466918945312,
      "learning_rate": 3.93e-05,
      "loss": 6.3261,
      "step": 400
    },
    {
      "epoch": 0.08609375820253032,
      "grad_norm": 130.061279296875,
      "learning_rate": 4.03e-05,
      "loss": 6.2809,
      "step": 410
    },
    {
      "epoch": 0.08819360596356764,
      "grad_norm": 115.39459991455078,
      "learning_rate": 4.1299999999999994e-05,
      "loss": 6.2646,
      "step": 420
    },
    {
      "epoch": 0.09029345372460497,
      "grad_norm": 50.863616943359375,
      "learning_rate": 4.229999999999999e-05,
      "loss": 6.2808,
      "step": 430
    },
    {
      "epoch": 0.09239330148564229,
      "grad_norm": 113.06661987304688,
      "learning_rate": 4.3299999999999995e-05,
      "loss": 6.2387,
      "step": 440
    },
    {
      "epoch": 0.09449314924667962,
      "grad_norm": 202.89398193359375,
      "learning_rate": 4.43e-05,
      "loss": 6.2476,
      "step": 450
    },
    {
      "epoch": 0.09659299700771694,
      "grad_norm": 154.97865295410156,
      "learning_rate": 4.5299999999999997e-05,
      "loss": 6.2345,
      "step": 460
    },
    {
      "epoch": 0.09869284476875427,
      "grad_norm": 72.81023406982422,
      "learning_rate": 4.6299999999999994e-05,
      "loss": 6.1687,
      "step": 470
    },
    {
      "epoch": 0.10079269252979159,
      "grad_norm": 101.40583801269531,
      "learning_rate": 4.73e-05,
      "loss": 6.1705,
      "step": 480
    },
    {
      "epoch": 0.10289254029082892,
      "grad_norm": 80.50221252441406,
      "learning_rate": 4.8299999999999995e-05,
      "loss": 6.1665,
      "step": 490
    },
    {
      "epoch": 0.10499238805186624,
      "grad_norm": 91.6736068725586,
      "learning_rate": 4.929999999999999e-05,
      "loss": 6.1587,
      "step": 500
    },
    {
      "epoch": 0.10709223581290356,
      "grad_norm": 253.29408264160156,
      "learning_rate": 5.0299999999999996e-05,
      "loss": 6.1218,
      "step": 510
    },
    {
      "epoch": 0.10919208357394089,
      "grad_norm": 117.43933868408203,
      "learning_rate": 5.13e-05,
      "loss": 6.1313,
      "step": 520
    },
    {
      "epoch": 0.11129193133497821,
      "grad_norm": 69.32656860351562,
      "learning_rate": 5.23e-05,
      "loss": 6.1038,
      "step": 530
    },
    {
      "epoch": 0.11339177909601554,
      "grad_norm": 85.16144561767578,
      "learning_rate": 5.3299999999999995e-05,
      "loss": 6.0745,
      "step": 540
    },
    {
      "epoch": 0.11549162685705286,
      "grad_norm": 67.62905883789062,
      "learning_rate": 5.429999999999999e-05,
      "loss": 6.0786,
      "step": 550
    },
    {
      "epoch": 0.11759147461809019,
      "grad_norm": 103.80160522460938,
      "learning_rate": 5.529999999999999e-05,
      "loss": 6.0472,
      "step": 560
    },
    {
      "epoch": 0.11969132237912751,
      "grad_norm": 45.10822677612305,
      "learning_rate": 5.63e-05,
      "loss": 6.0311,
      "step": 570
    },
    {
      "epoch": 0.12179117014016484,
      "grad_norm": 59.20137023925781,
      "learning_rate": 5.73e-05,
      "loss": 6.0219,
      "step": 580
    },
    {
      "epoch": 0.12389101790120216,
      "grad_norm": 49.00022506713867,
      "learning_rate": 5.8299999999999994e-05,
      "loss": 6.0013,
      "step": 590
    },
    {
      "epoch": 0.1259908656622395,
      "grad_norm": 50.88911437988281,
      "learning_rate": 5.929999999999999e-05,
      "loss": 5.981,
      "step": 600
    },
    {
      "epoch": 0.12809071342327683,
      "grad_norm": 43.3376579284668,
      "learning_rate": 6.0299999999999995e-05,
      "loss": 5.9482,
      "step": 610
    },
    {
      "epoch": 0.13019056118431413,
      "grad_norm": 54.567779541015625,
      "learning_rate": 6.13e-05,
      "loss": 5.9478,
      "step": 620
    },
    {
      "epoch": 0.13229040894535146,
      "grad_norm": 51.82001495361328,
      "learning_rate": 6.23e-05,
      "loss": 5.9583,
      "step": 630
    },
    {
      "epoch": 0.1343902567063888,
      "grad_norm": 65.38532257080078,
      "learning_rate": 6.33e-05,
      "loss": 5.9228,
      "step": 640
    },
    {
      "epoch": 0.1364901044674261,
      "grad_norm": 47.24418640136719,
      "learning_rate": 6.429999999999999e-05,
      "loss": 5.8942,
      "step": 650
    },
    {
      "epoch": 0.13858995222846343,
      "grad_norm": 39.78090286254883,
      "learning_rate": 6.53e-05,
      "loss": 5.8764,
      "step": 660
    },
    {
      "epoch": 0.14068979998950076,
      "grad_norm": 59.94386672973633,
      "learning_rate": 6.63e-05,
      "loss": 5.8611,
      "step": 670
    },
    {
      "epoch": 0.1427896477505381,
      "grad_norm": 50.66661071777344,
      "learning_rate": 6.73e-05,
      "loss": 5.8163,
      "step": 680
    },
    {
      "epoch": 0.1448894955115754,
      "grad_norm": 59.74818801879883,
      "learning_rate": 6.829999999999999e-05,
      "loss": 5.8398,
      "step": 690
    },
    {
      "epoch": 0.14698934327261273,
      "grad_norm": 53.87904739379883,
      "learning_rate": 6.93e-05,
      "loss": 5.7908,
      "step": 700
    }
  ],
  "logging_steps": 10,
  "max_steps": 100000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 21,
  "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": 4.56474459181056e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}