{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05735918320523116,
  "eval_steps": 10,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001147183664104623,
      "eval_loss": 1.873344898223877,
      "eval_runtime": 12.7647,
      "eval_samples_per_second": 515.797,
      "eval_steps_per_second": 8.069,
      "step": 10
    },
    {
      "epoch": 0.002294367328209246,
      "eval_loss": 1.8726389408111572,
      "eval_runtime": 12.8667,
      "eval_samples_per_second": 511.709,
      "eval_steps_per_second": 8.005,
      "step": 20
    },
    {
      "epoch": 0.0034415509923138693,
      "eval_loss": 1.8714078664779663,
      "eval_runtime": 12.9103,
      "eval_samples_per_second": 509.979,
      "eval_steps_per_second": 7.978,
      "step": 30
    },
    {
      "epoch": 0.004588734656418492,
      "eval_loss": 1.8696790933609009,
      "eval_runtime": 12.947,
      "eval_samples_per_second": 508.534,
      "eval_steps_per_second": 7.955,
      "step": 40
    },
    {
      "epoch": 0.0057359183205231154,
      "eval_loss": 1.8675329685211182,
      "eval_runtime": 12.9458,
      "eval_samples_per_second": 508.582,
      "eval_steps_per_second": 7.956,
      "step": 50
    },
    {
      "epoch": 0.006883101984627739,
      "eval_loss": 1.8649154901504517,
      "eval_runtime": 13.0432,
      "eval_samples_per_second": 504.785,
      "eval_steps_per_second": 7.897,
      "step": 60
    },
    {
      "epoch": 0.008030285648732363,
      "eval_loss": 1.8619294166564941,
      "eval_runtime": 13.0638,
      "eval_samples_per_second": 503.988,
      "eval_steps_per_second": 7.884,
      "step": 70
    },
    {
      "epoch": 0.009177469312836984,
      "eval_loss": 1.8583979606628418,
      "eval_runtime": 13.0482,
      "eval_samples_per_second": 504.592,
      "eval_steps_per_second": 7.894,
      "step": 80
    },
    {
      "epoch": 0.010324652976941608,
      "eval_loss": 1.85438871383667,
      "eval_runtime": 13.0615,
      "eval_samples_per_second": 504.075,
      "eval_steps_per_second": 7.886,
      "step": 90
    },
    {
      "epoch": 0.011471836641046231,
      "grad_norm": 9.938580513000488,
      "learning_rate": 3.8226299694189603e-07,
      "loss": 3.1046,
      "step": 100
    },
    {
      "epoch": 0.011471836641046231,
      "eval_loss": 1.849947214126587,
      "eval_runtime": 13.0663,
      "eval_samples_per_second": 503.89,
      "eval_steps_per_second": 7.883,
      "step": 100
    },
    {
      "epoch": 0.012619020305150854,
      "eval_loss": 1.8451412916183472,
      "eval_runtime": 12.9771,
      "eval_samples_per_second": 507.357,
      "eval_steps_per_second": 7.937,
      "step": 110
    },
    {
      "epoch": 0.013766203969255477,
      "eval_loss": 1.8399487733840942,
      "eval_runtime": 13.0209,
      "eval_samples_per_second": 505.648,
      "eval_steps_per_second": 7.91,
      "step": 120
    },
    {
      "epoch": 0.0149133876333601,
      "eval_loss": 1.8342881202697754,
      "eval_runtime": 13.0369,
      "eval_samples_per_second": 505.028,
      "eval_steps_per_second": 7.901,
      "step": 130
    },
    {
      "epoch": 0.016060571297464726,
      "eval_loss": 1.8283486366271973,
      "eval_runtime": 13.0149,
      "eval_samples_per_second": 505.88,
      "eval_steps_per_second": 7.914,
      "step": 140
    },
    {
      "epoch": 0.017207754961569347,
      "eval_loss": 1.822334885597229,
      "eval_runtime": 13.0213,
      "eval_samples_per_second": 505.632,
      "eval_steps_per_second": 7.91,
      "step": 150
    },
    {
      "epoch": 0.01835493862567397,
      "eval_loss": 1.8158738613128662,
      "eval_runtime": 13.0599,
      "eval_samples_per_second": 504.14,
      "eval_steps_per_second": 7.887,
      "step": 160
    },
    {
      "epoch": 0.019502122289778594,
      "eval_loss": 1.8090614080429077,
      "eval_runtime": 13.034,
      "eval_samples_per_second": 505.14,
      "eval_steps_per_second": 7.902,
      "step": 170
    },
    {
      "epoch": 0.020649305953883215,
      "eval_loss": 1.8015782833099365,
      "eval_runtime": 13.0665,
      "eval_samples_per_second": 503.885,
      "eval_steps_per_second": 7.883,
      "step": 180
    },
    {
      "epoch": 0.02179648961798784,
      "eval_loss": 1.793796420097351,
      "eval_runtime": 13.0555,
      "eval_samples_per_second": 504.31,
      "eval_steps_per_second": 7.889,
      "step": 190
    },
    {
      "epoch": 0.022943673282092462,
      "grad_norm": 4.906337738037109,
      "learning_rate": 7.645259938837921e-07,
      "loss": 3.0303,
      "step": 200
    },
    {
      "epoch": 0.022943673282092462,
      "eval_loss": 1.785815715789795,
      "eval_runtime": 12.9925,
      "eval_samples_per_second": 506.754,
      "eval_steps_per_second": 7.928,
      "step": 200
    },
    {
      "epoch": 0.024090856946197087,
      "eval_loss": 1.7775053977966309,
      "eval_runtime": 13.0639,
      "eval_samples_per_second": 503.986,
      "eval_steps_per_second": 7.884,
      "step": 210
    },
    {
      "epoch": 0.025238040610301708,
      "eval_loss": 1.7692992687225342,
      "eval_runtime": 13.0129,
      "eval_samples_per_second": 505.96,
      "eval_steps_per_second": 7.915,
      "step": 220
    },
    {
      "epoch": 0.026385224274406333,
      "eval_loss": 1.760453224182129,
      "eval_runtime": 13.0078,
      "eval_samples_per_second": 506.158,
      "eval_steps_per_second": 7.918,
      "step": 230
    },
    {
      "epoch": 0.027532407938510955,
      "eval_loss": 1.751396656036377,
      "eval_runtime": 12.9957,
      "eval_samples_per_second": 506.628,
      "eval_steps_per_second": 7.926,
      "step": 240
    },
    {
      "epoch": 0.02867959160261558,
      "eval_loss": 1.7417218685150146,
      "eval_runtime": 12.9774,
      "eval_samples_per_second": 507.344,
      "eval_steps_per_second": 7.937,
      "step": 250
    },
    {
      "epoch": 0.0298267752667202,
      "eval_loss": 1.7319914102554321,
      "eval_runtime": 13.0219,
      "eval_samples_per_second": 505.611,
      "eval_steps_per_second": 7.91,
      "step": 260
    },
    {
      "epoch": 0.030973958930824826,
      "eval_loss": 1.7227253913879395,
      "eval_runtime": 13.0026,
      "eval_samples_per_second": 506.361,
      "eval_steps_per_second": 7.922,
      "step": 270
    },
    {
      "epoch": 0.03212114259492945,
      "eval_loss": 1.7133797407150269,
      "eval_runtime": 12.9757,
      "eval_samples_per_second": 507.409,
      "eval_steps_per_second": 7.938,
      "step": 280
    },
    {
      "epoch": 0.03326832625903407,
      "eval_loss": 1.704041600227356,
      "eval_runtime": 12.9845,
      "eval_samples_per_second": 507.065,
      "eval_steps_per_second": 7.933,
      "step": 290
    },
    {
      "epoch": 0.034415509923138694,
      "grad_norm": 4.665822505950928,
      "learning_rate": 1.1467889908256882e-06,
      "loss": 2.9459,
      "step": 300
    },
    {
      "epoch": 0.034415509923138694,
      "eval_loss": 1.6940686702728271,
      "eval_runtime": 13.0019,
      "eval_samples_per_second": 506.387,
      "eval_steps_per_second": 7.922,
      "step": 300
    },
    {
      "epoch": 0.035562693587243316,
      "eval_loss": 1.683342695236206,
      "eval_runtime": 13.0065,
      "eval_samples_per_second": 506.209,
      "eval_steps_per_second": 7.919,
      "step": 310
    },
    {
      "epoch": 0.03670987725134794,
      "eval_loss": 1.6724653244018555,
      "eval_runtime": 13.0129,
      "eval_samples_per_second": 505.96,
      "eval_steps_per_second": 7.915,
      "step": 320
    },
    {
      "epoch": 0.037857060915452566,
      "eval_loss": 1.6614341735839844,
      "eval_runtime": 12.9921,
      "eval_samples_per_second": 506.769,
      "eval_steps_per_second": 7.928,
      "step": 330
    },
    {
      "epoch": 0.03900424457955719,
      "eval_loss": 1.6510112285614014,
      "eval_runtime": 13.0242,
      "eval_samples_per_second": 505.52,
      "eval_steps_per_second": 7.908,
      "step": 340
    },
    {
      "epoch": 0.04015142824366181,
      "eval_loss": 1.6401513814926147,
      "eval_runtime": 12.9214,
      "eval_samples_per_second": 509.542,
      "eval_steps_per_second": 7.971,
      "step": 350
    },
    {
      "epoch": 0.04129861190776643,
      "eval_loss": 1.6295816898345947,
      "eval_runtime": 12.9563,
      "eval_samples_per_second": 508.171,
      "eval_steps_per_second": 7.95,
      "step": 360
    },
    {
      "epoch": 0.04244579557187106,
      "eval_loss": 1.6187150478363037,
      "eval_runtime": 12.9758,
      "eval_samples_per_second": 507.405,
      "eval_steps_per_second": 7.938,
      "step": 370
    },
    {
      "epoch": 0.04359297923597568,
      "eval_loss": 1.607272982597351,
      "eval_runtime": 12.9876,
      "eval_samples_per_second": 506.947,
      "eval_steps_per_second": 7.931,
      "step": 380
    },
    {
      "epoch": 0.0447401629000803,
      "eval_loss": 1.5961676836013794,
      "eval_runtime": 12.9782,
      "eval_samples_per_second": 507.313,
      "eval_steps_per_second": 7.936,
      "step": 390
    },
    {
      "epoch": 0.045887346564184923,
      "grad_norm": 4.870114326477051,
      "learning_rate": 1.5290519877675841e-06,
      "loss": 2.7813,
      "step": 400
    },
    {
      "epoch": 0.045887346564184923,
      "eval_loss": 1.5848218202590942,
      "eval_runtime": 12.9783,
      "eval_samples_per_second": 507.309,
      "eval_steps_per_second": 7.936,
      "step": 400
    },
    {
      "epoch": 0.04703453022828955,
      "eval_loss": 1.5734797716140747,
      "eval_runtime": 12.9739,
      "eval_samples_per_second": 507.482,
      "eval_steps_per_second": 7.939,
      "step": 410
    },
    {
      "epoch": 0.04818171389239417,
      "eval_loss": 1.562021255493164,
      "eval_runtime": 12.9388,
      "eval_samples_per_second": 508.855,
      "eval_steps_per_second": 7.961,
      "step": 420
    },
    {
      "epoch": 0.049328897556498795,
      "eval_loss": 1.5495364665985107,
      "eval_runtime": 12.9412,
      "eval_samples_per_second": 508.764,
      "eval_steps_per_second": 7.959,
      "step": 430
    },
    {
      "epoch": 0.050476081220603417,
      "eval_loss": 1.5375314950942993,
      "eval_runtime": 12.9686,
      "eval_samples_per_second": 507.687,
      "eval_steps_per_second": 7.942,
      "step": 440
    },
    {
      "epoch": 0.051623264884708045,
      "eval_loss": 1.525598168373108,
      "eval_runtime": 12.9695,
      "eval_samples_per_second": 507.651,
      "eval_steps_per_second": 7.942,
      "step": 450
    },
    {
      "epoch": 0.052770448548812667,
      "eval_loss": 1.5132672786712646,
      "eval_runtime": 12.8961,
      "eval_samples_per_second": 510.543,
      "eval_steps_per_second": 7.987,
      "step": 460
    },
    {
      "epoch": 0.05391763221291729,
      "eval_loss": 1.5012215375900269,
      "eval_runtime": 12.9428,
      "eval_samples_per_second": 508.7,
      "eval_steps_per_second": 7.958,
      "step": 470
    },
    {
      "epoch": 0.05506481587702191,
      "eval_loss": 1.4892219305038452,
      "eval_runtime": 12.9208,
      "eval_samples_per_second": 509.567,
      "eval_steps_per_second": 7.972,
      "step": 480
    },
    {
      "epoch": 0.05621199954112653,
      "eval_loss": 1.4768636226654053,
      "eval_runtime": 12.9423,
      "eval_samples_per_second": 508.721,
      "eval_steps_per_second": 7.958,
      "step": 490
    },
    {
      "epoch": 0.05735918320523116,
      "grad_norm": 4.155641555786133,
      "learning_rate": 1.9113149847094803e-06,
      "loss": 2.6308,
      "step": 500
    },
    {
      "epoch": 0.05735918320523116,
      "eval_loss": 1.4640088081359863,
      "eval_runtime": 12.8729,
      "eval_samples_per_second": 511.462,
      "eval_steps_per_second": 8.001,
      "step": 500
    }
  ],
  "logging_steps": 100,
  "max_steps": 26151,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}