{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16666666666666666,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "grad_norm": 0.16593393683433533,
      "learning_rate": 6e-06,
      "loss": 1.2019,
      "step": 10
    },
    {
      "grad_norm": 0.2364676296710968,
      "learning_rate": 1.2666666666666668e-05,
      "loss": 1.2001,
      "step": 20
    },
    {
      "grad_norm": 0.3223605155944824,
      "learning_rate": 1.9333333333333333e-05,
      "loss": 1.1652,
      "step": 30
    },
    {
      "grad_norm": 0.288097620010376,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.1203,
      "step": 40
    },
    {
      "grad_norm": 0.2957666516304016,
      "learning_rate": 3.266666666666667e-05,
      "loss": 1.1073,
      "step": 50
    },
    {
      "grad_norm": 0.3105441927909851,
      "learning_rate": 3.933333333333333e-05,
      "loss": 1.0981,
      "step": 60
    },
    {
      "grad_norm": 0.2903534770011902,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.0992,
      "step": 70
    },
    {
      "grad_norm": 0.2657025158405304,
      "learning_rate": 5.266666666666666e-05,
      "loss": 1.0949,
      "step": 80
    },
    {
      "grad_norm": 0.22208809852600098,
      "learning_rate": 5.9333333333333343e-05,
      "loss": 1.0883,
      "step": 90
    },
    {
      "grad_norm": 0.32055118680000305,
      "learning_rate": 6.6e-05,
      "loss": 1.0812,
      "step": 100
    },
    {
      "grad_norm": 0.2965445816516876,
      "learning_rate": 7.266666666666667e-05,
      "loss": 1.0723,
      "step": 110
    },
    {
      "grad_norm": 0.3756393790245056,
      "learning_rate": 7.933333333333334e-05,
      "loss": 1.0464,
      "step": 120
    },
    {
      "grad_norm": 0.5002507567405701,
      "learning_rate": 8.6e-05,
      "loss": 1.0023,
      "step": 130
    },
    {
      "grad_norm": 0.4813876152038574,
      "learning_rate": 9.266666666666666e-05,
      "loss": 0.9625,
      "step": 140
    },
    {
      "grad_norm": 0.513647198677063,
      "learning_rate": 9.933333333333334e-05,
      "loss": 0.9308,
      "step": 150
    },
    {
      "grad_norm": 0.8362369537353516,
      "learning_rate": 9.999753945398704e-05,
      "loss": 0.8938,
      "step": 160
    },
    {
      "grad_norm": 0.5613930821418762,
      "learning_rate": 9.998903417374228e-05,
      "loss": 0.862,
      "step": 170
    },
    {
      "grad_norm": 0.5763223767280579,
      "learning_rate": 9.997445481536973e-05,
      "loss": 0.8221,
      "step": 180
    },
    {
      "grad_norm": 0.5941640734672546,
      "learning_rate": 9.995380315038119e-05,
      "loss": 0.7922,
      "step": 190
    },
    {
      "grad_norm": 0.7477675080299377,
      "learning_rate": 9.99270816881235e-05,
      "loss": 0.7702,
      "step": 200
    },
    {
      "grad_norm": 0.5304926633834839,
      "learning_rate": 9.989429367547377e-05,
      "loss": 0.7553,
      "step": 210
    },
    {
      "grad_norm": 0.5700099468231201,
      "learning_rate": 9.985544309644475e-05,
      "loss": 0.7369,
      "step": 220
    },
    {
      "grad_norm": 0.7928358316421509,
      "learning_rate": 9.98105346717008e-05,
      "loss": 0.7222,
      "step": 230
    },
    {
      "grad_norm": 0.7667017579078674,
      "learning_rate": 9.97595738579843e-05,
      "loss": 0.7114,
      "step": 240
    },
    {
      "grad_norm": 0.5060045123100281,
      "learning_rate": 9.970256684745258e-05,
      "loss": 0.6861,
      "step": 250
    },
    {
      "grad_norm": 0.6732467412948608,
      "learning_rate": 9.963952056692549e-05,
      "loss": 0.675,
      "step": 260
    },
    {
      "grad_norm": 0.6021248698234558,
      "learning_rate": 9.957044267704384e-05,
      "loss": 0.6767,
      "step": 270
    },
    {
      "grad_norm": 0.6704761981964111,
      "learning_rate": 9.949534157133844e-05,
      "loss": 0.6512,
      "step": 280
    },
    {
      "grad_norm": 0.7285646200180054,
      "learning_rate": 9.941422637521035e-05,
      "loss": 0.6512,
      "step": 290
    },
    {
      "grad_norm": 0.7110922336578369,
      "learning_rate": 9.932710694482191e-05,
      "loss": 0.6196,
      "step": 300
    },
    {
      "grad_norm": 0.6850391626358032,
      "learning_rate": 9.923399386589933e-05,
      "loss": 0.6118,
      "step": 310
    },
    {
      "grad_norm": 0.6997315883636475,
      "learning_rate": 9.913489845244626e-05,
      "loss": 0.5941,
      "step": 320
    },
    {
      "grad_norm": 0.760143518447876,
      "learning_rate": 9.902983274536912e-05,
      "loss": 0.5891,
      "step": 330
    },
    {
      "grad_norm": 0.759657084941864,
      "learning_rate": 9.891880951101407e-05,
      "loss": 0.5812,
      "step": 340
    },
    {
      "grad_norm": 0.8276827931404114,
      "learning_rate": 9.880184223961573e-05,
      "loss": 0.5674,
      "step": 350
    },
    {
      "grad_norm": 0.5555763244628906,
      "learning_rate": 9.867894514365802e-05,
      "loss": 0.5544,
      "step": 360
    },
    {
      "grad_norm": 0.6141887307167053,
      "learning_rate": 9.855013315614725e-05,
      "loss": 0.5504,
      "step": 370
    },
    {
      "grad_norm": 0.7782378792762756,
      "learning_rate": 9.841542192879762e-05,
      "loss": 0.5447,
      "step": 380
    },
    {
      "grad_norm": 0.8065223693847656,
      "learning_rate": 9.82748278301294e-05,
      "loss": 0.5435,
      "step": 390
    },
    {
      "grad_norm": 0.7179561257362366,
      "learning_rate": 9.812836794348004e-05,
      "loss": 0.5344,
      "step": 400
    },
    {
      "grad_norm": 0.7837668657302856,
      "learning_rate": 9.797606006492841e-05,
      "loss": 0.5249,
      "step": 410
    },
    {
      "grad_norm": 0.7675067782402039,
      "learning_rate": 9.781792270113241e-05,
      "loss": 0.5199,
      "step": 420
    },
    {
      "grad_norm": 0.8279472589492798,
      "learning_rate": 9.765397506708023e-05,
      "loss": 0.5071,
      "step": 430
    },
    {
      "grad_norm": 0.8260670304298401,
      "learning_rate": 9.748423708375563e-05,
      "loss": 0.4926,
      "step": 440
    },
    {
      "grad_norm": 0.881014347076416,
      "learning_rate": 9.730872937571739e-05,
      "loss": 0.4907,
      "step": 450
    },
    {
      "grad_norm": 0.9371006488800049,
      "learning_rate": 9.712747326859315e-05,
      "loss": 0.4815,
      "step": 460
    },
    {
      "grad_norm": 0.8164715766906738,
      "learning_rate": 9.69404907864883e-05,
      "loss": 0.4755,
      "step": 470
    },
    {
      "grad_norm": 0.7007074952125549,
      "learning_rate": 9.674780464930979e-05,
      "loss": 0.4649,
      "step": 480
    },
    {
      "grad_norm": 0.9710970520973206,
      "learning_rate": 9.654943827000548e-05,
      "loss": 0.4578,
      "step": 490
    },
    {
      "grad_norm": 0.7813271284103394,
      "learning_rate": 9.634541575171929e-05,
      "loss": 0.4481,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 3000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "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": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}