{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8800880088008801,
  "eval_steps": 100,
  "global_step": 700,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 8.996486892091073e-06,
      "loss": 0.6543,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.985953053665263e-06,
      "loss": 0.469,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.968414932060827e-06,
      "loss": 0.2958,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.94389991097275e-06,
      "loss": 0.2424,
      "step": 40
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.912446267696357e-06,
      "loss": 0.2481,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.874103113361848e-06,
      "loss": 0.251,
      "step": 60
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.828930316253112e-06,
      "loss": 0.1803,
      "step": 70
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.7769984083305e-06,
      "loss": 0.2148,
      "step": 80
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.718388475103545e-06,
      "loss": 0.1926,
      "step": 90
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.653192029025561e-06,
      "loss": 0.2202,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_accuracy": 0.0,
      "eval_loss": 0.07498380541801453,
      "eval_runtime": 28.9719,
      "eval_samples_per_second": 97.612,
      "eval_steps_per_second": 24.403,
      "step": 100
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.581510866607817e-06,
      "loss": 0.1805,
      "step": 110
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.503456909476364e-06,
      "loss": 0.2322,
      "step": 120
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.419152029619696e-06,
      "loss": 0.1636,
      "step": 130
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.32872785910012e-06,
      "loss": 0.1689,
      "step": 140
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.232325584525908e-06,
      "loss": 0.1738,
      "step": 150
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.130095726605169e-06,
      "loss": 0.1509,
      "step": 160
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.022197905125629e-06,
      "loss": 0.1821,
      "step": 170
    },
    {
      "epoch": 0.23,
      "learning_rate": 7.90880058972729e-06,
      "loss": 0.1435,
      "step": 180
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.790080836857073e-06,
      "loss": 0.1621,
      "step": 190
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.666224013316203e-06,
      "loss": 0.1527,
      "step": 200
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.0,
      "eval_loss": 0.03772040829062462,
      "eval_runtime": 29.7593,
      "eval_samples_per_second": 95.029,
      "eval_steps_per_second": 23.757,
      "step": 200
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.537423506831948e-06,
      "loss": 0.1684,
      "step": 210
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.403880424105644e-06,
      "loss": 0.2118,
      "step": 220
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.2658032768084485e-06,
      "loss": 0.1381,
      "step": 230
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.123407656015124e-06,
      "loss": 0.1364,
      "step": 240
    },
    {
      "epoch": 0.31,
      "learning_rate": 6.976915895584163e-06,
      "loss": 0.1147,
      "step": 250
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.826556725009857e-06,
      "loss": 0.1129,
      "step": 260
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.672564912288353e-06,
      "loss": 0.1357,
      "step": 270
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.515180897355285e-06,
      "loss": 0.1285,
      "step": 280
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.354650416667365e-06,
      "loss": 0.1013,
      "step": 290
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.191224119514071e-06,
      "loss": 0.1483,
      "step": 300
    },
    {
      "epoch": 0.38,
      "eval_accuracy": 0.0,
      "eval_loss": 0.07286300510168076,
      "eval_runtime": 29.1592,
      "eval_samples_per_second": 96.985,
      "eval_steps_per_second": 24.246,
      "step": 300
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.0251571766585436e-06,
      "loss": 0.1199,
      "step": 310
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.856708881918714e-06,
      "loss": 0.1211,
      "step": 320
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.6861422473108045e-06,
      "loss": 0.1637,
      "step": 330
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.513723592387277e-06,
      "loss": 0.1656,
      "step": 340
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.339722128410471e-06,
      "loss": 0.1099,
      "step": 350
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.164409538011166e-06,
      "loss": 0.1771,
      "step": 360
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.988059550988415e-06,
      "loss": 0.1509,
      "step": 370
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.810947516912951e-06,
      "loss": 0.1177,
      "step": 380
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.633349975201519e-06,
      "loss": 0.1135,
      "step": 390
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.455544223333405e-06,
      "loss": 0.1896,
      "step": 400
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.0,
      "eval_loss": 0.14649830758571625,
      "eval_runtime": 29.7909,
      "eval_samples_per_second": 94.928,
      "eval_steps_per_second": 23.732,
      "step": 400
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.277807883883337e-06,
      "loss": 0.1044,
      "step": 410
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.100418471046794e-06,
      "loss": 0.1084,
      "step": 420
    },
    {
      "epoch": 0.54,
      "learning_rate": 3.9236529573345295e-06,
      "loss": 0.0895,
      "step": 430
    },
    {
      "epoch": 0.55,
      "learning_rate": 3.7477873411128757e-06,
      "loss": 0.0877,
      "step": 440
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.573096215665058e-06,
      "loss": 0.1421,
      "step": 450
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.399852340446378e-06,
      "loss": 0.1461,
      "step": 460
    },
    {
      "epoch": 0.59,
      "learning_rate": 3.2283262152027056e-06,
      "loss": 0.1126,
      "step": 470
    },
    {
      "epoch": 0.6,
      "learning_rate": 3.0587856576172314e-06,
      "loss": 0.0901,
      "step": 480
    },
    {
      "epoch": 0.62,
      "learning_rate": 2.89149538514495e-06,
      "loss": 0.1441,
      "step": 490
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.726716601687775e-06,
      "loss": 0.1341,
      "step": 500
    },
    {
      "epoch": 0.63,
      "eval_accuracy": 0.0,
      "eval_loss": 0.07294097542762756,
      "eval_runtime": 29.0559,
      "eval_samples_per_second": 97.33,
      "eval_steps_per_second": 24.332,
      "step": 500
    },
    {
      "epoch": 0.64,
      "learning_rate": 2.5647065897556595e-06,
      "loss": 0.0889,
      "step": 510
    },
    {
      "epoch": 0.65,
      "learning_rate": 2.405718308750485e-06,
      "loss": 0.0849,
      "step": 520
    },
    {
      "epoch": 0.67,
      "learning_rate": 2.250000000000001e-06,
      "loss": 0.1501,
      "step": 530
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.097794799158444e-06,
      "loss": 0.0813,
      "step": 540
    },
    {
      "epoch": 0.69,
      "learning_rate": 1.9493403565790804e-06,
      "loss": 0.0866,
      "step": 550
    },
    {
      "epoch": 0.7,
      "learning_rate": 1.8048684662514e-06,
      "loss": 0.1651,
      "step": 560
    },
    {
      "epoch": 0.72,
      "learning_rate": 1.6646047038823006e-06,
      "loss": 0.1361,
      "step": 570
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.5287680746864134e-06,
      "loss": 0.1593,
      "step": 580
    },
    {
      "epoch": 0.74,
      "learning_rate": 1.3975706714354478e-06,
      "loss": 0.0883,
      "step": 590
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.2712173433005088e-06,
      "loss": 0.0876,
      "step": 600
    },
    {
      "epoch": 0.75,
      "eval_accuracy": 0.0,
      "eval_loss": 0.035098280757665634,
      "eval_runtime": 29.6788,
      "eval_samples_per_second": 95.287,
      "eval_steps_per_second": 23.822,
      "step": 600
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.1499053760044425e-06,
      "loss": 0.1194,
      "step": 610
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.0338241837835812e-06,
      "loss": 0.1013,
      "step": 620
    },
    {
      "epoch": 0.79,
      "learning_rate": 9.231550136399099e-07,
      "loss": 0.1059,
      "step": 630
    },
    {
      "epoch": 0.8,
      "learning_rate": 8.180706623453892e-07,
      "loss": 0.1042,
      "step": 640
    },
    {
      "epoch": 0.82,
      "learning_rate": 7.187352066403012e-07,
      "loss": 0.1477,
      "step": 650
    },
    {
      "epoch": 0.83,
      "learning_rate": 6.253037470469e-07,
      "loss": 0.1009,
      "step": 660
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.379221656983615e-07,
      "loss": 0.0672,
      "step": 670
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.567268985611408e-07,
      "loss": 0.0963,
      "step": 680
    },
    {
      "epoch": 0.87,
      "learning_rate": 3.8184472240641696e-07,
      "loss": 0.0679,
      "step": 690
    },
    {
      "epoch": 0.88,
      "learning_rate": 3.133925568632049e-07,
      "loss": 0.1345,
      "step": 700
    },
    {
      "epoch": 0.88,
      "eval_accuracy": 0.0,
      "eval_loss": 0.06039029359817505,
      "eval_runtime": 29.1232,
      "eval_samples_per_second": 97.105,
      "eval_steps_per_second": 24.276,
      "step": 700
    }
  ],
  "logging_steps": 10,
  "max_steps": 795,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}