{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5029074336005029,
  "eval_steps": 100,
  "global_step": 400,
  "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": 0.4664,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.985953053665263e-06,
      "loss": 0.3347,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.968414932060827e-06,
      "loss": 0.2232,
      "step": 30
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.94389991097275e-06,
      "loss": 0.213,
      "step": 40
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.912446267696357e-06,
      "loss": 0.1234,
      "step": 50
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.874103113361848e-06,
      "loss": 0.1673,
      "step": 60
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.828930316253112e-06,
      "loss": 0.119,
      "step": 70
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.7769984083305e-06,
      "loss": 0.1706,
      "step": 80
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.718388475103545e-06,
      "loss": 0.1219,
      "step": 90
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.653192029025561e-06,
      "loss": 0.1952,
      "step": 100
    },
    {
      "epoch": 0.13,
      "eval_accuracy": 0.0,
      "eval_loss": 0.07885408401489258,
      "eval_runtime": 41.9306,
      "eval_samples_per_second": 67.445,
      "eval_steps_per_second": 16.861,
      "step": 100
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.581510866607817e-06,
      "loss": 0.1524,
      "step": 110
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.503456909476364e-06,
      "loss": 0.1673,
      "step": 120
    },
    {
      "epoch": 0.16,
      "learning_rate": 8.419152029619696e-06,
      "loss": 0.1217,
      "step": 130
    },
    {
      "epoch": 0.18,
      "learning_rate": 8.32872785910012e-06,
      "loss": 0.1325,
      "step": 140
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.232325584525908e-06,
      "loss": 0.1048,
      "step": 150
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.130095726605169e-06,
      "loss": 0.0894,
      "step": 160
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.022197905125629e-06,
      "loss": 0.1635,
      "step": 170
    },
    {
      "epoch": 0.23,
      "learning_rate": 7.90880058972729e-06,
      "loss": 0.1144,
      "step": 180
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.790080836857073e-06,
      "loss": 0.1336,
      "step": 190
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.666224013316203e-06,
      "loss": 0.0753,
      "step": 200
    },
    {
      "epoch": 0.25,
      "eval_accuracy": 0.0,
      "eval_loss": 0.01828611083328724,
      "eval_runtime": 43.6178,
      "eval_samples_per_second": 64.836,
      "eval_steps_per_second": 16.209,
      "step": 200
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.537423506831948e-06,
      "loss": 0.1167,
      "step": 210
    },
    {
      "epoch": 0.28,
      "learning_rate": 7.403880424105644e-06,
      "loss": 0.1221,
      "step": 220
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.2658032768084485e-06,
      "loss": 0.1258,
      "step": 230
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.123407656015124e-06,
      "loss": 0.1295,
      "step": 240
    },
    {
      "epoch": 0.31,
      "learning_rate": 6.976915895584163e-06,
      "loss": 0.0717,
      "step": 250
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.826556725009857e-06,
      "loss": 0.0966,
      "step": 260
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.672564912288353e-06,
      "loss": 0.0993,
      "step": 270
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.515180897355285e-06,
      "loss": 0.0734,
      "step": 280
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.354650416667365e-06,
      "loss": 0.0728,
      "step": 290
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.191224119514071e-06,
      "loss": 0.0789,
      "step": 300
    },
    {
      "epoch": 0.38,
      "eval_accuracy": 0.0,
      "eval_loss": 0.027279604226350784,
      "eval_runtime": 42.5997,
      "eval_samples_per_second": 66.385,
      "eval_steps_per_second": 16.596,
      "step": 300
    },
    {
      "epoch": 0.39,
      "learning_rate": 6.0251571766585436e-06,
      "loss": 0.0933,
      "step": 310
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.856708881918714e-06,
      "loss": 0.0718,
      "step": 320
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.6861422473108045e-06,
      "loss": 0.1392,
      "step": 330
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.513723592387277e-06,
      "loss": 0.081,
      "step": 340
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.339722128410471e-06,
      "loss": 0.1022,
      "step": 350
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.164409538011166e-06,
      "loss": 0.0992,
      "step": 360
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.988059550988415e-06,
      "loss": 0.0835,
      "step": 370
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.810947516912951e-06,
      "loss": 0.1079,
      "step": 380
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.633349975201519e-06,
      "loss": 0.0686,
      "step": 390
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.455544223333405e-06,
      "loss": 0.1131,
      "step": 400
    },
    {
      "epoch": 0.5,
      "eval_accuracy": 0.0,
      "eval_loss": 0.014577045105397701,
      "eval_runtime": 41.7766,
      "eval_samples_per_second": 67.693,
      "eval_steps_per_second": 16.923,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 795,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}