{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0712900650165393,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 8.999954848325688e-06,
      "loss": 0.7277,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.999819394208827e-06,
      "loss": 0.6455,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.999593640367633e-06,
      "loss": 0.5428,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.9992775913324e-06,
      "loss": 0.3486,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.998871253445414e-06,
      "loss": 0.3524,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.998374634860822e-06,
      "loss": 0.2701,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.997787745544478e-06,
      "loss": 0.2106,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.997110597273727e-06,
      "loss": 0.2596,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.996343203637181e-06,
      "loss": 0.2015,
      "step": 90
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.995485580034448e-06,
      "loss": 0.2462,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.99453774367581e-06,
      "loss": 0.2172,
      "step": 110
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.993499713581887e-06,
      "loss": 0.2655,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.992371510583257e-06,
      "loss": 0.1823,
      "step": 130
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.991153157320033e-06,
      "loss": 0.227,
      "step": 140
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.989844678241412e-06,
      "loss": 0.2243,
      "step": 150
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.988446099605179e-06,
      "loss": 0.1787,
      "step": 160
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.986957449477188e-06,
      "loss": 0.2211,
      "step": 170
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.98537875773079e-06,
      "loss": 0.1683,
      "step": 180
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.983710056046243e-06,
      "loss": 0.1879,
      "step": 190
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.98195137791007e-06,
      "loss": 0.1809,
      "step": 200
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.980102758614384e-06,
      "loss": 0.2204,
      "step": 210
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.978164235256191e-06,
      "loss": 0.189,
      "step": 220
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.976135846736634e-06,
      "loss": 0.1389,
      "step": 230
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.97401763376022e-06,
      "loss": 0.1231,
      "step": 240
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.971809638833998e-06,
      "loss": 0.2018,
      "step": 250
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.96951190626671e-06,
      "loss": 0.1271,
      "step": 260
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.967124482167896e-06,
      "loss": 0.1364,
      "step": 270
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.964647414446981e-06,
      "loss": 0.1658,
      "step": 280
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.9620807528123e-06,
      "loss": 0.1479,
      "step": 290
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.959424548770104e-06,
      "loss": 0.1353,
      "step": 300
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.95667885562353e-06,
      "loss": 0.1761,
      "step": 310
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.953843728471533e-06,
      "loss": 0.1391,
      "step": 320
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.950919224207774e-06,
      "loss": 0.1776,
      "step": 330
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.94790540151948e-06,
      "loss": 0.2089,
      "step": 340
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.94480232088627e-06,
      "loss": 0.1368,
      "step": 350
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.941610044578937e-06,
      "loss": 0.1501,
      "step": 360
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.938328636658202e-06,
      "loss": 0.1807,
      "step": 370
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.934958162973425e-06,
      "loss": 0.13,
      "step": 380
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.931498691161287e-06,
      "loss": 0.1437,
      "step": 390
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.92795029064443e-06,
      "loss": 0.0828,
      "step": 400
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.924313032630063e-06,
      "loss": 0.1041,
      "step": 410
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.920586990108539e-06,
      "loss": 0.2663,
      "step": 420
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.916772237851882e-06,
      "loss": 0.2055,
      "step": 430
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.912868852412294e-06,
      "loss": 0.151,
      "step": 440
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.908876912120614e-06,
      "loss": 0.1638,
      "step": 450
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.904796497084747e-06,
      "loss": 0.1399,
      "step": 460
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.900627689188059e-06,
      "loss": 0.1615,
      "step": 470
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.89637057208773e-06,
      "loss": 0.1209,
      "step": 480
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.892025231213077e-06,
      "loss": 0.1605,
      "step": 490
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.887591753763842e-06,
      "loss": 0.124,
      "step": 500
    },
    {
      "epoch": 0.07,
      "eval_accuracy": 0.0,
      "eval_loss": 0.13451002538204193,
      "eval_runtime": 446.6893,
      "eval_samples_per_second": 52.338,
      "eval_steps_per_second": 8.724,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 7013,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}