{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5140507196710076,
  "eval_steps": 100,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 8.993468091981985e-05,
      "loss": 0.6403,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.973891330515646e-05,
      "loss": 0.5248,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.941326548314407e-05,
      "loss": 0.5079,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.895868283228029e-05,
      "loss": 0.5916,
      "step": 40
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.837648503792598e-05,
      "loss": 0.5116,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.766836226116608e-05,
      "loss": 0.5206,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.683637023215313e-05,
      "loss": 0.535,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.588292428217834e-05,
      "loss": 0.6067,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.481079233179524e-05,
      "loss": 0.6139,
      "step": 90
    },
    {
      "epoch": 0.17,
      "learning_rate": 8.362308685535183e-05,
      "loss": 0.5015,
      "step": 100
    },
    {
      "epoch": 0.17,
      "eval_accuracy": 0.0,
      "eval_loss": 0.5284319519996643,
      "eval_runtime": 27.5165,
      "eval_samples_per_second": 141.406,
      "eval_steps_per_second": 23.586,
      "step": 100
    },
    {
      "epoch": 0.19,
      "learning_rate": 8.232325584525909e-05,
      "loss": 0.6008,
      "step": 110
    },
    {
      "epoch": 0.21,
      "learning_rate": 8.091507280222672e-05,
      "loss": 0.549,
      "step": 120
    },
    {
      "epoch": 0.22,
      "learning_rate": 7.940262578052567e-05,
      "loss": 0.5512,
      "step": 130
    },
    {
      "epoch": 0.24,
      "learning_rate": 7.779030552007946e-05,
      "loss": 0.4872,
      "step": 140
    },
    {
      "epoch": 0.26,
      "learning_rate": 7.608279269983776e-05,
      "loss": 0.505,
      "step": 150
    },
    {
      "epoch": 0.27,
      "learning_rate": 7.428504434943677e-05,
      "loss": 0.4774,
      "step": 160
    },
    {
      "epoch": 0.29,
      "learning_rate": 7.240227945859396e-05,
      "loss": 0.5005,
      "step": 170
    },
    {
      "epoch": 0.31,
      "learning_rate": 7.043996382601448e-05,
      "loss": 0.4286,
      "step": 180
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.840379419179358e-05,
      "loss": 0.4746,
      "step": 190
    },
    {
      "epoch": 0.34,
      "learning_rate": 6.629968169938006e-05,
      "loss": 0.4259,
      "step": 200
    },
    {
      "epoch": 0.34,
      "eval_accuracy": 0.0,
      "eval_loss": 0.3847603499889374,
      "eval_runtime": 28.0384,
      "eval_samples_per_second": 138.774,
      "eval_steps_per_second": 23.147,
      "step": 200
    },
    {
      "epoch": 0.36,
      "learning_rate": 6.41337347351117e-05,
      "loss": 0.4118,
      "step": 210
    },
    {
      "epoch": 0.38,
      "learning_rate": 6.191224119514072e-05,
      "loss": 0.3758,
      "step": 220
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.9641650231229666e-05,
      "loss": 0.4376,
      "step": 230
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.7328553528410896e-05,
      "loss": 0.4189,
      "step": 240
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.497966616886201e-05,
      "loss": 0.3686,
      "step": 250
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.2601807137550664e-05,
      "loss": 0.377,
      "step": 260
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.020187952624234e-05,
      "loss": 0.3708,
      "step": 270
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.7786850493340155e-05,
      "loss": 0.4092,
      "step": 280
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.536373103773464e-05,
      "loss": 0.3521,
      "step": 290
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.293955564538168e-05,
      "loss": 0.3808,
      "step": 300
    },
    {
      "epoch": 0.51,
      "eval_accuracy": 0.0,
      "eval_loss": 0.2961568832397461,
      "eval_runtime": 27.3269,
      "eval_samples_per_second": 142.387,
      "eval_steps_per_second": 23.749,
      "step": 300
    }
  ],
  "logging_steps": 10,
  "max_steps": 583,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}