{
  "best_metric": 0.19460569322109222,
  "best_model_checkpoint": "./beans_outputs/checkpoint-165",
  "epoch": 5.0,
  "global_step": 165,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3,
      "learning_rate": 1.8787878787878792e-05,
      "loss": 1.0301,
      "step": 10
    },
    {
      "epoch": 0.61,
      "learning_rate": 1.7575757575757576e-05,
      "loss": 0.8837,
      "step": 20
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 0.7436,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.6124519109725952,
      "eval_runtime": 1.9453,
      "eval_samples_per_second": 68.371,
      "eval_steps_per_second": 2.57,
      "step": 33
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.5151515151515153e-05,
      "loss": 0.611,
      "step": 40
    },
    {
      "epoch": 1.52,
      "learning_rate": 1.3939393939393942e-05,
      "loss": 0.516,
      "step": 50
    },
    {
      "epoch": 1.82,
      "learning_rate": 1.2727272727272728e-05,
      "loss": 0.4365,
      "step": 60
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.34239351749420166,
      "eval_runtime": 1.9228,
      "eval_samples_per_second": 69.17,
      "eval_steps_per_second": 2.6,
      "step": 66
    },
    {
      "epoch": 2.12,
      "learning_rate": 1.1515151515151517e-05,
      "loss": 0.4036,
      "step": 70
    },
    {
      "epoch": 2.42,
      "learning_rate": 1.0303030303030304e-05,
      "loss": 0.3354,
      "step": 80
    },
    {
      "epoch": 2.73,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.3164,
      "step": 90
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9849624060150376,
      "eval_loss": 0.23850761353969574,
      "eval_runtime": 1.9166,
      "eval_samples_per_second": 69.394,
      "eval_steps_per_second": 2.609,
      "step": 99
    },
    {
      "epoch": 3.03,
      "learning_rate": 7.87878787878788e-06,
      "loss": 0.3057,
      "step": 100
    },
    {
      "epoch": 3.33,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.2561,
      "step": 110
    },
    {
      "epoch": 3.64,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.2487,
      "step": 120
    },
    {
      "epoch": 3.94,
      "learning_rate": 4.242424242424243e-06,
      "loss": 0.2347,
      "step": 130
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.1993345469236374,
      "eval_runtime": 1.9018,
      "eval_samples_per_second": 69.932,
      "eval_steps_per_second": 2.629,
      "step": 132
    },
    {
      "epoch": 4.24,
      "learning_rate": 3.0303030303030305e-06,
      "loss": 0.2092,
      "step": 140
    },
    {
      "epoch": 4.55,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.2314,
      "step": 150
    },
    {
      "epoch": 4.85,
      "learning_rate": 6.060606060606061e-07,
      "loss": 0.2135,
      "step": 160
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.19460569322109222,
      "eval_runtime": 1.9052,
      "eval_samples_per_second": 69.809,
      "eval_steps_per_second": 2.624,
      "step": 165
    },
    {
      "epoch": 5.0,
      "step": 165,
      "total_flos": 0.0,
      "train_loss": 0.42934251626332604,
      "train_runtime": 152.2911,
      "train_samples_per_second": 33.948,
      "train_steps_per_second": 1.083
    }
  ],
  "max_steps": 165,
  "num_train_epochs": 5,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}