{
  "best_metric": 0.14674656093120575,
  "best_model_checkpoint": "./model/flower_classification/checkpoint-1640",
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 2050,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 5.132025241851807,
      "learning_rate": 0.0004937256939571119,
      "loss": 2.134,
      "step": 205
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8581907090464548,
      "eval_f1": 0.837674825067582,
      "eval_loss": 0.8454212546348572,
      "eval_runtime": 28.1199,
      "eval_samples_per_second": 29.09,
      "eval_steps_per_second": 0.925,
      "step": 205
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.387629508972168,
      "learning_rate": 0.0004633096331859128,
      "loss": 0.6349,
      "step": 410
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8251833740831296,
      "eval_f1": 0.7946504203094102,
      "eval_loss": 0.722923755645752,
      "eval_runtime": 29.0663,
      "eval_samples_per_second": 28.143,
      "eval_steps_per_second": 0.895,
      "step": 410
    },
    {
      "epoch": 3.0,
      "grad_norm": 4.2244768142700195,
      "learning_rate": 0.00041068007996259456,
      "loss": 0.3946,
      "step": 615
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8520782396088019,
      "eval_f1": 0.8300712608562401,
      "eval_loss": 0.6452921628952026,
      "eval_runtime": 28.4361,
      "eval_samples_per_second": 28.766,
      "eval_steps_per_second": 0.914,
      "step": 615
    },
    {
      "epoch": 4.0,
      "grad_norm": 5.550930500030518,
      "learning_rate": 0.0003413177346466465,
      "loss": 0.2747,
      "step": 820
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9083129584352079,
      "eval_f1": 0.8900593969894474,
      "eval_loss": 0.36649200320243835,
      "eval_runtime": 28.7281,
      "eval_samples_per_second": 28.474,
      "eval_steps_per_second": 0.905,
      "step": 820
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.33117157220840454,
      "learning_rate": 0.00026244580563763596,
      "loss": 0.1668,
      "step": 1025
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8997555012224939,
      "eval_f1": 0.8691618009468008,
      "eval_loss": 0.3963604271411896,
      "eval_runtime": 27.4025,
      "eval_samples_per_second": 29.851,
      "eval_steps_per_second": 0.949,
      "step": 1025
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.8778561353683472,
      "learning_rate": 0.000182277803847181,
      "loss": 0.0767,
      "step": 1230
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9303178484107579,
      "eval_f1": 0.9282400977654337,
      "eval_loss": 0.2997395992279053,
      "eval_runtime": 29.2732,
      "eval_samples_per_second": 27.944,
      "eval_steps_per_second": 0.888,
      "step": 1230
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.5752906799316406,
      "learning_rate": 0.00010916220972633387,
      "loss": 0.0205,
      "step": 1435
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.9584352078239609,
      "eval_f1": 0.9589704701855204,
      "eval_loss": 0.17742082476615906,
      "eval_runtime": 28.0934,
      "eval_samples_per_second": 29.117,
      "eval_steps_per_second": 0.925,
      "step": 1435
    },
    {
      "epoch": 8.0,
      "grad_norm": 0.01407159585505724,
      "learning_rate": 5.0713084927528714e-05,
      "loss": 0.0066,
      "step": 1640
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.9718826405867971,
      "eval_f1": 0.9731818411225849,
      "eval_loss": 0.14674656093120575,
      "eval_runtime": 27.9516,
      "eval_samples_per_second": 29.265,
      "eval_steps_per_second": 0.93,
      "step": 1640
    },
    {
      "epoch": 9.0,
      "grad_norm": 0.00672489358112216,
      "learning_rate": 1.3017164368262945e-05,
      "loss": 0.0027,
      "step": 1845
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.9706601466992665,
      "eval_f1": 0.9716328709451881,
      "eval_loss": 0.15707702934741974,
      "eval_runtime": 28.2664,
      "eval_samples_per_second": 28.939,
      "eval_steps_per_second": 0.92,
      "step": 1845
    },
    {
      "epoch": 10.0,
      "grad_norm": 0.012862198986113071,
      "learning_rate": 0.0,
      "loss": 0.0026,
      "step": 2050
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.969437652811736,
      "eval_f1": 0.9708655887840052,
      "eval_loss": 0.16029977798461914,
      "eval_runtime": 29.4555,
      "eval_samples_per_second": 27.771,
      "eval_steps_per_second": 0.883,
      "step": 2050
    },
    {
      "epoch": 10.0,
      "step": 2050,
      "total_flos": 5.081825760678052e+18,
      "train_loss": 0.3714197819988902,
      "train_runtime": 7592.4189,
      "train_samples_per_second": 8.63,
      "train_steps_per_second": 0.27
    }
  ],
  "logging_steps": 500,
  "max_steps": 2050,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 5.081825760678052e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}