{
  "best_metric": 0.03436475992202759,
  "best_model_checkpoint": "plant_classification/checkpoint-200",
  "epoch": 4.0,
  "eval_steps": 100,
  "global_step": 260,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 2.763857841491699,
      "learning_rate": 1.9230769230769234e-06,
      "loss": 0.0382,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 12.728006362915039,
      "learning_rate": 3.846153846153847e-06,
      "loss": 0.0264,
      "step": 20
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.14380256831645966,
      "learning_rate": 5.769230769230769e-06,
      "loss": 0.0588,
      "step": 30
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.625977635383606,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.0259,
      "step": 40
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.28217747807502747,
      "learning_rate": 9.615384615384616e-06,
      "loss": 0.0119,
      "step": 50
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 17.04554557800293,
      "learning_rate": 9.615384615384616e-06,
      "loss": 0.0696,
      "step": 60
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 2.1516802310943604,
      "learning_rate": 9.134615384615384e-06,
      "loss": 0.0193,
      "step": 70
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 1.7008322477340698,
      "learning_rate": 8.653846153846155e-06,
      "loss": 0.0446,
      "step": 80
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.13665564358234406,
      "learning_rate": 8.173076923076923e-06,
      "loss": 0.0064,
      "step": 90
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.5729480385780334,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.0079,
      "step": 100
    },
    {
      "epoch": 1.5384615384615383,
      "eval_accuracy": 0.9924812030075187,
      "eval_loss": 0.03526682406663895,
      "eval_runtime": 5.1896,
      "eval_samples_per_second": 25.628,
      "eval_steps_per_second": 3.276,
      "step": 100
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.028321973979473114,
      "learning_rate": 7.211538461538462e-06,
      "loss": 0.0038,
      "step": 110
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.02708490751683712,
      "learning_rate": 6.730769230769232e-06,
      "loss": 0.0087,
      "step": 120
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.005777100566774607,
      "learning_rate": 6.25e-06,
      "loss": 0.0171,
      "step": 130
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.606082022190094,
      "learning_rate": 5.769230769230769e-06,
      "loss": 0.0242,
      "step": 140
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.3665677011013031,
      "learning_rate": 5.288461538461539e-06,
      "loss": 0.0036,
      "step": 150
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.07272122800350189,
      "learning_rate": 4.807692307692308e-06,
      "loss": 0.0098,
      "step": 160
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.27849578857421875,
      "learning_rate": 4.326923076923077e-06,
      "loss": 0.0035,
      "step": 170
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 2.9973416328430176,
      "learning_rate": 3.846153846153847e-06,
      "loss": 0.0064,
      "step": 180
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.30117306113243103,
      "learning_rate": 3.365384615384616e-06,
      "loss": 0.0042,
      "step": 190
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.04479280859231949,
      "learning_rate": 2.8846153846153845e-06,
      "loss": 0.0079,
      "step": 200
    },
    {
      "epoch": 3.076923076923077,
      "eval_accuracy": 0.9924812030075187,
      "eval_loss": 0.03436475992202759,
      "eval_runtime": 5.5035,
      "eval_samples_per_second": 24.166,
      "eval_steps_per_second": 3.089,
      "step": 200
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 0.20207858085632324,
      "learning_rate": 2.403846153846154e-06,
      "loss": 0.0093,
      "step": 210
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 0.8401392698287964,
      "learning_rate": 1.9230769230769234e-06,
      "loss": 0.003,
      "step": 220
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 0.17295202612876892,
      "learning_rate": 1.4423076923076922e-06,
      "loss": 0.0087,
      "step": 230
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 2.996504068374634,
      "learning_rate": 9.615384615384617e-07,
      "loss": 0.0063,
      "step": 240
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 8.349090576171875,
      "learning_rate": 4.807692307692308e-07,
      "loss": 0.0105,
      "step": 250
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.021630151197314262,
      "learning_rate": 0.0,
      "loss": 0.0063,
      "step": 260
    },
    {
      "epoch": 4.0,
      "step": 260,
      "total_flos": 1.0280724304719053e+17,
      "train_loss": 0.017011618363456084,
      "train_runtime": 403.5216,
      "train_samples_per_second": 10.25,
      "train_steps_per_second": 0.644
    }
  ],
  "logging_steps": 10,
  "max_steps": 260,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0280724304719053e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}