{
  "best_metric": 0.035541191697120667,
  "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": 6.145578384399414,
      "learning_rate": 7.692307692307694e-06,
      "loss": 1.078,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 6.7720441818237305,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.9303,
      "step": 20
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 7.24746561050415,
      "learning_rate": 1.965811965811966e-05,
      "loss": 0.7624,
      "step": 30
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 7.476565837860107,
      "learning_rate": 1.8803418803418804e-05,
      "loss": 0.5213,
      "step": 40
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 11.678607940673828,
      "learning_rate": 1.794871794871795e-05,
      "loss": 0.309,
      "step": 50
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 13.353544235229492,
      "learning_rate": 1.7094017094017095e-05,
      "loss": 0.3275,
      "step": 60
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 11.612092971801758,
      "learning_rate": 1.623931623931624e-05,
      "loss": 0.2435,
      "step": 70
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 6.987435817718506,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.1946,
      "step": 80
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 1.3243111371994019,
      "learning_rate": 1.4529914529914531e-05,
      "loss": 0.1017,
      "step": 90
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 16.304893493652344,
      "learning_rate": 1.3675213675213677e-05,
      "loss": 0.1031,
      "step": 100
    },
    {
      "epoch": 1.5384615384615383,
      "eval_accuracy": 0.9849624060150376,
      "eval_loss": 0.040253832936286926,
      "eval_runtime": 5.7782,
      "eval_samples_per_second": 23.017,
      "eval_steps_per_second": 2.942,
      "step": 100
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 1.3267813920974731,
      "learning_rate": 1.2820512820512823e-05,
      "loss": 0.0926,
      "step": 110
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 1.3231496810913086,
      "learning_rate": 1.1965811965811966e-05,
      "loss": 0.1027,
      "step": 120
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6598650217056274,
      "learning_rate": 1.1111111111111113e-05,
      "loss": 0.096,
      "step": 130
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 4.875283241271973,
      "learning_rate": 1.0256410256410256e-05,
      "loss": 0.1066,
      "step": 140
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.7839311361312866,
      "learning_rate": 9.401709401709402e-06,
      "loss": 0.0662,
      "step": 150
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 3.084962844848633,
      "learning_rate": 8.547008547008548e-06,
      "loss": 0.0887,
      "step": 160
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 4.014326095581055,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.0444,
      "step": 170
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 13.623960494995117,
      "learning_rate": 6.837606837606839e-06,
      "loss": 0.0707,
      "step": 180
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 1.9218041896820068,
      "learning_rate": 5.982905982905983e-06,
      "loss": 0.0493,
      "step": 190
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.4377898573875427,
      "learning_rate": 5.128205128205128e-06,
      "loss": 0.059,
      "step": 200
    },
    {
      "epoch": 3.076923076923077,
      "eval_accuracy": 0.9849624060150376,
      "eval_loss": 0.035541191697120667,
      "eval_runtime": 5.14,
      "eval_samples_per_second": 25.875,
      "eval_steps_per_second": 3.307,
      "step": 200
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 0.859157919883728,
      "learning_rate": 4.273504273504274e-06,
      "loss": 0.0203,
      "step": 210
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 6.222720623016357,
      "learning_rate": 3.4188034188034193e-06,
      "loss": 0.0184,
      "step": 220
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 0.6217049956321716,
      "learning_rate": 2.564102564102564e-06,
      "loss": 0.0636,
      "step": 230
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 8.089138984680176,
      "learning_rate": 1.7094017094017097e-06,
      "loss": 0.0171,
      "step": 240
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 10.144171714782715,
      "learning_rate": 8.547008547008548e-07,
      "loss": 0.0423,
      "step": 250
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.059058304876089096,
      "learning_rate": 0.0,
      "loss": 0.0486,
      "step": 260
    },
    {
      "epoch": 4.0,
      "step": 260,
      "total_flos": 1.0280724304719053e+17,
      "train_loss": 0.21376643198040815,
      "train_runtime": 415.522,
      "train_samples_per_second": 9.954,
      "train_steps_per_second": 0.626
    }
  ],
  "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
}