{
  "best_metric": 0.018673665821552277,
  "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": 6.1219401359558105,
      "learning_rate": 0.00019230769230769233,
      "loss": 0.8735,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 6.421919345855713,
      "learning_rate": 0.00018461538461538463,
      "loss": 0.4227,
      "step": 20
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 8.949458122253418,
      "learning_rate": 0.00017692307692307693,
      "loss": 0.619,
      "step": 30
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 18.531173706054688,
      "learning_rate": 0.00016923076923076923,
      "loss": 0.3132,
      "step": 40
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 11.649073600769043,
      "learning_rate": 0.00016153846153846155,
      "loss": 0.1747,
      "step": 50
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 9.787153244018555,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.4578,
      "step": 60
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 11.584129333496094,
      "learning_rate": 0.00014615384615384615,
      "loss": 0.1248,
      "step": 70
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 5.55765438079834,
      "learning_rate": 0.00013846153846153847,
      "loss": 0.1797,
      "step": 80
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 11.325220108032227,
      "learning_rate": 0.00013076923076923077,
      "loss": 0.2009,
      "step": 90
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 8.960542678833008,
      "learning_rate": 0.0001230769230769231,
      "loss": 0.1026,
      "step": 100
    },
    {
      "epoch": 1.5384615384615383,
      "eval_accuracy": 0.9849624060150376,
      "eval_loss": 0.03040493279695511,
      "eval_runtime": 6.9438,
      "eval_samples_per_second": 19.154,
      "eval_steps_per_second": 2.448,
      "step": 100
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 26.664871215820312,
      "learning_rate": 0.00011538461538461538,
      "loss": 0.0844,
      "step": 110
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.047984011471271515,
      "learning_rate": 0.0001076923076923077,
      "loss": 0.1192,
      "step": 120
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.053843218833208084,
      "learning_rate": 0.0001,
      "loss": 0.0604,
      "step": 130
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.12431614845991135,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.0354,
      "step": 140
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.006539974361658096,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.0209,
      "step": 150
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.0014725056244060397,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.0145,
      "step": 160
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.0049270084127783775,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.0091,
      "step": 170
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 42.14358901977539,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.1402,
      "step": 180
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.02492058463394642,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.0065,
      "step": 190
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.0023473859764635563,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.0101,
      "step": 200
    },
    {
      "epoch": 3.076923076923077,
      "eval_accuracy": 0.9924812030075187,
      "eval_loss": 0.018673665821552277,
      "eval_runtime": 6.8913,
      "eval_samples_per_second": 19.3,
      "eval_steps_per_second": 2.467,
      "step": 200
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 0.023455169051885605,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.0004,
      "step": 210
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 0.0006098861922509968,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.0001,
      "step": 220
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 28.16423988342285,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.0388,
      "step": 230
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.027881141752004623,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.0002,
      "step": 240
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.07322639971971512,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.0002,
      "step": 250
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.0007401489419862628,
      "learning_rate": 0.0,
      "loss": 0.0008,
      "step": 260
    },
    {
      "epoch": 4.0,
      "step": 260,
      "total_flos": 1.0280724304719053e+17,
      "train_loss": 0.15423231131683748,
      "train_runtime": 475.1171,
      "train_samples_per_second": 8.705,
      "train_steps_per_second": 0.547
    }
  ],
  "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
}