{
  "best_metric": 0.1631537675857544,
  "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": 0.0036831500474363565,
      "learning_rate": 0.00019230769230769233,
      "loss": 0.2402,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.37796255946159363,
      "learning_rate": 0.00018461538461538463,
      "loss": 0.1955,
      "step": 20
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 31.321809768676758,
      "learning_rate": 0.00017692307692307693,
      "loss": 0.2262,
      "step": 30
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 5.618703365325928,
      "learning_rate": 0.00016923076923076923,
      "loss": 0.1265,
      "step": 40
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 1.3796021938323975,
      "learning_rate": 0.00016153846153846155,
      "loss": 0.1004,
      "step": 50
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 9.802377700805664,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.0927,
      "step": 60
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.1012055054306984,
      "learning_rate": 0.00014615384615384615,
      "loss": 0.01,
      "step": 70
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.03965623676776886,
      "learning_rate": 0.00013846153846153847,
      "loss": 0.1504,
      "step": 80
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.01619710959494114,
      "learning_rate": 0.00013076923076923077,
      "loss": 0.0473,
      "step": 90
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.01804116927087307,
      "learning_rate": 0.0001230769230769231,
      "loss": 0.0007,
      "step": 100
    },
    {
      "epoch": 1.5384615384615383,
      "eval_accuracy": 0.9548872180451128,
      "eval_loss": 0.2284693568944931,
      "eval_runtime": 5.8195,
      "eval_samples_per_second": 22.854,
      "eval_steps_per_second": 2.921,
      "step": 100
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 2.150287628173828,
      "learning_rate": 0.00011538461538461538,
      "loss": 0.0236,
      "step": 110
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.004995028022676706,
      "learning_rate": 0.0001076923076923077,
      "loss": 0.0006,
      "step": 120
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.00010829918755916879,
      "learning_rate": 0.0001,
      "loss": 0.0089,
      "step": 130
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.0008967414614744484,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.0032,
      "step": 140
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.008112355135381222,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.0258,
      "step": 150
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.0023394483141601086,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.0001,
      "step": 160
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.03999931737780571,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.0521,
      "step": 170
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.12175856530666351,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.0064,
      "step": 180
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.0003706614370457828,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.0,
      "step": 190
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.00019209070887882262,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.0005,
      "step": 200
    },
    {
      "epoch": 3.076923076923077,
      "eval_accuracy": 0.9699248120300752,
      "eval_loss": 0.1631537675857544,
      "eval_runtime": 6.8037,
      "eval_samples_per_second": 19.548,
      "eval_steps_per_second": 2.499,
      "step": 200
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 0.00012901176523882896,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.0024,
      "step": 210
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 0.0013422417687252164,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.0299,
      "step": 220
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 0.0007627483573742211,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.0,
      "step": 230
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 2.576974868774414,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.0002,
      "step": 240
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.002301289001479745,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.0,
      "step": 250
    },
    {
      "epoch": 4.0,
      "grad_norm": 5.4764645028626546e-05,
      "learning_rate": 0.0,
      "loss": 0.0002,
      "step": 260
    },
    {
      "epoch": 4.0,
      "step": 260,
      "total_flos": 1.0280724304719053e+17,
      "train_loss": 0.05168719090436823,
      "train_runtime": 444.679,
      "train_samples_per_second": 9.301,
      "train_steps_per_second": 0.585
    }
  ],
  "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
}