{
  "best_metric": 0.004344217013567686,
  "best_model_checkpoint": "./vit-base-beans/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": 7.798569202423096,
      "learning_rate": 0.00019230769230769233,
      "loss": 0.8615,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 6.179608345031738,
      "learning_rate": 0.00018461538461538463,
      "loss": 0.4858,
      "step": 20
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 8.181507110595703,
      "learning_rate": 0.00017692307692307693,
      "loss": 0.4727,
      "step": 30
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 14.38829517364502,
      "learning_rate": 0.00016923076923076923,
      "loss": 0.2262,
      "step": 40
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 15.033473014831543,
      "learning_rate": 0.00016153846153846155,
      "loss": 0.2322,
      "step": 50
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 7.98081111907959,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.358,
      "step": 60
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.5512467622756958,
      "learning_rate": 0.00014615384615384615,
      "loss": 0.095,
      "step": 70
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 1.6140762567520142,
      "learning_rate": 0.00013846153846153847,
      "loss": 0.1814,
      "step": 80
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 10.034732818603516,
      "learning_rate": 0.00013076923076923077,
      "loss": 0.1525,
      "step": 90
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 12.553338050842285,
      "learning_rate": 0.0001230769230769231,
      "loss": 0.0907,
      "step": 100
    },
    {
      "epoch": 1.5384615384615383,
      "eval_accuracy": 0.9924812030075187,
      "eval_loss": 0.020247915759682655,
      "eval_runtime": 5.2577,
      "eval_samples_per_second": 25.296,
      "eval_steps_per_second": 3.233,
      "step": 100
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.03536086902022362,
      "learning_rate": 0.00011538461538461538,
      "loss": 0.0342,
      "step": 110
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.006372655741870403,
      "learning_rate": 0.0001076923076923077,
      "loss": 0.1332,
      "step": 120
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.015240202657878399,
      "learning_rate": 0.0001,
      "loss": 0.1694,
      "step": 130
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 2.709064483642578,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.033,
      "step": 140
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.1343306005001068,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.0829,
      "step": 150
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.020713090896606445,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.0183,
      "step": 160
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.018071629106998444,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.0787,
      "step": 170
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 13.67061710357666,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.0115,
      "step": 180
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.5912205576896667,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.0682,
      "step": 190
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.007540373597294092,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.015,
      "step": 200
    },
    {
      "epoch": 3.076923076923077,
      "eval_accuracy": 1.0,
      "eval_loss": 0.004344217013567686,
      "eval_runtime": 5.8098,
      "eval_samples_per_second": 22.892,
      "eval_steps_per_second": 2.926,
      "step": 200
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 0.014537331648170948,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.0003,
      "step": 210
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 0.001026735408231616,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.001,
      "step": 220
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 0.01899067498743534,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.0053,
      "step": 230
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.009394258260726929,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.0001,
      "step": 240
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.04736953228712082,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.0006,
      "step": 250
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.001292641507461667,
      "learning_rate": 0.0,
      "loss": 0.0028,
      "step": 260
    },
    {
      "epoch": 4.0,
      "step": 260,
      "total_flos": 1.0280724304719053e+17,
      "train_loss": 0.14655229947664059,
      "train_runtime": 416.65,
      "train_samples_per_second": 9.927,
      "train_steps_per_second": 0.624
    }
  ],
  "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
}