{
  "best_metric": 0.00626166770234704,
  "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": 0.09662118554115295,
      "learning_rate": 0.00019230769230769233,
      "loss": 0.1369,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.07074641436338425,
      "learning_rate": 0.00018461538461538463,
      "loss": 0.0427,
      "step": 20
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 13.250753402709961,
      "learning_rate": 0.00017692307692307693,
      "loss": 0.2138,
      "step": 30
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 4.6117377281188965,
      "learning_rate": 0.00016923076923076923,
      "loss": 0.1703,
      "step": 40
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 4.517739772796631,
      "learning_rate": 0.00016153846153846155,
      "loss": 0.112,
      "step": 50
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.10043614357709885,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.0916,
      "step": 60
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.1665734201669693,
      "learning_rate": 0.00014615384615384615,
      "loss": 0.088,
      "step": 70
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.06032606214284897,
      "learning_rate": 0.00013846153846153847,
      "loss": 0.0704,
      "step": 80
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.6214683055877686,
      "learning_rate": 0.00013076923076923077,
      "loss": 0.0156,
      "step": 90
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 1.3439762592315674,
      "learning_rate": 0.0001230769230769231,
      "loss": 0.0101,
      "step": 100
    },
    {
      "epoch": 1.5384615384615383,
      "eval_accuracy": 0.9849624060150376,
      "eval_loss": 0.0765344426035881,
      "eval_runtime": 1.366,
      "eval_samples_per_second": 97.361,
      "eval_steps_per_second": 12.445,
      "step": 100
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.14764006435871124,
      "learning_rate": 0.00011538461538461538,
      "loss": 0.1026,
      "step": 110
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.044659219682216644,
      "learning_rate": 0.0001076923076923077,
      "loss": 0.0685,
      "step": 120
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.07455907762050629,
      "learning_rate": 0.0001,
      "loss": 0.026,
      "step": 130
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.03619804233312607,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.0092,
      "step": 140
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.0522390641272068,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.0238,
      "step": 150
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.06478125602006912,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.0207,
      "step": 160
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 3.4158685207366943,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.0274,
      "step": 170
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.028454679995775223,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.0378,
      "step": 180
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.5384447574615479,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.0062,
      "step": 190
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.02775881439447403,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.0367,
      "step": 200
    },
    {
      "epoch": 3.076923076923077,
      "eval_accuracy": 1.0,
      "eval_loss": 0.00626166770234704,
      "eval_runtime": 1.2564,
      "eval_samples_per_second": 105.855,
      "eval_steps_per_second": 13.53,
      "step": 200
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 0.02590871788561344,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.0053,
      "step": 210
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 0.026522768661379814,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.0048,
      "step": 220
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 0.02560822106897831,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.0046,
      "step": 230
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.02393898367881775,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.0044,
      "step": 240
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.02538886107504368,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.0045,
      "step": 250
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.02267070859670639,
      "learning_rate": 0.0,
      "loss": 0.0045,
      "step": 260
    },
    {
      "epoch": 4.0,
      "step": 260,
      "total_flos": 3.205097416476426e+17,
      "train_loss": 0.05148093067109585,
      "train_runtime": 110.3977,
      "train_samples_per_second": 37.465,
      "train_steps_per_second": 2.355
    }
  ],
  "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": 3.205097416476426e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}