{
  "best_metric": 0.03951447829604149,
  "best_model_checkpoint": "./vit-base-beans-demo-v5/checkpoint-100",
  "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": 0.10121775418519974,
      "learning_rate": 0.00019230769230769233,
      "loss": 0.0511,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.09825766086578369,
      "learning_rate": 0.00018461538461538463,
      "loss": 0.0676,
      "step": 20
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.08373750001192093,
      "learning_rate": 0.00017692307692307693,
      "loss": 0.0651,
      "step": 30
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 1.3777884244918823,
      "learning_rate": 0.00016923076923076923,
      "loss": 0.1962,
      "step": 40
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 5.368072986602783,
      "learning_rate": 0.00016153846153846155,
      "loss": 0.1049,
      "step": 50
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.5872201323509216,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.1314,
      "step": 60
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.5075070858001709,
      "learning_rate": 0.00014615384615384615,
      "loss": 0.0292,
      "step": 70
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.1086004301905632,
      "learning_rate": 0.00013846153846153847,
      "loss": 0.0212,
      "step": 80
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.07343905419111252,
      "learning_rate": 0.00013076923076923077,
      "loss": 0.1352,
      "step": 90
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.0549425408244133,
      "learning_rate": 0.0001230769230769231,
      "loss": 0.0908,
      "step": 100
    },
    {
      "epoch": 1.5384615384615383,
      "eval_accuracy": 0.9924812030075187,
      "eval_loss": 0.03951447829604149,
      "eval_runtime": 1.2809,
      "eval_samples_per_second": 103.836,
      "eval_steps_per_second": 13.272,
      "step": 100
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 2.310343027114868,
      "learning_rate": 0.00011538461538461538,
      "loss": 0.06,
      "step": 110
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.05756788328289986,
      "learning_rate": 0.0001076923076923077,
      "loss": 0.0682,
      "step": 120
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.04645319655537605,
      "learning_rate": 0.0001,
      "loss": 0.0507,
      "step": 130
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 8.705768585205078,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.0137,
      "step": 140
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 1.395561933517456,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.0385,
      "step": 150
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.03628158941864967,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.0091,
      "step": 160
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.056354835629463196,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.0193,
      "step": 170
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.4058499336242676,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.0071,
      "step": 180
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.1187632828950882,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.0061,
      "step": 190
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.03182573989033699,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.0405,
      "step": 200
    },
    {
      "epoch": 3.076923076923077,
      "eval_accuracy": 0.9774436090225563,
      "eval_loss": 0.08808419853448868,
      "eval_runtime": 1.2947,
      "eval_samples_per_second": 102.726,
      "eval_steps_per_second": 13.13,
      "step": 200
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 0.027759993448853493,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.007,
      "step": 210
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 0.029192451387643814,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.0065,
      "step": 220
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 0.029540522024035454,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.0051,
      "step": 230
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.029079928994178772,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.0051,
      "step": 240
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.02755054645240307,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.0051,
      "step": 250
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.02570190466940403,
      "learning_rate": 0.0,
      "loss": 0.0069,
      "step": 260
    },
    {
      "epoch": 4.0,
      "step": 260,
      "total_flos": 3.205097416476426e+17,
      "train_loss": 0.04775545258934681,
      "train_runtime": 87.4101,
      "train_samples_per_second": 47.317,
      "train_steps_per_second": 2.974
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.205097416476426e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}