{
  "best_metric": 0.07106763869524002,
  "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": 1.6026091575622559,
      "learning_rate": 0.00019230769230769233,
      "loss": 0.857,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 1.5386457443237305,
      "learning_rate": 0.00018461538461538463,
      "loss": 0.3705,
      "step": 20
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.38434720039367676,
      "learning_rate": 0.00017692307692307693,
      "loss": 0.2474,
      "step": 30
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.6597588062286377,
      "learning_rate": 0.00016923076923076923,
      "loss": 0.2648,
      "step": 40
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 6.412318706512451,
      "learning_rate": 0.00016153846153846155,
      "loss": 0.2766,
      "step": 50
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 4.713058948516846,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.2076,
      "step": 60
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.7322153449058533,
      "learning_rate": 0.00014615384615384615,
      "loss": 0.1394,
      "step": 70
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.17962901294231415,
      "learning_rate": 0.00013846153846153847,
      "loss": 0.1321,
      "step": 80
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.38781630992889404,
      "learning_rate": 0.00013076923076923077,
      "loss": 0.0399,
      "step": 90
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.7888959646224976,
      "learning_rate": 0.0001230769230769231,
      "loss": 0.0631,
      "step": 100
    },
    {
      "epoch": 1.5384615384615383,
      "eval_accuracy": 0.9849624060150376,
      "eval_loss": 0.07106763869524002,
      "eval_runtime": 1.9552,
      "eval_samples_per_second": 68.024,
      "eval_steps_per_second": 8.695,
      "step": 100
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 1.7944247722625732,
      "learning_rate": 0.00011538461538461538,
      "loss": 0.1224,
      "step": 110
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 1.4098163843154907,
      "learning_rate": 0.0001076923076923077,
      "loss": 0.1294,
      "step": 120
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.0332523584365845,
      "learning_rate": 0.0001,
      "loss": 0.0575,
      "step": 130
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 2.570497512817383,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.0472,
      "step": 140
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.09198305010795593,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.0345,
      "step": 150
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 3.40727162361145,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.03,
      "step": 160
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.07246225327253342,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.0402,
      "step": 170
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 1.846726894378662,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.0652,
      "step": 180
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 3.1595141887664795,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.0358,
      "step": 190
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.06781166791915894,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.0409,
      "step": 200
    },
    {
      "epoch": 3.076923076923077,
      "eval_accuracy": 0.9699248120300752,
      "eval_loss": 0.12198615819215775,
      "eval_runtime": 1.6615,
      "eval_samples_per_second": 80.047,
      "eval_steps_per_second": 10.232,
      "step": 200
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 0.06514012068510056,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.0484,
      "step": 210
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 0.06250347942113876,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.0142,
      "step": 220
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 0.06651216000318527,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.0123,
      "step": 230
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.07879933714866638,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.0122,
      "step": 240
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.062080804258584976,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.0144,
      "step": 250
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.06278563290834427,
      "learning_rate": 0.0,
      "loss": 0.0125,
      "step": 260
    },
    {
      "epoch": 4.0,
      "step": 260,
      "total_flos": 3.205097416476426e+17,
      "train_loss": 0.12752302890786757,
      "train_runtime": 91.8806,
      "train_samples_per_second": 45.015,
      "train_steps_per_second": 2.83
    }
  ],
  "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
}