{
  "best_metric": 0.007931315340101719,
  "best_model_checkpoint": "./vit-base-beans-demo-v5/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": 0.05331134423613548,
      "learning_rate": 0.00019230769230769233,
      "loss": 0.011,
      "step": 10
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.048330385237932205,
      "learning_rate": 0.00018461538461538463,
      "loss": 0.0094,
      "step": 20
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.044056687504053116,
      "learning_rate": 0.00017692307692307693,
      "loss": 0.0082,
      "step": 30
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.03760308027267456,
      "learning_rate": 0.00016923076923076923,
      "loss": 0.0073,
      "step": 40
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.03363609313964844,
      "learning_rate": 0.00016153846153846155,
      "loss": 0.0065,
      "step": 50
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.03068053536117077,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.0061,
      "step": 60
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.030666179955005646,
      "learning_rate": 0.00014615384615384615,
      "loss": 0.0054,
      "step": 70
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 0.027142781764268875,
      "learning_rate": 0.00013846153846153847,
      "loss": 0.0051,
      "step": 80
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.025556331500411034,
      "learning_rate": 0.00013076923076923077,
      "loss": 0.0048,
      "step": 90
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.024526281282305717,
      "learning_rate": 0.0001230769230769231,
      "loss": 0.0045,
      "step": 100
    },
    {
      "epoch": 1.5384615384615383,
      "eval_accuracy": 1.0,
      "eval_loss": 0.01218804344534874,
      "eval_runtime": 1.3045,
      "eval_samples_per_second": 101.958,
      "eval_steps_per_second": 13.032,
      "step": 100
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.022517597302794456,
      "learning_rate": 0.00011538461538461538,
      "loss": 0.0042,
      "step": 110
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.02247401885688305,
      "learning_rate": 0.0001076923076923077,
      "loss": 0.0041,
      "step": 120
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.021185290068387985,
      "learning_rate": 0.0001,
      "loss": 0.0039,
      "step": 130
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.02046911045908928,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.0037,
      "step": 140
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.020843908190727234,
      "learning_rate": 8.461538461538461e-05,
      "loss": 0.0036,
      "step": 150
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.019343167543411255,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.0035,
      "step": 160
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 0.018962811678647995,
      "learning_rate": 6.923076923076924e-05,
      "loss": 0.0034,
      "step": 170
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.01806730031967163,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.0033,
      "step": 180
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.018040303140878677,
      "learning_rate": 5.384615384615385e-05,
      "loss": 0.0033,
      "step": 190
    },
    {
      "epoch": 3.076923076923077,
      "grad_norm": 0.01774403266608715,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.0032,
      "step": 200
    },
    {
      "epoch": 3.076923076923077,
      "eval_accuracy": 1.0,
      "eval_loss": 0.007931315340101719,
      "eval_runtime": 1.5332,
      "eval_samples_per_second": 86.749,
      "eval_steps_per_second": 11.088,
      "step": 200
    },
    {
      "epoch": 3.230769230769231,
      "grad_norm": 0.017440617084503174,
      "learning_rate": 3.846153846153846e-05,
      "loss": 0.0032,
      "step": 210
    },
    {
      "epoch": 3.3846153846153846,
      "grad_norm": 0.017518451437354088,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.0031,
      "step": 220
    },
    {
      "epoch": 3.5384615384615383,
      "grad_norm": 0.01766134239733219,
      "learning_rate": 2.307692307692308e-05,
      "loss": 0.0031,
      "step": 230
    },
    {
      "epoch": 3.6923076923076925,
      "grad_norm": 0.017332762479782104,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.003,
      "step": 240
    },
    {
      "epoch": 3.8461538461538463,
      "grad_norm": 0.01711300015449524,
      "learning_rate": 7.692307692307694e-06,
      "loss": 0.003,
      "step": 250
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.016509544104337692,
      "learning_rate": 0.0,
      "loss": 0.003,
      "step": 260
    },
    {
      "epoch": 4.0,
      "step": 260,
      "total_flos": 3.205097416476426e+17,
      "train_loss": 0.004738062426734429,
      "train_runtime": 87.348,
      "train_samples_per_second": 47.351,
      "train_steps_per_second": 2.977
    }
  ],
  "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
}