{
  "best_metric": 0.619316577911377,
  "best_model_checkpoint": "./vit-base-beans/checkpoint-400",
  "epoch": 3.883495145631068,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1,
      "learning_rate": 0.00019805825242718447,
      "loss": 2.2781,
      "step": 10
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019611650485436895,
      "loss": 2.0539,
      "step": 20
    },
    {
      "epoch": 0.24,
      "eval_accuracy": 0.6347826086956522,
      "eval_loss": 1.684175968170166,
      "eval_runtime": 199.797,
      "eval_samples_per_second": 2.302,
      "eval_steps_per_second": 0.29,
      "step": 25
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001941747572815534,
      "loss": 1.7246,
      "step": 30
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019223300970873787,
      "loss": 1.6027,
      "step": 40
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019029126213592236,
      "loss": 1.4159,
      "step": 50
    },
    {
      "epoch": 0.49,
      "eval_accuracy": 0.6934782608695652,
      "eval_loss": 1.2154264450073242,
      "eval_runtime": 14.461,
      "eval_samples_per_second": 31.81,
      "eval_steps_per_second": 4.011,
      "step": 50
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00018834951456310681,
      "loss": 1.243,
      "step": 60
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00018640776699029127,
      "loss": 1.2138,
      "step": 70
    },
    {
      "epoch": 0.73,
      "eval_accuracy": 0.741304347826087,
      "eval_loss": 1.0337247848510742,
      "eval_runtime": 14.5332,
      "eval_samples_per_second": 31.652,
      "eval_steps_per_second": 3.991,
      "step": 75
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00018446601941747576,
      "loss": 1.096,
      "step": 80
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00018252427184466022,
      "loss": 1.012,
      "step": 90
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00018058252427184467,
      "loss": 0.8889,
      "step": 100
    },
    {
      "epoch": 0.97,
      "eval_accuracy": 0.7652173913043478,
      "eval_loss": 0.845034122467041,
      "eval_runtime": 14.4751,
      "eval_samples_per_second": 31.779,
      "eval_steps_per_second": 4.007,
      "step": 100
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00017864077669902913,
      "loss": 0.7514,
      "step": 110
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00017669902912621362,
      "loss": 0.7239,
      "step": 120
    },
    {
      "epoch": 1.21,
      "eval_accuracy": 0.6869565217391305,
      "eval_loss": 1.0301238298416138,
      "eval_runtime": 13.8604,
      "eval_samples_per_second": 33.188,
      "eval_steps_per_second": 4.185,
      "step": 125
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00017475728155339805,
      "loss": 0.6558,
      "step": 130
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00017281553398058253,
      "loss": 0.6192,
      "step": 140
    },
    {
      "epoch": 1.46,
      "learning_rate": 0.000170873786407767,
      "loss": 0.6241,
      "step": 150
    },
    {
      "epoch": 1.46,
      "eval_accuracy": 0.7869565217391304,
      "eval_loss": 0.7646523118019104,
      "eval_runtime": 13.9259,
      "eval_samples_per_second": 33.032,
      "eval_steps_per_second": 4.165,
      "step": 150
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00016893203883495145,
      "loss": 0.6511,
      "step": 160
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.00016699029126213594,
      "loss": 0.7607,
      "step": 170
    },
    {
      "epoch": 1.7,
      "eval_accuracy": 0.7956521739130434,
      "eval_loss": 0.7208316922187805,
      "eval_runtime": 15.3767,
      "eval_samples_per_second": 29.915,
      "eval_steps_per_second": 3.772,
      "step": 175
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0001650485436893204,
      "loss": 0.6508,
      "step": 180
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00016310679611650485,
      "loss": 0.5474,
      "step": 190
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.0001611650485436893,
      "loss": 0.5841,
      "step": 200
    },
    {
      "epoch": 1.94,
      "eval_accuracy": 0.7913043478260869,
      "eval_loss": 0.6974421143531799,
      "eval_runtime": 13.8536,
      "eval_samples_per_second": 33.204,
      "eval_steps_per_second": 4.187,
      "step": 200
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0001592233009708738,
      "loss": 0.5992,
      "step": 210
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.00015728155339805825,
      "loss": 0.3827,
      "step": 220
    },
    {
      "epoch": 2.18,
      "eval_accuracy": 0.7869565217391304,
      "eval_loss": 0.6890577077865601,
      "eval_runtime": 14.5884,
      "eval_samples_per_second": 31.532,
      "eval_steps_per_second": 3.976,
      "step": 225
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001553398058252427,
      "loss": 0.4169,
      "step": 230
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0001533980582524272,
      "loss": 0.3825,
      "step": 240
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00015145631067961166,
      "loss": 0.3534,
      "step": 250
    },
    {
      "epoch": 2.43,
      "eval_accuracy": 0.8,
      "eval_loss": 0.6881299614906311,
      "eval_runtime": 14.5452,
      "eval_samples_per_second": 31.626,
      "eval_steps_per_second": 3.988,
      "step": 250
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00014951456310679611,
      "loss": 0.2475,
      "step": 260
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0001475728155339806,
      "loss": 0.438,
      "step": 270
    },
    {
      "epoch": 2.67,
      "eval_accuracy": 0.7869565217391304,
      "eval_loss": 0.794903039932251,
      "eval_runtime": 14.6276,
      "eval_samples_per_second": 31.447,
      "eval_steps_per_second": 3.965,
      "step": 275
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.00014563106796116506,
      "loss": 0.3039,
      "step": 280
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.00014368932038834952,
      "loss": 0.2605,
      "step": 290
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.000141747572815534,
      "loss": 0.4453,
      "step": 300
    },
    {
      "epoch": 2.91,
      "eval_accuracy": 0.7804347826086957,
      "eval_loss": 0.7851635217666626,
      "eval_runtime": 14.6262,
      "eval_samples_per_second": 31.45,
      "eval_steps_per_second": 3.965,
      "step": 300
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.00013980582524271846,
      "loss": 0.3196,
      "step": 310
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.00013786407766990292,
      "loss": 0.1714,
      "step": 320
    },
    {
      "epoch": 3.16,
      "eval_accuracy": 0.7956521739130434,
      "eval_loss": 0.7182856798171997,
      "eval_runtime": 16.1817,
      "eval_samples_per_second": 28.427,
      "eval_steps_per_second": 3.584,
      "step": 325
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.0001359223300970874,
      "loss": 0.1467,
      "step": 330
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.00013398058252427186,
      "loss": 0.1825,
      "step": 340
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.00013203883495145632,
      "loss": 0.1664,
      "step": 350
    },
    {
      "epoch": 3.4,
      "eval_accuracy": 0.8,
      "eval_loss": 0.6710854172706604,
      "eval_runtime": 14.7551,
      "eval_samples_per_second": 31.176,
      "eval_steps_per_second": 3.931,
      "step": 350
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.00013009708737864078,
      "loss": 0.1266,
      "step": 360
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.00012815533980582526,
      "loss": 0.1962,
      "step": 370
    },
    {
      "epoch": 3.64,
      "eval_accuracy": 0.8043478260869565,
      "eval_loss": 0.7439975738525391,
      "eval_runtime": 14.5665,
      "eval_samples_per_second": 31.579,
      "eval_steps_per_second": 3.982,
      "step": 375
    },
    {
      "epoch": 3.69,
      "learning_rate": 0.00012621359223300972,
      "loss": 0.1609,
      "step": 380
    },
    {
      "epoch": 3.79,
      "learning_rate": 0.00012427184466019418,
      "loss": 0.1891,
      "step": 390
    },
    {
      "epoch": 3.88,
      "learning_rate": 0.00012233009708737864,
      "loss": 0.1961,
      "step": 400
    },
    {
      "epoch": 3.88,
      "eval_accuracy": 0.8391304347826087,
      "eval_loss": 0.619316577911377,
      "eval_runtime": 14.1432,
      "eval_samples_per_second": 32.525,
      "eval_steps_per_second": 4.101,
      "step": 400
    }
  ],
  "max_steps": 1030,
  "num_train_epochs": 10,
  "total_flos": 4.929663074408755e+17,
  "trial_name": null,
  "trial_params": null
}