{
  "best_metric": 0.9953664541244507,
  "best_model_checkpoint": "Transformers/vit-base-clothing-leafs-example-full-simple/checkpoint-20000",
  "epoch": 4.0,
  "global_step": 28924,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.14,
      "learning_rate": 2.8963836260544875e-05,
      "loss": 1.9495,
      "step": 1000
    },
    {
      "epoch": 0.14,
      "eval_accuracy": 0.6307309314708527,
      "eval_loss": 1.4553368091583252,
      "eval_runtime": 164.2927,
      "eval_samples_per_second": 176.039,
      "eval_steps_per_second": 22.009,
      "step": 1000
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.7926635320149357e-05,
      "loss": 1.3079,
      "step": 2000
    },
    {
      "epoch": 0.28,
      "eval_accuracy": 0.6676924140792476,
      "eval_loss": 1.2347172498703003,
      "eval_runtime": 157.0046,
      "eval_samples_per_second": 184.211,
      "eval_steps_per_second": 23.031,
      "step": 2000
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.6890471580694235e-05,
      "loss": 1.178,
      "step": 3000
    },
    {
      "epoch": 0.41,
      "eval_accuracy": 0.6757831408616278,
      "eval_loss": 1.1606581211090088,
      "eval_runtime": 154.1382,
      "eval_samples_per_second": 187.637,
      "eval_steps_per_second": 23.459,
      "step": 3000
    },
    {
      "epoch": 0.55,
      "learning_rate": 2.5853270640298713e-05,
      "loss": 1.1324,
      "step": 4000
    },
    {
      "epoch": 0.55,
      "eval_accuracy": 0.682387110158357,
      "eval_loss": 1.1307393312454224,
      "eval_runtime": 154.2255,
      "eval_samples_per_second": 187.531,
      "eval_steps_per_second": 23.446,
      "step": 4000
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.4816069699903195e-05,
      "loss": 1.0928,
      "step": 5000
    },
    {
      "epoch": 0.69,
      "eval_accuracy": 0.6908927460065002,
      "eval_loss": 1.0955638885498047,
      "eval_runtime": 152.3863,
      "eval_samples_per_second": 189.794,
      "eval_steps_per_second": 23.729,
      "step": 5000
    },
    {
      "epoch": 0.83,
      "learning_rate": 2.3778868759507677e-05,
      "loss": 1.0679,
      "step": 6000
    },
    {
      "epoch": 0.83,
      "eval_accuracy": 0.6912385035613028,
      "eval_loss": 1.0789850950241089,
      "eval_runtime": 153.243,
      "eval_samples_per_second": 188.733,
      "eval_steps_per_second": 23.597,
      "step": 6000
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.274166781911216e-05,
      "loss": 1.0488,
      "step": 7000
    },
    {
      "epoch": 0.97,
      "eval_accuracy": 0.7013691999170182,
      "eval_loss": 1.0485832691192627,
      "eval_runtime": 155.3074,
      "eval_samples_per_second": 186.224,
      "eval_steps_per_second": 23.283,
      "step": 7000
    },
    {
      "epoch": 1.11,
      "learning_rate": 2.1705504079657033e-05,
      "loss": 0.9548,
      "step": 8000
    },
    {
      "epoch": 1.11,
      "eval_accuracy": 0.70161123020538,
      "eval_loss": 1.0449484586715698,
      "eval_runtime": 154.3409,
      "eval_samples_per_second": 187.39,
      "eval_steps_per_second": 23.429,
      "step": 8000
    },
    {
      "epoch": 1.24,
      "learning_rate": 2.0668303139261512e-05,
      "loss": 0.9352,
      "step": 9000
    },
    {
      "epoch": 1.24,
      "eval_accuracy": 0.7042044118663993,
      "eval_loss": 1.034779667854309,
      "eval_runtime": 155.2786,
      "eval_samples_per_second": 186.259,
      "eval_steps_per_second": 23.287,
      "step": 9000
    },
    {
      "epoch": 1.38,
      "learning_rate": 1.963213939980639e-05,
      "loss": 0.9164,
      "step": 10000
    },
    {
      "epoch": 1.38,
      "eval_accuracy": 0.7033745937348731,
      "eval_loss": 1.0340265035629272,
      "eval_runtime": 154.4587,
      "eval_samples_per_second": 187.247,
      "eval_steps_per_second": 23.411,
      "step": 10000
    },
    {
      "epoch": 1.52,
      "learning_rate": 1.8595975660351264e-05,
      "loss": 0.9267,
      "step": 11000
    },
    {
      "epoch": 1.52,
      "eval_accuracy": 0.7089412903671946,
      "eval_loss": 1.0178329944610596,
      "eval_runtime": 153.0672,
      "eval_samples_per_second": 188.95,
      "eval_steps_per_second": 23.624,
      "step": 11000
    },
    {
      "epoch": 1.66,
      "learning_rate": 1.7558774719955746e-05,
      "loss": 0.9058,
      "step": 12000
    },
    {
      "epoch": 1.66,
      "eval_accuracy": 0.7063481087061753,
      "eval_loss": 1.0159752368927002,
      "eval_runtime": 153.6019,
      "eval_samples_per_second": 188.292,
      "eval_steps_per_second": 23.541,
      "step": 12000
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.6521573779560228e-05,
      "loss": 0.9028,
      "step": 13000
    },
    {
      "epoch": 1.8,
      "eval_accuracy": 0.7110504114514902,
      "eval_loss": 1.0084210634231567,
      "eval_runtime": 154.4213,
      "eval_samples_per_second": 187.293,
      "eval_steps_per_second": 23.416,
      "step": 13000
    },
    {
      "epoch": 1.94,
      "learning_rate": 1.548437283916471e-05,
      "loss": 0.9093,
      "step": 14000
    },
    {
      "epoch": 1.94,
      "eval_accuracy": 0.7136090173570292,
      "eval_loss": 1.00092351436615,
      "eval_runtime": 151.8217,
      "eval_samples_per_second": 190.5,
      "eval_steps_per_second": 23.817,
      "step": 14000
    },
    {
      "epoch": 2.07,
      "learning_rate": 1.4447171898769188e-05,
      "loss": 0.8346,
      "step": 15000
    },
    {
      "epoch": 2.07,
      "eval_accuracy": 0.7117073508056151,
      "eval_loss": 1.0151883363723755,
      "eval_runtime": 153.6777,
      "eval_samples_per_second": 188.199,
      "eval_steps_per_second": 23.53,
      "step": 15000
    },
    {
      "epoch": 2.21,
      "learning_rate": 1.3411008159314064e-05,
      "loss": 0.7897,
      "step": 16000
    },
    {
      "epoch": 2.21,
      "eval_accuracy": 0.7141276536892331,
      "eval_loss": 1.0071992874145508,
      "eval_runtime": 153.402,
      "eval_samples_per_second": 188.537,
      "eval_steps_per_second": 23.572,
      "step": 16000
    },
    {
      "epoch": 2.35,
      "learning_rate": 1.237484441985894e-05,
      "loss": 0.7869,
      "step": 17000
    },
    {
      "epoch": 2.35,
      "eval_accuracy": 0.7082843510130696,
      "eval_loss": 1.0088136196136475,
      "eval_runtime": 153.7395,
      "eval_samples_per_second": 188.123,
      "eval_steps_per_second": 23.52,
      "step": 17000
    },
    {
      "epoch": 2.49,
      "learning_rate": 1.133764347946342e-05,
      "loss": 0.7853,
      "step": 18000
    },
    {
      "epoch": 2.49,
      "eval_accuracy": 0.7162021990180485,
      "eval_loss": 0.9981487989425659,
      "eval_runtime": 153.6335,
      "eval_samples_per_second": 188.253,
      "eval_steps_per_second": 23.537,
      "step": 18000
    },
    {
      "epoch": 2.63,
      "learning_rate": 1.0300442539067902e-05,
      "loss": 0.7732,
      "step": 19000
    },
    {
      "epoch": 2.63,
      "eval_accuracy": 0.7148537445543185,
      "eval_loss": 1.003010630607605,
      "eval_runtime": 152.6681,
      "eval_samples_per_second": 189.444,
      "eval_steps_per_second": 23.685,
      "step": 19000
    },
    {
      "epoch": 2.77,
      "learning_rate": 9.264278799612779e-06,
      "loss": 0.779,
      "step": 20000
    },
    {
      "epoch": 2.77,
      "eval_accuracy": 0.7155106839084434,
      "eval_loss": 0.9953664541244507,
      "eval_runtime": 154.6075,
      "eval_samples_per_second": 187.067,
      "eval_steps_per_second": 23.388,
      "step": 20000
    },
    {
      "epoch": 2.9,
      "learning_rate": 8.227077859217259e-06,
      "loss": 0.7655,
      "step": 21000
    },
    {
      "epoch": 2.9,
      "eval_accuracy": 0.7178618352811009,
      "eval_loss": 0.9971597790718079,
      "eval_runtime": 153.1084,
      "eval_samples_per_second": 188.899,
      "eval_steps_per_second": 23.617,
      "step": 21000
    },
    {
      "epoch": 3.04,
      "learning_rate": 7.1898769188217404e-06,
      "loss": 0.74,
      "step": 22000
    },
    {
      "epoch": 3.04,
      "eval_accuracy": 0.7138164718899108,
      "eval_loss": 1.0114420652389526,
      "eval_runtime": 152.2988,
      "eval_samples_per_second": 189.903,
      "eval_steps_per_second": 23.743,
      "step": 22000
    },
    {
      "epoch": 3.18,
      "learning_rate": 6.1526759784262205e-06,
      "loss": 0.6824,
      "step": 23000
    },
    {
      "epoch": 3.18,
      "eval_accuracy": 0.7130212295138649,
      "eval_loss": 1.017103910446167,
      "eval_runtime": 152.678,
      "eval_samples_per_second": 189.431,
      "eval_steps_per_second": 23.684,
      "step": 23000
    },
    {
      "epoch": 3.32,
      "learning_rate": 5.116512238971097e-06,
      "loss": 0.68,
      "step": 24000
    },
    {
      "epoch": 3.32,
      "eval_accuracy": 0.7177581080146601,
      "eval_loss": 1.011143684387207,
      "eval_runtime": 152.6609,
      "eval_samples_per_second": 189.453,
      "eval_steps_per_second": 23.686,
      "step": 24000
    },
    {
      "epoch": 3.46,
      "learning_rate": 4.079311298575578e-06,
      "loss": 0.6787,
      "step": 25000
    },
    {
      "epoch": 3.46,
      "eval_accuracy": 0.7151303505981605,
      "eval_loss": 1.0124437808990479,
      "eval_runtime": 152.3072,
      "eval_samples_per_second": 189.893,
      "eval_steps_per_second": 23.741,
      "step": 25000
    },
    {
      "epoch": 3.6,
      "learning_rate": 3.042110358180058e-06,
      "loss": 0.6808,
      "step": 26000
    },
    {
      "epoch": 3.6,
      "eval_accuracy": 0.7149920475762396,
      "eval_loss": 1.0181164741516113,
      "eval_runtime": 153.0013,
      "eval_samples_per_second": 189.031,
      "eval_steps_per_second": 23.634,
      "step": 26000
    },
    {
      "epoch": 3.73,
      "learning_rate": 2.0059466187249345e-06,
      "loss": 0.6561,
      "step": 27000
    },
    {
      "epoch": 3.73,
      "eval_accuracy": 0.7168245626166931,
      "eval_loss": 1.0144038200378418,
      "eval_runtime": 153.8199,
      "eval_samples_per_second": 188.025,
      "eval_steps_per_second": 23.508,
      "step": 27000
    },
    {
      "epoch": 3.87,
      "learning_rate": 9.697828792698105e-07,
      "loss": 0.6611,
      "step": 28000
    },
    {
      "epoch": 3.87,
      "eval_accuracy": 0.7155106839084434,
      "eval_loss": 1.0154051780700684,
      "eval_runtime": 153.3953,
      "eval_samples_per_second": 188.546,
      "eval_steps_per_second": 23.573,
      "step": 28000
    },
    {
      "epoch": 4.0,
      "step": 28924,
      "total_flos": 7.174773947150918e+19,
      "train_loss": 0.9035214643197474,
      "train_runtime": 13914.0149,
      "train_samples_per_second": 66.516,
      "train_steps_per_second": 2.079
    }
  ],
  "max_steps": 28924,
  "num_train_epochs": 4,
  "total_flos": 7.174773947150918e+19,
  "trial_name": null,
  "trial_params": null
}