{
  "best_metric": 0.4047260880470276,
  "best_model_checkpoint": "./output/vit-base-riego/checkpoint-300",
  "epoch": 3.0,
  "global_step": 378,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08,
      "learning_rate": 0.0001947089947089947,
      "loss": 0.5579,
      "step": 10
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00018941798941798943,
      "loss": 0.3376,
      "step": 20
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018412698412698412,
      "loss": 0.2934,
      "step": 30
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017883597883597884,
      "loss": 0.3096,
      "step": 40
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00017354497354497354,
      "loss": 0.2475,
      "step": 50
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00016825396825396826,
      "loss": 0.173,
      "step": 60
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00016296296296296295,
      "loss": 0.3087,
      "step": 70
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00015820105820105822,
      "loss": 0.3236,
      "step": 80
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001529100529100529,
      "loss": 0.2005,
      "step": 90
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00014761904761904763,
      "loss": 0.249,
      "step": 100
    },
    {
      "epoch": 0.79,
      "eval_f1": 0.31901840490797545,
      "eval_loss": 0.6620292067527771,
      "eval_runtime": 7.2847,
      "eval_samples_per_second": 132.882,
      "eval_steps_per_second": 16.61,
      "step": 100
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00014232804232804233,
      "loss": 0.2803,
      "step": 110
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013703703703703705,
      "loss": 0.163,
      "step": 120
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.00013174603174603174,
      "loss": 0.2306,
      "step": 130
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00012645502645502646,
      "loss": 0.0607,
      "step": 140
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012116402116402117,
      "loss": 0.1109,
      "step": 150
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0001158730158730159,
      "loss": 0.2241,
      "step": 160
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.00011058201058201059,
      "loss": 0.1394,
      "step": 170
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.00010529100529100531,
      "loss": 0.153,
      "step": 180
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0001,
      "loss": 0.1361,
      "step": 190
    },
    {
      "epoch": 1.59,
      "learning_rate": 9.470899470899471e-05,
      "loss": 0.0348,
      "step": 200
    },
    {
      "epoch": 1.59,
      "eval_f1": 0.427536231884058,
      "eval_loss": 0.514543354511261,
      "eval_runtime": 9.2968,
      "eval_samples_per_second": 104.122,
      "eval_steps_per_second": 13.015,
      "step": 200
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.941798941798942e-05,
      "loss": 0.1362,
      "step": 210
    },
    {
      "epoch": 1.75,
      "learning_rate": 8.412698412698413e-05,
      "loss": 0.1059,
      "step": 220
    },
    {
      "epoch": 1.83,
      "learning_rate": 7.883597883597884e-05,
      "loss": 0.1051,
      "step": 230
    },
    {
      "epoch": 1.9,
      "learning_rate": 7.354497354497355e-05,
      "loss": 0.2335,
      "step": 240
    },
    {
      "epoch": 1.98,
      "learning_rate": 6.825396825396825e-05,
      "loss": 0.0877,
      "step": 250
    },
    {
      "epoch": 2.06,
      "learning_rate": 6.296296296296296e-05,
      "loss": 0.0765,
      "step": 260
    },
    {
      "epoch": 2.14,
      "learning_rate": 5.7671957671957676e-05,
      "loss": 0.0409,
      "step": 270
    },
    {
      "epoch": 2.22,
      "learning_rate": 5.2380952380952384e-05,
      "loss": 0.0978,
      "step": 280
    },
    {
      "epoch": 2.3,
      "learning_rate": 4.708994708994709e-05,
      "loss": 0.048,
      "step": 290
    },
    {
      "epoch": 2.38,
      "learning_rate": 4.17989417989418e-05,
      "loss": 0.0135,
      "step": 300
    },
    {
      "epoch": 2.38,
      "eval_f1": 0.580441640378549,
      "eval_loss": 0.4047260880470276,
      "eval_runtime": 9.0047,
      "eval_samples_per_second": 107.499,
      "eval_steps_per_second": 13.437,
      "step": 300
    },
    {
      "epoch": 2.46,
      "learning_rate": 3.650793650793651e-05,
      "loss": 0.0093,
      "step": 310
    },
    {
      "epoch": 2.54,
      "learning_rate": 3.121693121693122e-05,
      "loss": 0.0163,
      "step": 320
    },
    {
      "epoch": 2.62,
      "learning_rate": 2.5925925925925925e-05,
      "loss": 0.0783,
      "step": 330
    },
    {
      "epoch": 2.7,
      "learning_rate": 2.0634920634920636e-05,
      "loss": 0.0288,
      "step": 340
    },
    {
      "epoch": 2.78,
      "learning_rate": 1.5343915343915344e-05,
      "loss": 0.033,
      "step": 350
    },
    {
      "epoch": 2.86,
      "learning_rate": 1.0052910052910053e-05,
      "loss": 0.0308,
      "step": 360
    },
    {
      "epoch": 2.94,
      "learning_rate": 4.7619047619047615e-06,
      "loss": 0.0293,
      "step": 370
    },
    {
      "epoch": 3.0,
      "step": 378,
      "total_flos": 4.665792694694584e+17,
      "train_loss": 0.15108026370958047,
      "train_runtime": 222.8357,
      "train_samples_per_second": 27.02,
      "train_steps_per_second": 1.696
    }
  ],
  "max_steps": 378,
  "num_train_epochs": 3,
  "total_flos": 4.665792694694584e+17,
  "trial_name": null,
  "trial_params": null
}