{
  "best_metric": 0.7441600240875771,
  "best_model_checkpoint": "./models/clip-wikispan-10240/checkpoint-70",
  "epoch": 0.554675118858954,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.4999999999999998e-06,
      "loss": 2.7855,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 2.0697,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.5e-06,
      "loss": 1.7787,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.999999999999999e-06,
      "loss": 1.6455,
      "step": 20
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.25e-05,
      "loss": 1.5062,
      "step": 25
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.5e-05,
      "loss": 1.3864,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 1.3053,
      "step": 35
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 1.2504,
      "step": 40
    },
    {
      "epoch": 0.07,
      "learning_rate": 2.25e-05,
      "loss": 1.2084,
      "step": 45
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.5e-05,
      "loss": 1.1481,
      "step": 50
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.75e-05,
      "loss": 1.1259,
      "step": 55
    },
    {
      "epoch": 0.1,
      "learning_rate": 3e-05,
      "loss": 1.092,
      "step": 60
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.974137931034483e-05,
      "loss": 1.0701,
      "step": 65
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.9482758620689654e-05,
      "loss": 1.0545,
      "step": 70
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.9224137931034483e-05,
      "loss": 1.0146,
      "step": 75
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.8965517241379313e-05,
      "loss": 1.0161,
      "step": 80
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.8706896551724136e-05,
      "loss": 0.9977,
      "step": 85
    },
    {
      "epoch": 0.14,
      "learning_rate": 2.8448275862068966e-05,
      "loss": 0.9831,
      "step": 90
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.8189655172413796e-05,
      "loss": 0.9901,
      "step": 95
    },
    {
      "epoch": 0.16,
      "learning_rate": 2.793103448275862e-05,
      "loss": 0.9492,
      "step": 100
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.767241379310345e-05,
      "loss": 0.9572,
      "step": 105
    },
    {
      "epoch": 0.17,
      "learning_rate": 2.741379310344828e-05,
      "loss": 0.9501,
      "step": 110
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.7155172413793102e-05,
      "loss": 0.9408,
      "step": 115
    },
    {
      "epoch": 0.19,
      "learning_rate": 2.689655172413793e-05,
      "loss": 0.9383,
      "step": 120
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.663793103448276e-05,
      "loss": 0.9237,
      "step": 125
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.6379310344827588e-05,
      "loss": 0.9112,
      "step": 130
    },
    {
      "epoch": 0.21,
      "learning_rate": 2.6120689655172414e-05,
      "loss": 0.9042,
      "step": 135
    },
    {
      "epoch": 0.22,
      "learning_rate": 2.586206896551724e-05,
      "loss": 0.911,
      "step": 140
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.560344827586207e-05,
      "loss": 0.9149,
      "step": 145
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.5344827586206897e-05,
      "loss": 0.9,
      "step": 150
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.5086206896551723e-05,
      "loss": 0.8907,
      "step": 155
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.4827586206896553e-05,
      "loss": 0.9004,
      "step": 160
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.456896551724138e-05,
      "loss": 0.8775,
      "step": 165
    },
    {
      "epoch": 0.27,
      "learning_rate": 2.4310344827586206e-05,
      "loss": 0.8751,
      "step": 170
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.4051724137931036e-05,
      "loss": 0.8692,
      "step": 175
    },
    {
      "epoch": 0.29,
      "learning_rate": 2.3793103448275862e-05,
      "loss": 0.8652,
      "step": 180
    },
    {
      "epoch": 0.29,
      "learning_rate": 2.353448275862069e-05,
      "loss": 0.86,
      "step": 185
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.327586206896552e-05,
      "loss": 0.8572,
      "step": 190
    },
    {
      "epoch": 0.31,
      "learning_rate": 2.3017241379310345e-05,
      "loss": 0.8393,
      "step": 195
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.275862068965517e-05,
      "loss": 0.8399,
      "step": 200
    },
    {
      "epoch": 0.32,
      "learning_rate": 2.25e-05,
      "loss": 0.8357,
      "step": 205
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.2241379310344828e-05,
      "loss": 0.8328,
      "step": 210
    },
    {
      "epoch": 0.34,
      "learning_rate": 2.1982758620689654e-05,
      "loss": 0.8415,
      "step": 215
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.1724137931034484e-05,
      "loss": 0.8268,
      "step": 220
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.146551724137931e-05,
      "loss": 0.8275,
      "step": 225
    },
    {
      "epoch": 0.36,
      "learning_rate": 2.1206896551724137e-05,
      "loss": 0.8192,
      "step": 230
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.0948275862068967e-05,
      "loss": 0.8179,
      "step": 235
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.0689655172413797e-05,
      "loss": 0.8254,
      "step": 240
    },
    {
      "epoch": 0.39,
      "learning_rate": 2.043103448275862e-05,
      "loss": 0.8145,
      "step": 245
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.017241379310345e-05,
      "loss": 0.8176,
      "step": 250
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.991379310344828e-05,
      "loss": 0.8209,
      "step": 255
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.9655172413793102e-05,
      "loss": 0.8117,
      "step": 260
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.9396551724137932e-05,
      "loss": 0.823,
      "step": 265
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.9137931034482762e-05,
      "loss": 0.8001,
      "step": 270
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.8879310344827585e-05,
      "loss": 0.8112,
      "step": 275
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.8620689655172415e-05,
      "loss": 0.8062,
      "step": 280
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.836206896551724e-05,
      "loss": 0.7992,
      "step": 285
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.8103448275862068e-05,
      "loss": 0.7895,
      "step": 290
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.7844827586206898e-05,
      "loss": 0.7973,
      "step": 295
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.7586206896551724e-05,
      "loss": 0.7964,
      "step": 300
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.732758620689655e-05,
      "loss": 0.7866,
      "step": 305
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.706896551724138e-05,
      "loss": 0.7879,
      "step": 310
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.6810344827586207e-05,
      "loss": 0.7666,
      "step": 315
    },
    {
      "epoch": 0.51,
      "learning_rate": 1.6551724137931033e-05,
      "loss": 0.7924,
      "step": 320
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.6293103448275863e-05,
      "loss": 0.7818,
      "step": 325
    },
    {
      "epoch": 0.52,
      "learning_rate": 1.603448275862069e-05,
      "loss": 0.7784,
      "step": 330
    },
    {
      "epoch": 0.53,
      "learning_rate": 1.5775862068965516e-05,
      "loss": 0.7786,
      "step": 335
    },
    {
      "epoch": 0.54,
      "learning_rate": 1.5517241379310346e-05,
      "loss": 0.7754,
      "step": 340
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.5258620689655172e-05,
      "loss": 0.7797,
      "step": 345
    },
    {
      "epoch": 0.55,
      "learning_rate": 1.5e-05,
      "loss": 0.7723,
      "step": 350
    }
  ],
  "max_steps": 640,
  "num_train_epochs": 2,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}