{
  "best_metric": 0.22492648661136627,
  "best_model_checkpoint": "finetuned-indian-food/checkpoint-600",
  "epoch": 4.0,
  "eval_steps": 100,
  "global_step": 668,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "learning_rate": 0.0001970059880239521,
      "loss": 0.7242,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019401197604790419,
      "loss": 0.5,
      "step": 20
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001910179640718563,
      "loss": 0.4122,
      "step": 30
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0001880239520958084,
      "loss": 0.3271,
      "step": 40
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001850299401197605,
      "loss": 0.2387,
      "step": 50
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00018203592814371256,
      "loss": 0.2743,
      "step": 60
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001790419161676647,
      "loss": 0.2427,
      "step": 70
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001760479041916168,
      "loss": 0.2863,
      "step": 80
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00017305389221556887,
      "loss": 0.2558,
      "step": 90
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00017005988023952097,
      "loss": 0.3083,
      "step": 100
    },
    {
      "epoch": 0.6,
      "eval_accuracy": 0.9139213602550478,
      "eval_loss": 0.36738213896751404,
      "eval_runtime": 29.7859,
      "eval_samples_per_second": 31.592,
      "eval_steps_per_second": 3.962,
      "step": 100
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00016706586826347307,
      "loss": 0.4045,
      "step": 110
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00016407185628742517,
      "loss": 0.2997,
      "step": 120
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00016107784431137724,
      "loss": 0.6153,
      "step": 130
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00015808383233532935,
      "loss": 0.5334,
      "step": 140
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00015508982035928145,
      "loss": 0.4115,
      "step": 150
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00015209580838323355,
      "loss": 0.5174,
      "step": 160
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00014910179640718565,
      "loss": 0.4409,
      "step": 170
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00014610778443113772,
      "loss": 0.3202,
      "step": 180
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00014311377245508983,
      "loss": 0.4374,
      "step": 190
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00014011976047904193,
      "loss": 0.3447,
      "step": 200
    },
    {
      "epoch": 1.2,
      "eval_accuracy": 0.9277364505844846,
      "eval_loss": 0.291175901889801,
      "eval_runtime": 28.6559,
      "eval_samples_per_second": 32.838,
      "eval_steps_per_second": 4.118,
      "step": 200
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00013712574850299403,
      "loss": 0.2344,
      "step": 210
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.0001341317365269461,
      "loss": 0.3497,
      "step": 220
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0001311377245508982,
      "loss": 0.3752,
      "step": 230
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0001281437125748503,
      "loss": 0.3246,
      "step": 240
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.0001251497005988024,
      "loss": 0.3515,
      "step": 250
    },
    {
      "epoch": 1.56,
      "learning_rate": 0.0001221556886227545,
      "loss": 0.3613,
      "step": 260
    },
    {
      "epoch": 1.62,
      "learning_rate": 0.0001191616766467066,
      "loss": 0.3377,
      "step": 270
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0001161676646706587,
      "loss": 0.1799,
      "step": 280
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00011317365269461077,
      "loss": 0.3553,
      "step": 290
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00011017964071856288,
      "loss": 0.3753,
      "step": 300
    },
    {
      "epoch": 1.8,
      "eval_accuracy": 0.924548352816153,
      "eval_loss": 0.28174886107444763,
      "eval_runtime": 28.984,
      "eval_samples_per_second": 32.466,
      "eval_steps_per_second": 4.071,
      "step": 300
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00010718562874251496,
      "loss": 0.2564,
      "step": 310
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00010419161676646707,
      "loss": 0.4214,
      "step": 320
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.00010119760479041918,
      "loss": 0.2334,
      "step": 330
    },
    {
      "epoch": 2.04,
      "learning_rate": 9.820359281437126e-05,
      "loss": 0.2205,
      "step": 340
    },
    {
      "epoch": 2.1,
      "learning_rate": 9.520958083832335e-05,
      "loss": 0.2027,
      "step": 350
    },
    {
      "epoch": 2.16,
      "learning_rate": 9.221556886227547e-05,
      "loss": 0.2422,
      "step": 360
    },
    {
      "epoch": 2.22,
      "learning_rate": 8.922155688622755e-05,
      "loss": 0.2055,
      "step": 370
    },
    {
      "epoch": 2.28,
      "learning_rate": 8.622754491017964e-05,
      "loss": 0.2053,
      "step": 380
    },
    {
      "epoch": 2.34,
      "learning_rate": 8.323353293413174e-05,
      "loss": 0.2482,
      "step": 390
    },
    {
      "epoch": 2.4,
      "learning_rate": 8.023952095808383e-05,
      "loss": 0.1742,
      "step": 400
    },
    {
      "epoch": 2.4,
      "eval_accuracy": 0.9319872476089267,
      "eval_loss": 0.250567227602005,
      "eval_runtime": 29.9273,
      "eval_samples_per_second": 31.443,
      "eval_steps_per_second": 3.943,
      "step": 400
    },
    {
      "epoch": 2.46,
      "learning_rate": 7.724550898203593e-05,
      "loss": 0.259,
      "step": 410
    },
    {
      "epoch": 2.51,
      "learning_rate": 7.425149700598802e-05,
      "loss": 0.2942,
      "step": 420
    },
    {
      "epoch": 2.57,
      "learning_rate": 7.125748502994012e-05,
      "loss": 0.2989,
      "step": 430
    },
    {
      "epoch": 2.63,
      "learning_rate": 6.826347305389222e-05,
      "loss": 0.1775,
      "step": 440
    },
    {
      "epoch": 2.69,
      "learning_rate": 6.526946107784432e-05,
      "loss": 0.1276,
      "step": 450
    },
    {
      "epoch": 2.75,
      "learning_rate": 6.227544910179641e-05,
      "loss": 0.1553,
      "step": 460
    },
    {
      "epoch": 2.81,
      "learning_rate": 5.9281437125748505e-05,
      "loss": 0.2272,
      "step": 470
    },
    {
      "epoch": 2.87,
      "learning_rate": 5.62874251497006e-05,
      "loss": 0.2583,
      "step": 480
    },
    {
      "epoch": 2.93,
      "learning_rate": 5.3293413173652694e-05,
      "loss": 0.167,
      "step": 490
    },
    {
      "epoch": 2.99,
      "learning_rate": 5.029940119760479e-05,
      "loss": 0.1844,
      "step": 500
    },
    {
      "epoch": 2.99,
      "eval_accuracy": 0.9415515409139213,
      "eval_loss": 0.2510787546634674,
      "eval_runtime": 29.362,
      "eval_samples_per_second": 32.048,
      "eval_steps_per_second": 4.019,
      "step": 500
    },
    {
      "epoch": 3.05,
      "learning_rate": 4.7604790419161675e-05,
      "loss": 0.2104,
      "step": 510
    },
    {
      "epoch": 3.11,
      "learning_rate": 4.4610778443113777e-05,
      "loss": 0.183,
      "step": 520
    },
    {
      "epoch": 3.17,
      "learning_rate": 4.161676646706587e-05,
      "loss": 0.1606,
      "step": 530
    },
    {
      "epoch": 3.23,
      "learning_rate": 3.8622754491017966e-05,
      "loss": 0.1711,
      "step": 540
    },
    {
      "epoch": 3.29,
      "learning_rate": 3.562874251497006e-05,
      "loss": 0.1211,
      "step": 550
    },
    {
      "epoch": 3.35,
      "learning_rate": 3.263473053892216e-05,
      "loss": 0.1289,
      "step": 560
    },
    {
      "epoch": 3.41,
      "learning_rate": 2.9640718562874252e-05,
      "loss": 0.1742,
      "step": 570
    },
    {
      "epoch": 3.47,
      "learning_rate": 2.6646706586826347e-05,
      "loss": 0.2005,
      "step": 580
    },
    {
      "epoch": 3.53,
      "learning_rate": 2.3652694610778445e-05,
      "loss": 0.1092,
      "step": 590
    },
    {
      "epoch": 3.59,
      "learning_rate": 2.065868263473054e-05,
      "loss": 0.1797,
      "step": 600
    },
    {
      "epoch": 3.59,
      "eval_accuracy": 0.9415515409139213,
      "eval_loss": 0.22492648661136627,
      "eval_runtime": 28.7472,
      "eval_samples_per_second": 32.734,
      "eval_steps_per_second": 4.105,
      "step": 600
    },
    {
      "epoch": 3.65,
      "learning_rate": 1.7664670658682637e-05,
      "loss": 0.1906,
      "step": 610
    },
    {
      "epoch": 3.71,
      "learning_rate": 1.467065868263473e-05,
      "loss": 0.1834,
      "step": 620
    },
    {
      "epoch": 3.77,
      "learning_rate": 1.1676646706586828e-05,
      "loss": 0.1454,
      "step": 630
    },
    {
      "epoch": 3.83,
      "learning_rate": 8.682634730538922e-06,
      "loss": 0.2321,
      "step": 640
    },
    {
      "epoch": 3.89,
      "learning_rate": 5.688622754491018e-06,
      "loss": 0.1515,
      "step": 650
    },
    {
      "epoch": 3.95,
      "learning_rate": 2.6946107784431138e-06,
      "loss": 0.1474,
      "step": 660
    },
    {
      "epoch": 4.0,
      "step": 668,
      "total_flos": 1.651775717862015e+18,
      "train_loss": 0.27738739541190827,
      "train_runtime": 949.4922,
      "train_samples_per_second": 22.446,
      "train_steps_per_second": 0.704
    }
  ],
  "logging_steps": 10,
  "max_steps": 668,
  "num_train_epochs": 4,
  "save_steps": 100,
  "total_flos": 1.651775717862015e+18,
  "trial_name": null,
  "trial_params": null
}