{
  "best_metric": 1.0196388959884644,
  "best_model_checkpoint": "convnext-tiny-224-finetuned/checkpoint-261",
  "epoch": 28.363636363636363,
  "eval_steps": 500,
  "global_step": 390,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.7272727272727273,
      "grad_norm": 0.9955764412879944,
      "learning_rate": 1.282051282051282e-05,
      "loss": 1.6135,
      "step": 10
    },
    {
      "epoch": 0.9454545454545454,
      "eval_accuracy": {
        "accuracy": 0.22323462414578588
      },
      "eval_logLoss": 1.5881173610687256,
      "eval_loss": 1.588117241859436,
      "eval_runtime": 405.8824,
      "eval_samples_per_second": 1.082,
      "eval_steps_per_second": 0.034,
      "step": 13
    },
    {
      "epoch": 1.4545454545454546,
      "grad_norm": 1.0506945848464966,
      "learning_rate": 2.564102564102564e-05,
      "loss": 1.5823,
      "step": 20
    },
    {
      "epoch": 1.9636363636363636,
      "eval_accuracy": {
        "accuracy": 0.35990888382687924
      },
      "eval_logLoss": 1.5302075147628784,
      "eval_loss": 1.5302073955535889,
      "eval_runtime": 6.3692,
      "eval_samples_per_second": 68.926,
      "eval_steps_per_second": 2.198,
      "step": 27
    },
    {
      "epoch": 2.1818181818181817,
      "grad_norm": 1.089643120765686,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.5485,
      "step": 30
    },
    {
      "epoch": 2.909090909090909,
      "grad_norm": 1.260988712310791,
      "learning_rate": 4.985754985754986e-05,
      "loss": 1.4988,
      "step": 40
    },
    {
      "epoch": 2.981818181818182,
      "eval_accuracy": {
        "accuracy": 0.4874715261958998
      },
      "eval_logLoss": 1.4480493068695068,
      "eval_loss": 1.4480493068695068,
      "eval_runtime": 6.4414,
      "eval_samples_per_second": 68.153,
      "eval_steps_per_second": 2.173,
      "step": 41
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 1.314483642578125,
      "learning_rate": 4.8433048433048433e-05,
      "loss": 1.4303,
      "step": 50
    },
    {
      "epoch": 4.0,
      "eval_accuracy": {
        "accuracy": 0.5034168564920274
      },
      "eval_logLoss": 1.3424228429794312,
      "eval_loss": 1.3424230813980103,
      "eval_runtime": 6.3233,
      "eval_samples_per_second": 69.426,
      "eval_steps_per_second": 2.214,
      "step": 55
    },
    {
      "epoch": 4.363636363636363,
      "grad_norm": 1.4022053480148315,
      "learning_rate": 4.700854700854701e-05,
      "loss": 1.3653,
      "step": 60
    },
    {
      "epoch": 4.945454545454545,
      "eval_accuracy": {
        "accuracy": 0.5239179954441914
      },
      "eval_logLoss": 1.2543689012527466,
      "eval_loss": 1.2543689012527466,
      "eval_runtime": 6.3884,
      "eval_samples_per_second": 68.718,
      "eval_steps_per_second": 2.191,
      "step": 68
    },
    {
      "epoch": 5.090909090909091,
      "grad_norm": 1.9723025560379028,
      "learning_rate": 4.558404558404559e-05,
      "loss": 1.2829,
      "step": 70
    },
    {
      "epoch": 5.818181818181818,
      "grad_norm": 1.580014944076538,
      "learning_rate": 4.415954415954416e-05,
      "loss": 1.2232,
      "step": 80
    },
    {
      "epoch": 5.963636363636364,
      "eval_accuracy": {
        "accuracy": 0.5239179954441914
      },
      "eval_logLoss": 1.1867280006408691,
      "eval_loss": 1.1867281198501587,
      "eval_runtime": 6.3056,
      "eval_samples_per_second": 69.621,
      "eval_steps_per_second": 2.22,
      "step": 82
    },
    {
      "epoch": 6.545454545454545,
      "grad_norm": 1.6402294635772705,
      "learning_rate": 4.2735042735042735e-05,
      "loss": 1.1734,
      "step": 90
    },
    {
      "epoch": 6.9818181818181815,
      "eval_accuracy": {
        "accuracy": 0.5466970387243736
      },
      "eval_logLoss": 1.1329878568649292,
      "eval_loss": 1.1329878568649292,
      "eval_runtime": 6.5296,
      "eval_samples_per_second": 67.232,
      "eval_steps_per_second": 2.144,
      "step": 96
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 2.135455846786499,
      "learning_rate": 4.131054131054131e-05,
      "loss": 1.146,
      "step": 100
    },
    {
      "epoch": 8.0,
      "grad_norm": 2.3969764709472656,
      "learning_rate": 3.988603988603989e-05,
      "loss": 1.0747,
      "step": 110
    },
    {
      "epoch": 8.0,
      "eval_accuracy": {
        "accuracy": 0.5626423690205011
      },
      "eval_logLoss": 1.1196777820587158,
      "eval_loss": 1.1196777820587158,
      "eval_runtime": 6.221,
      "eval_samples_per_second": 70.567,
      "eval_steps_per_second": 2.25,
      "step": 110
    },
    {
      "epoch": 8.727272727272727,
      "grad_norm": 2.5098071098327637,
      "learning_rate": 3.846153846153846e-05,
      "loss": 1.0405,
      "step": 120
    },
    {
      "epoch": 8.945454545454545,
      "eval_accuracy": {
        "accuracy": 0.5535307517084282
      },
      "eval_logLoss": 1.0871223211288452,
      "eval_loss": 1.0871223211288452,
      "eval_runtime": 6.225,
      "eval_samples_per_second": 70.522,
      "eval_steps_per_second": 2.249,
      "step": 123
    },
    {
      "epoch": 9.454545454545455,
      "grad_norm": 2.5964548587799072,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.0313,
      "step": 130
    },
    {
      "epoch": 9.963636363636363,
      "eval_accuracy": {
        "accuracy": 0.5671981776765376
      },
      "eval_logLoss": 1.0899914503097534,
      "eval_loss": 1.0899913311004639,
      "eval_runtime": 6.2747,
      "eval_samples_per_second": 69.964,
      "eval_steps_per_second": 2.231,
      "step": 137
    },
    {
      "epoch": 10.181818181818182,
      "grad_norm": 3.431312084197998,
      "learning_rate": 3.561253561253561e-05,
      "loss": 0.9867,
      "step": 140
    },
    {
      "epoch": 10.909090909090908,
      "grad_norm": 1.9337528944015503,
      "learning_rate": 3.418803418803419e-05,
      "loss": 0.959,
      "step": 150
    },
    {
      "epoch": 10.981818181818182,
      "eval_accuracy": {
        "accuracy": 0.5603644646924829
      },
      "eval_logLoss": 1.0766180753707886,
      "eval_loss": 1.0766180753707886,
      "eval_runtime": 6.3132,
      "eval_samples_per_second": 69.537,
      "eval_steps_per_second": 2.218,
      "step": 151
    },
    {
      "epoch": 11.636363636363637,
      "grad_norm": 2.0123398303985596,
      "learning_rate": 3.2763532763532764e-05,
      "loss": 0.9314,
      "step": 160
    },
    {
      "epoch": 12.0,
      "eval_accuracy": {
        "accuracy": 0.5603644646924829
      },
      "eval_logLoss": 1.0608227252960205,
      "eval_loss": 1.0608227252960205,
      "eval_runtime": 6.2643,
      "eval_samples_per_second": 70.079,
      "eval_steps_per_second": 2.235,
      "step": 165
    },
    {
      "epoch": 12.363636363636363,
      "grad_norm": 2.423022508621216,
      "learning_rate": 3.133903133903134e-05,
      "loss": 0.9102,
      "step": 170
    },
    {
      "epoch": 12.945454545454545,
      "eval_accuracy": {
        "accuracy": 0.5649202733485194
      },
      "eval_logLoss": 1.0388399362564087,
      "eval_loss": 1.0388399362564087,
      "eval_runtime": 6.2456,
      "eval_samples_per_second": 70.289,
      "eval_steps_per_second": 2.242,
      "step": 178
    },
    {
      "epoch": 13.090909090909092,
      "grad_norm": 2.3961944580078125,
      "learning_rate": 2.9914529914529915e-05,
      "loss": 0.8825,
      "step": 180
    },
    {
      "epoch": 13.818181818181818,
      "grad_norm": 2.1838817596435547,
      "learning_rate": 2.8490028490028492e-05,
      "loss": 0.8437,
      "step": 190
    },
    {
      "epoch": 13.963636363636363,
      "eval_accuracy": {
        "accuracy": 0.5785876993166287
      },
      "eval_logLoss": 1.0331932306289673,
      "eval_loss": 1.0331931114196777,
      "eval_runtime": 6.3139,
      "eval_samples_per_second": 69.529,
      "eval_steps_per_second": 2.217,
      "step": 192
    },
    {
      "epoch": 14.545454545454545,
      "grad_norm": 2.22560453414917,
      "learning_rate": 2.706552706552707e-05,
      "loss": 0.8234,
      "step": 200
    },
    {
      "epoch": 14.981818181818182,
      "eval_accuracy": {
        "accuracy": 0.5763097949886105
      },
      "eval_logLoss": 1.030157446861267,
      "eval_loss": 1.0301573276519775,
      "eval_runtime": 6.2242,
      "eval_samples_per_second": 70.531,
      "eval_steps_per_second": 2.249,
      "step": 206
    },
    {
      "epoch": 15.272727272727273,
      "grad_norm": 2.565896987915039,
      "learning_rate": 2.564102564102564e-05,
      "loss": 0.7888,
      "step": 210
    },
    {
      "epoch": 16.0,
      "grad_norm": 4.106865882873535,
      "learning_rate": 2.4216524216524217e-05,
      "loss": 0.7883,
      "step": 220
    },
    {
      "epoch": 16.0,
      "eval_accuracy": {
        "accuracy": 0.5649202733485194
      },
      "eval_logLoss": 1.0276356935501099,
      "eval_loss": 1.0276355743408203,
      "eval_runtime": 6.221,
      "eval_samples_per_second": 70.568,
      "eval_steps_per_second": 2.25,
      "step": 220
    },
    {
      "epoch": 16.727272727272727,
      "grad_norm": 2.70666766166687,
      "learning_rate": 2.2792022792022794e-05,
      "loss": 0.7364,
      "step": 230
    },
    {
      "epoch": 16.945454545454545,
      "eval_accuracy": {
        "accuracy": 0.5649202733485194
      },
      "eval_logLoss": 1.0277541875839233,
      "eval_loss": 1.0277544260025024,
      "eval_runtime": 6.2998,
      "eval_samples_per_second": 69.685,
      "eval_steps_per_second": 2.222,
      "step": 233
    },
    {
      "epoch": 17.454545454545453,
      "grad_norm": 3.2285561561584473,
      "learning_rate": 2.1367521367521368e-05,
      "loss": 0.7561,
      "step": 240
    },
    {
      "epoch": 17.963636363636365,
      "eval_accuracy": {
        "accuracy": 0.5649202733485194
      },
      "eval_logLoss": 1.0257948637008667,
      "eval_loss": 1.0257947444915771,
      "eval_runtime": 6.223,
      "eval_samples_per_second": 70.544,
      "eval_steps_per_second": 2.25,
      "step": 247
    },
    {
      "epoch": 18.181818181818183,
      "grad_norm": 3.2319438457489014,
      "learning_rate": 1.9943019943019945e-05,
      "loss": 0.7162,
      "step": 250
    },
    {
      "epoch": 18.90909090909091,
      "grad_norm": 3.1322107315063477,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 0.7062,
      "step": 260
    },
    {
      "epoch": 18.98181818181818,
      "eval_accuracy": {
        "accuracy": 0.5694760820045558
      },
      "eval_logLoss": 1.019639015197754,
      "eval_loss": 1.0196388959884644,
      "eval_runtime": 6.1923,
      "eval_samples_per_second": 70.894,
      "eval_steps_per_second": 2.261,
      "step": 261
    },
    {
      "epoch": 19.636363636363637,
      "grad_norm": 2.8413918018341064,
      "learning_rate": 1.7094017094017095e-05,
      "loss": 0.6897,
      "step": 270
    },
    {
      "epoch": 20.0,
      "eval_accuracy": {
        "accuracy": 0.5558086560364465
      },
      "eval_logLoss": 1.0308281183242798,
      "eval_loss": 1.0308281183242798,
      "eval_runtime": 6.1943,
      "eval_samples_per_second": 70.871,
      "eval_steps_per_second": 2.26,
      "step": 275
    },
    {
      "epoch": 20.363636363636363,
      "grad_norm": 2.9819412231445312,
      "learning_rate": 1.566951566951567e-05,
      "loss": 0.6511,
      "step": 280
    },
    {
      "epoch": 20.945454545454545,
      "eval_accuracy": {
        "accuracy": 0.5626423690205011
      },
      "eval_logLoss": 1.0247496366500854,
      "eval_loss": 1.0247496366500854,
      "eval_runtime": 6.2512,
      "eval_samples_per_second": 70.226,
      "eval_steps_per_second": 2.24,
      "step": 288
    },
    {
      "epoch": 21.09090909090909,
      "grad_norm": 4.308482646942139,
      "learning_rate": 1.4245014245014246e-05,
      "loss": 0.6456,
      "step": 290
    },
    {
      "epoch": 21.818181818181817,
      "grad_norm": 3.1177256107330322,
      "learning_rate": 1.282051282051282e-05,
      "loss": 0.6338,
      "step": 300
    },
    {
      "epoch": 21.963636363636365,
      "eval_accuracy": {
        "accuracy": 0.5603644646924829
      },
      "eval_logLoss": 1.0310317277908325,
      "eval_loss": 1.031031608581543,
      "eval_runtime": 6.1732,
      "eval_samples_per_second": 71.114,
      "eval_steps_per_second": 2.268,
      "step": 302
    },
    {
      "epoch": 22.545454545454547,
      "grad_norm": 2.941620111465454,
      "learning_rate": 1.1396011396011397e-05,
      "loss": 0.619,
      "step": 310
    },
    {
      "epoch": 22.98181818181818,
      "eval_accuracy": {
        "accuracy": 0.5671981776765376
      },
      "eval_logLoss": 1.0257664918899536,
      "eval_loss": 1.025766372680664,
      "eval_runtime": 6.1895,
      "eval_samples_per_second": 70.927,
      "eval_steps_per_second": 2.262,
      "step": 316
    },
    {
      "epoch": 23.272727272727273,
      "grad_norm": 3.034752368927002,
      "learning_rate": 9.971509971509972e-06,
      "loss": 0.6187,
      "step": 320
    },
    {
      "epoch": 24.0,
      "grad_norm": 3.183673620223999,
      "learning_rate": 8.547008547008548e-06,
      "loss": 0.6008,
      "step": 330
    },
    {
      "epoch": 24.0,
      "eval_accuracy": {
        "accuracy": 0.5626423690205011
      },
      "eval_logLoss": 1.0298672914505005,
      "eval_loss": 1.029867172241211,
      "eval_runtime": 6.3628,
      "eval_samples_per_second": 68.995,
      "eval_steps_per_second": 2.2,
      "step": 330
    },
    {
      "epoch": 24.727272727272727,
      "grad_norm": 2.810622215270996,
      "learning_rate": 7.122507122507123e-06,
      "loss": 0.601,
      "step": 340
    },
    {
      "epoch": 24.945454545454545,
      "eval_accuracy": {
        "accuracy": 0.5671981776765376
      },
      "eval_logLoss": 1.0329437255859375,
      "eval_loss": 1.0329439640045166,
      "eval_runtime": 6.2697,
      "eval_samples_per_second": 70.019,
      "eval_steps_per_second": 2.233,
      "step": 343
    },
    {
      "epoch": 25.454545454545453,
      "grad_norm": 4.746636867523193,
      "learning_rate": 5.6980056980056985e-06,
      "loss": 0.595,
      "step": 350
    },
    {
      "epoch": 25.963636363636365,
      "eval_accuracy": {
        "accuracy": 0.5694760820045558
      },
      "eval_logLoss": 1.0277411937713623,
      "eval_loss": 1.0277411937713623,
      "eval_runtime": 6.3782,
      "eval_samples_per_second": 68.828,
      "eval_steps_per_second": 2.195,
      "step": 357
    },
    {
      "epoch": 26.181818181818183,
      "grad_norm": 3.6217236518859863,
      "learning_rate": 4.273504273504274e-06,
      "loss": 0.5713,
      "step": 360
    },
    {
      "epoch": 26.90909090909091,
      "grad_norm": 4.607295989990234,
      "learning_rate": 2.8490028490028492e-06,
      "loss": 0.598,
      "step": 370
    },
    {
      "epoch": 26.98181818181818,
      "eval_accuracy": {
        "accuracy": 0.5671981776765376
      },
      "eval_logLoss": 1.0288209915161133,
      "eval_loss": 1.0288212299346924,
      "eval_runtime": 6.3179,
      "eval_samples_per_second": 69.485,
      "eval_steps_per_second": 2.216,
      "step": 371
    },
    {
      "epoch": 27.636363636363637,
      "grad_norm": 3.8291075229644775,
      "learning_rate": 1.4245014245014246e-06,
      "loss": 0.5771,
      "step": 380
    },
    {
      "epoch": 28.0,
      "eval_accuracy": {
        "accuracy": 0.5603644646924829
      },
      "eval_logLoss": 1.031100869178772,
      "eval_loss": 1.0311009883880615,
      "eval_runtime": 6.2861,
      "eval_samples_per_second": 69.836,
      "eval_steps_per_second": 2.227,
      "step": 385
    },
    {
      "epoch": 28.363636363636363,
      "grad_norm": 3.588949203491211,
      "learning_rate": 0.0,
      "loss": 0.5829,
      "step": 390
    },
    {
      "epoch": 28.363636363636363,
      "eval_accuracy": {
        "accuracy": 0.5626423690205011
      },
      "eval_logLoss": 1.0311228036880493,
      "eval_loss": 1.0311226844787598,
      "eval_runtime": 6.7799,
      "eval_samples_per_second": 64.75,
      "eval_steps_per_second": 2.065,
      "step": 390
    },
    {
      "epoch": 28.363636363636363,
      "step": 390,
      "total_flos": 1.248846666821075e+18,
      "train_loss": 0.9185584948613094,
      "train_runtime": 3358.32,
      "train_samples_per_second": 15.651,
      "train_steps_per_second": 0.116
    }
  ],
  "logging_steps": 10,
  "max_steps": 390,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 30,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.248846666821075e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}