{
  "best_metric": 0.8655030800821355,
  "best_model_checkpoint": "AnimeCharacterClassifierMark1/checkpoint-258",
  "epoch": 16.0,
  "eval_steps": 500,
  "global_step": 276,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.58,
      "learning_rate": 6.944444444444445e-06,
      "loss": 5.0145,
      "step": 10
    },
    {
      "epoch": 0.99,
      "eval_accuracy": 0.009240246406570842,
      "eval_loss": 4.930349826812744,
      "eval_runtime": 9.5929,
      "eval_samples_per_second": 101.533,
      "eval_steps_per_second": 0.834,
      "step": 17
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.388888888888889e-05,
      "loss": 4.932,
      "step": 20
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 4.8416,
      "step": 30
    },
    {
      "epoch": 1.97,
      "eval_accuracy": 0.028747433264887063,
      "eval_loss": 4.748697757720947,
      "eval_runtime": 8.8137,
      "eval_samples_per_second": 110.51,
      "eval_steps_per_second": 0.908,
      "step": 34
    },
    {
      "epoch": 2.32,
      "learning_rate": 2.777777777777778e-05,
      "loss": 4.6652,
      "step": 40
    },
    {
      "epoch": 2.9,
      "learning_rate": 3.472222222222222e-05,
      "loss": 4.4383,
      "step": 50
    },
    {
      "epoch": 2.96,
      "eval_accuracy": 0.11704312114989733,
      "eval_loss": 4.359685897827148,
      "eval_runtime": 10.311,
      "eval_samples_per_second": 94.462,
      "eval_steps_per_second": 0.776,
      "step": 51
    },
    {
      "epoch": 3.48,
      "learning_rate": 4.166666666666667e-05,
      "loss": 4.0762,
      "step": 60
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.32238193018480493,
      "eval_loss": 3.641871213912964,
      "eval_runtime": 9.02,
      "eval_samples_per_second": 107.982,
      "eval_steps_per_second": 0.887,
      "step": 69
    },
    {
      "epoch": 4.06,
      "learning_rate": 4.8611111111111115e-05,
      "loss": 3.6518,
      "step": 70
    },
    {
      "epoch": 4.64,
      "learning_rate": 4.937694704049845e-05,
      "loss": 3.108,
      "step": 80
    },
    {
      "epoch": 4.99,
      "eval_accuracy": 0.5246406570841889,
      "eval_loss": 2.857390880584717,
      "eval_runtime": 8.9304,
      "eval_samples_per_second": 109.065,
      "eval_steps_per_second": 0.896,
      "step": 86
    },
    {
      "epoch": 5.22,
      "learning_rate": 4.85981308411215e-05,
      "loss": 2.606,
      "step": 90
    },
    {
      "epoch": 5.8,
      "learning_rate": 4.781931464174455e-05,
      "loss": 2.1571,
      "step": 100
    },
    {
      "epoch": 5.97,
      "eval_accuracy": 0.6652977412731006,
      "eval_loss": 2.2128942012786865,
      "eval_runtime": 8.8437,
      "eval_samples_per_second": 110.136,
      "eval_steps_per_second": 0.905,
      "step": 103
    },
    {
      "epoch": 6.38,
      "learning_rate": 4.7040498442367604e-05,
      "loss": 1.7668,
      "step": 110
    },
    {
      "epoch": 6.96,
      "learning_rate": 4.6261682242990654e-05,
      "loss": 1.4685,
      "step": 120
    },
    {
      "epoch": 6.96,
      "eval_accuracy": 0.7494866529774127,
      "eval_loss": 1.7289572954177856,
      "eval_runtime": 9.9463,
      "eval_samples_per_second": 97.926,
      "eval_steps_per_second": 0.804,
      "step": 120
    },
    {
      "epoch": 7.54,
      "learning_rate": 4.548286604361371e-05,
      "loss": 1.1649,
      "step": 130
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.797741273100616,
      "eval_loss": 1.3861801624298096,
      "eval_runtime": 8.8226,
      "eval_samples_per_second": 110.398,
      "eval_steps_per_second": 0.907,
      "step": 138
    },
    {
      "epoch": 8.12,
      "learning_rate": 4.470404984423676e-05,
      "loss": 0.9897,
      "step": 140
    },
    {
      "epoch": 8.7,
      "learning_rate": 4.392523364485982e-05,
      "loss": 0.7905,
      "step": 150
    },
    {
      "epoch": 8.99,
      "eval_accuracy": 0.8213552361396304,
      "eval_loss": 1.1588941812515259,
      "eval_runtime": 8.795,
      "eval_samples_per_second": 110.745,
      "eval_steps_per_second": 0.91,
      "step": 155
    },
    {
      "epoch": 9.28,
      "learning_rate": 4.314641744548287e-05,
      "loss": 0.6727,
      "step": 160
    },
    {
      "epoch": 9.86,
      "learning_rate": 4.236760124610592e-05,
      "loss": 0.5549,
      "step": 170
    },
    {
      "epoch": 9.97,
      "eval_accuracy": 0.8295687885010267,
      "eval_loss": 1.0262539386749268,
      "eval_runtime": 8.8584,
      "eval_samples_per_second": 109.953,
      "eval_steps_per_second": 0.903,
      "step": 172
    },
    {
      "epoch": 10.43,
      "learning_rate": 4.1588785046728974e-05,
      "loss": 0.4577,
      "step": 180
    },
    {
      "epoch": 10.96,
      "eval_accuracy": 0.8367556468172485,
      "eval_loss": 0.8994325995445251,
      "eval_runtime": 8.7654,
      "eval_samples_per_second": 111.119,
      "eval_steps_per_second": 0.913,
      "step": 189
    },
    {
      "epoch": 11.01,
      "learning_rate": 4.0809968847352024e-05,
      "loss": 0.3757,
      "step": 190
    },
    {
      "epoch": 11.59,
      "learning_rate": 4.003115264797508e-05,
      "loss": 0.2964,
      "step": 200
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.8552361396303901,
      "eval_loss": 0.808638870716095,
      "eval_runtime": 11.2618,
      "eval_samples_per_second": 86.487,
      "eval_steps_per_second": 0.71,
      "step": 207
    },
    {
      "epoch": 12.17,
      "learning_rate": 3.925233644859813e-05,
      "loss": 0.2592,
      "step": 210
    },
    {
      "epoch": 12.75,
      "learning_rate": 3.847352024922119e-05,
      "loss": 0.194,
      "step": 220
    },
    {
      "epoch": 12.99,
      "eval_accuracy": 0.8583162217659137,
      "eval_loss": 0.744567334651947,
      "eval_runtime": 8.8124,
      "eval_samples_per_second": 110.526,
      "eval_steps_per_second": 0.908,
      "step": 224
    },
    {
      "epoch": 13.33,
      "learning_rate": 3.769470404984424e-05,
      "loss": 0.1626,
      "step": 230
    },
    {
      "epoch": 13.91,
      "learning_rate": 3.691588785046729e-05,
      "loss": 0.1358,
      "step": 240
    },
    {
      "epoch": 13.97,
      "eval_accuracy": 0.8572895277207392,
      "eval_loss": 0.7063936591148376,
      "eval_runtime": 8.8917,
      "eval_samples_per_second": 109.54,
      "eval_steps_per_second": 0.9,
      "step": 241
    },
    {
      "epoch": 14.49,
      "learning_rate": 3.6137071651090344e-05,
      "loss": 0.1116,
      "step": 250
    },
    {
      "epoch": 14.96,
      "eval_accuracy": 0.8655030800821355,
      "eval_loss": 0.67196124792099,
      "eval_runtime": 9.0077,
      "eval_samples_per_second": 108.129,
      "eval_steps_per_second": 0.888,
      "step": 258
    },
    {
      "epoch": 15.07,
      "learning_rate": 3.5358255451713394e-05,
      "loss": 0.0974,
      "step": 260
    },
    {
      "epoch": 15.65,
      "learning_rate": 3.457943925233645e-05,
      "loss": 0.0811,
      "step": 270
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.864476386036961,
      "eval_loss": 0.6515084505081177,
      "eval_runtime": 9.3868,
      "eval_samples_per_second": 103.762,
      "eval_steps_per_second": 0.852,
      "step": 276
    },
    {
      "epoch": 16.0,
      "step": 276,
      "total_flos": 1.087746145977493e+19,
      "train_loss": 1.7795628476617993,
      "train_runtime": 3092.1212,
      "train_samples_per_second": 119.027,
      "train_steps_per_second": 0.231
    }
  ],
  "logging_steps": 10,
  "max_steps": 714,
  "num_train_epochs": 42,
  "save_steps": 500,
  "total_flos": 1.087746145977493e+19,
  "trial_name": null,
  "trial_params": null
}