{
  "best_metric": 0.7391304347826086,
  "best_model_checkpoint": "swiftformer-xs-DMAE\\checkpoint-87",
  "epoch": 34.285714285714285,
  "eval_steps": 500,
  "global_step": 120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.86,
      "eval_accuracy": 0.32608695652173914,
      "eval_loss": 1.3860292434692383,
      "eval_runtime": 0.6541,
      "eval_samples_per_second": 70.321,
      "eval_steps_per_second": 4.586,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.5,
      "eval_loss": 1.383039951324463,
      "eval_runtime": 0.6141,
      "eval_samples_per_second": 74.902,
      "eval_steps_per_second": 4.885,
      "step": 7
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.00016666666666666666,
      "loss": 1.3842,
      "step": 10
    },
    {
      "epoch": 2.86,
      "eval_accuracy": 0.5869565217391305,
      "eval_loss": 1.3756428956985474,
      "eval_runtime": 0.6407,
      "eval_samples_per_second": 71.802,
      "eval_steps_per_second": 4.683,
      "step": 10
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6086956521739131,
      "eval_loss": 1.3493651151657104,
      "eval_runtime": 0.5981,
      "eval_samples_per_second": 76.904,
      "eval_steps_per_second": 5.015,
      "step": 14
    },
    {
      "epoch": 4.86,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 1.303892731666565,
      "eval_runtime": 0.6221,
      "eval_samples_per_second": 73.938,
      "eval_steps_per_second": 4.822,
      "step": 17
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.0002941176470588235,
      "loss": 1.3427,
      "step": 20
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 1.1961779594421387,
      "eval_runtime": 0.6102,
      "eval_samples_per_second": 75.391,
      "eval_steps_per_second": 4.917,
      "step": 21
    },
    {
      "epoch": 6.86,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 1.1310076713562012,
      "eval_runtime": 0.6321,
      "eval_samples_per_second": 72.769,
      "eval_steps_per_second": 4.746,
      "step": 24
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 1.07782781124115,
      "eval_runtime": 0.5902,
      "eval_samples_per_second": 77.946,
      "eval_steps_per_second": 5.083,
      "step": 28
    },
    {
      "epoch": 8.57,
      "learning_rate": 0.00026470588235294115,
      "loss": 1.1837,
      "step": 30
    },
    {
      "epoch": 8.86,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 1.027555227279663,
      "eval_runtime": 0.6977,
      "eval_samples_per_second": 65.934,
      "eval_steps_per_second": 4.3,
      "step": 31
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.717391304347826,
      "eval_loss": 0.9927520751953125,
      "eval_runtime": 0.6266,
      "eval_samples_per_second": 73.407,
      "eval_steps_per_second": 4.787,
      "step": 35
    },
    {
      "epoch": 10.86,
      "eval_accuracy": 0.717391304347826,
      "eval_loss": 0.9709724187850952,
      "eval_runtime": 0.6331,
      "eval_samples_per_second": 72.653,
      "eval_steps_per_second": 4.738,
      "step": 38
    },
    {
      "epoch": 11.43,
      "learning_rate": 0.0002352941176470588,
      "loss": 1.0531,
      "step": 40
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 0.9734796285629272,
      "eval_runtime": 0.6324,
      "eval_samples_per_second": 72.735,
      "eval_steps_per_second": 4.744,
      "step": 42
    },
    {
      "epoch": 12.86,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 0.9384742379188538,
      "eval_runtime": 0.6201,
      "eval_samples_per_second": 74.177,
      "eval_steps_per_second": 4.838,
      "step": 45
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 0.9601091146469116,
      "eval_runtime": 0.6196,
      "eval_samples_per_second": 74.236,
      "eval_steps_per_second": 4.841,
      "step": 49
    },
    {
      "epoch": 14.29,
      "learning_rate": 0.00020588235294117645,
      "loss": 0.9883,
      "step": 50
    },
    {
      "epoch": 14.86,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 0.9368714094161987,
      "eval_runtime": 0.5906,
      "eval_samples_per_second": 77.882,
      "eval_steps_per_second": 5.079,
      "step": 52
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 0.8928157687187195,
      "eval_runtime": 0.6201,
      "eval_samples_per_second": 74.177,
      "eval_steps_per_second": 4.838,
      "step": 56
    },
    {
      "epoch": 16.86,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 0.8825035691261292,
      "eval_runtime": 0.6252,
      "eval_samples_per_second": 73.581,
      "eval_steps_per_second": 4.799,
      "step": 59
    },
    {
      "epoch": 17.14,
      "learning_rate": 0.0001764705882352941,
      "loss": 0.8632,
      "step": 60
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 0.8742826581001282,
      "eval_runtime": 0.6216,
      "eval_samples_per_second": 73.997,
      "eval_steps_per_second": 4.826,
      "step": 63
    },
    {
      "epoch": 18.86,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 0.8478592038154602,
      "eval_runtime": 0.6091,
      "eval_samples_per_second": 75.517,
      "eval_steps_per_second": 4.925,
      "step": 66
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.00014705882352941175,
      "loss": 0.8732,
      "step": 70
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 0.834061324596405,
      "eval_runtime": 0.6332,
      "eval_samples_per_second": 72.651,
      "eval_steps_per_second": 4.738,
      "step": 70
    },
    {
      "epoch": 20.86,
      "eval_accuracy": 0.717391304347826,
      "eval_loss": 0.8133650422096252,
      "eval_runtime": 0.7277,
      "eval_samples_per_second": 63.215,
      "eval_steps_per_second": 4.123,
      "step": 73
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 0.8844852447509766,
      "eval_runtime": 0.6501,
      "eval_samples_per_second": 70.753,
      "eval_steps_per_second": 4.614,
      "step": 77
    },
    {
      "epoch": 22.86,
      "learning_rate": 0.0001176470588235294,
      "loss": 0.7524,
      "step": 80
    },
    {
      "epoch": 22.86,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 0.9037047624588013,
      "eval_runtime": 0.6262,
      "eval_samples_per_second": 73.464,
      "eval_steps_per_second": 4.791,
      "step": 80
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.6304347826086957,
      "eval_loss": 0.8921377062797546,
      "eval_runtime": 0.6157,
      "eval_samples_per_second": 74.718,
      "eval_steps_per_second": 4.873,
      "step": 84
    },
    {
      "epoch": 24.86,
      "eval_accuracy": 0.7391304347826086,
      "eval_loss": 0.8765698075294495,
      "eval_runtime": 0.6211,
      "eval_samples_per_second": 74.058,
      "eval_steps_per_second": 4.83,
      "step": 87
    },
    {
      "epoch": 25.71,
      "learning_rate": 8.823529411764705e-05,
      "loss": 0.6843,
      "step": 90
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.7391304347826086,
      "eval_loss": 0.8706851005554199,
      "eval_runtime": 0.6322,
      "eval_samples_per_second": 72.766,
      "eval_steps_per_second": 4.746,
      "step": 91
    },
    {
      "epoch": 26.86,
      "eval_accuracy": 0.7391304347826086,
      "eval_loss": 0.8922207951545715,
      "eval_runtime": 0.6461,
      "eval_samples_per_second": 71.192,
      "eval_steps_per_second": 4.643,
      "step": 94
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.8861702084541321,
      "eval_runtime": 0.6096,
      "eval_samples_per_second": 75.454,
      "eval_steps_per_second": 4.921,
      "step": 98
    },
    {
      "epoch": 28.57,
      "learning_rate": 5.88235294117647e-05,
      "loss": 0.7112,
      "step": 100
    },
    {
      "epoch": 28.86,
      "eval_accuracy": 0.7391304347826086,
      "eval_loss": 0.8954079747200012,
      "eval_runtime": 0.6282,
      "eval_samples_per_second": 73.23,
      "eval_steps_per_second": 4.776,
      "step": 101
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.9228313565254211,
      "eval_runtime": 0.6091,
      "eval_samples_per_second": 75.517,
      "eval_steps_per_second": 4.925,
      "step": 105
    },
    {
      "epoch": 30.86,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.9172708988189697,
      "eval_runtime": 0.6367,
      "eval_samples_per_second": 72.253,
      "eval_steps_per_second": 4.712,
      "step": 108
    },
    {
      "epoch": 31.43,
      "learning_rate": 2.941176470588235e-05,
      "loss": 0.6885,
      "step": 110
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.9317991137504578,
      "eval_runtime": 0.6256,
      "eval_samples_per_second": 73.524,
      "eval_steps_per_second": 4.795,
      "step": 112
    },
    {
      "epoch": 32.86,
      "eval_accuracy": 0.7391304347826086,
      "eval_loss": 0.9049164056777954,
      "eval_runtime": 0.6101,
      "eval_samples_per_second": 75.393,
      "eval_steps_per_second": 4.917,
      "step": 115
    },
    {
      "epoch": 34.0,
      "eval_accuracy": 0.717391304347826,
      "eval_loss": 0.915714681148529,
      "eval_runtime": 0.7362,
      "eval_samples_per_second": 62.485,
      "eval_steps_per_second": 4.075,
      "step": 119
    },
    {
      "epoch": 34.29,
      "learning_rate": 0.0,
      "loss": 0.6734,
      "step": 120
    },
    {
      "epoch": 34.29,
      "eval_accuracy": 0.7391304347826086,
      "eval_loss": 0.9050928354263306,
      "eval_runtime": 0.7057,
      "eval_samples_per_second": 65.186,
      "eval_steps_per_second": 4.251,
      "step": 120
    },
    {
      "epoch": 34.29,
      "step": 120,
      "total_flos": 2.0027429927092224e+16,
      "train_loss": 0.9331819852193196,
      "train_runtime": 134.062,
      "train_samples_per_second": 63.553,
      "train_steps_per_second": 0.895
    }
  ],
  "logging_steps": 10,
  "max_steps": 120,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 40,
  "save_steps": 500,
  "total_flos": 2.0027429927092224e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}