{
  "best_metric": 0.10869565217391304,
  "best_model_checkpoint": "swiftformer-xs-DMAE\\checkpoint-3",
  "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": 0.10869565217391304,
      "eval_loss": 113.97916412353516,
      "eval_runtime": 0.6657,
      "eval_samples_per_second": 69.104,
      "eval_steps_per_second": 4.507,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 113.9181137084961,
      "eval_runtime": 0.5771,
      "eval_samples_per_second": 79.702,
      "eval_steps_per_second": 5.198,
      "step": 7
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.00027499999999999996,
      "loss": 114.2395,
      "step": 10
    },
    {
      "epoch": 2.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 113.88134765625,
      "eval_runtime": 0.5806,
      "eval_samples_per_second": 79.223,
      "eval_steps_per_second": 5.167,
      "step": 10
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 113.81156921386719,
      "eval_runtime": 0.6172,
      "eval_samples_per_second": 74.535,
      "eval_steps_per_second": 4.861,
      "step": 14
    },
    {
      "epoch": 4.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 113.69862365722656,
      "eval_runtime": 0.6011,
      "eval_samples_per_second": 76.52,
      "eval_steps_per_second": 4.99,
      "step": 17
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.00025,
      "loss": 113.364,
      "step": 20
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 113.47984313964844,
      "eval_runtime": 0.5961,
      "eval_samples_per_second": 77.162,
      "eval_steps_per_second": 5.032,
      "step": 21
    },
    {
      "epoch": 6.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 113.23371887207031,
      "eval_runtime": 0.5811,
      "eval_samples_per_second": 79.156,
      "eval_steps_per_second": 5.162,
      "step": 24
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 112.82231140136719,
      "eval_runtime": 0.6192,
      "eval_samples_per_second": 74.295,
      "eval_steps_per_second": 4.845,
      "step": 28
    },
    {
      "epoch": 8.57,
      "learning_rate": 0.000225,
      "loss": 111.1062,
      "step": 30
    },
    {
      "epoch": 8.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 112.57879638671875,
      "eval_runtime": 0.6086,
      "eval_samples_per_second": 75.578,
      "eval_steps_per_second": 4.929,
      "step": 31
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 112.4156723022461,
      "eval_runtime": 0.7142,
      "eval_samples_per_second": 64.411,
      "eval_steps_per_second": 4.201,
      "step": 35
    },
    {
      "epoch": 10.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 112.55355072021484,
      "eval_runtime": 0.6382,
      "eval_samples_per_second": 72.082,
      "eval_steps_per_second": 4.701,
      "step": 38
    },
    {
      "epoch": 11.43,
      "learning_rate": 0.00019999999999999998,
      "loss": 114.7018,
      "step": 40
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 111.70433807373047,
      "eval_runtime": 0.5881,
      "eval_samples_per_second": 78.214,
      "eval_steps_per_second": 5.101,
      "step": 42
    },
    {
      "epoch": 12.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 111.65534973144531,
      "eval_runtime": 0.5961,
      "eval_samples_per_second": 77.162,
      "eval_steps_per_second": 5.032,
      "step": 45
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 111.61336517333984,
      "eval_runtime": 0.6682,
      "eval_samples_per_second": 68.845,
      "eval_steps_per_second": 4.49,
      "step": 49
    },
    {
      "epoch": 14.29,
      "learning_rate": 0.000175,
      "loss": 110.4914,
      "step": 50
    },
    {
      "epoch": 14.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 111.59801483154297,
      "eval_runtime": 0.5861,
      "eval_samples_per_second": 78.481,
      "eval_steps_per_second": 5.118,
      "step": 52
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 111.76158142089844,
      "eval_runtime": 0.6762,
      "eval_samples_per_second": 68.03,
      "eval_steps_per_second": 4.437,
      "step": 56
    },
    {
      "epoch": 16.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 111.15796661376953,
      "eval_runtime": 0.5936,
      "eval_samples_per_second": 77.488,
      "eval_steps_per_second": 5.054,
      "step": 59
    },
    {
      "epoch": 17.14,
      "learning_rate": 0.00015,
      "loss": 110.734,
      "step": 60
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 111.71080780029297,
      "eval_runtime": 0.6126,
      "eval_samples_per_second": 75.084,
      "eval_steps_per_second": 4.897,
      "step": 63
    },
    {
      "epoch": 18.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 111.52064514160156,
      "eval_runtime": 0.5926,
      "eval_samples_per_second": 77.619,
      "eval_steps_per_second": 5.062,
      "step": 66
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.000125,
      "loss": 111.3772,
      "step": 70
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 110.88188171386719,
      "eval_runtime": 0.6091,
      "eval_samples_per_second": 75.517,
      "eval_steps_per_second": 4.925,
      "step": 70
    },
    {
      "epoch": 20.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 110.802490234375,
      "eval_runtime": 0.6172,
      "eval_samples_per_second": 74.536,
      "eval_steps_per_second": 4.861,
      "step": 73
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 110.3514633178711,
      "eval_runtime": 0.5981,
      "eval_samples_per_second": 76.906,
      "eval_steps_per_second": 5.016,
      "step": 77
    },
    {
      "epoch": 22.86,
      "learning_rate": 9.999999999999999e-05,
      "loss": 111.2973,
      "step": 80
    },
    {
      "epoch": 22.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 110.23866271972656,
      "eval_runtime": 0.6086,
      "eval_samples_per_second": 75.578,
      "eval_steps_per_second": 4.929,
      "step": 80
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 109.80725860595703,
      "eval_runtime": 0.6562,
      "eval_samples_per_second": 70.104,
      "eval_steps_per_second": 4.572,
      "step": 84
    },
    {
      "epoch": 24.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 109.82267761230469,
      "eval_runtime": 0.5876,
      "eval_samples_per_second": 78.279,
      "eval_steps_per_second": 5.105,
      "step": 87
    },
    {
      "epoch": 25.71,
      "learning_rate": 7.5e-05,
      "loss": 110.7135,
      "step": 90
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 109.60858154296875,
      "eval_runtime": 0.6076,
      "eval_samples_per_second": 75.702,
      "eval_steps_per_second": 4.937,
      "step": 91
    },
    {
      "epoch": 26.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 109.5834732055664,
      "eval_runtime": 0.5922,
      "eval_samples_per_second": 77.683,
      "eval_steps_per_second": 5.066,
      "step": 94
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 109.5829849243164,
      "eval_runtime": 0.6041,
      "eval_samples_per_second": 76.142,
      "eval_steps_per_second": 4.966,
      "step": 98
    },
    {
      "epoch": 28.57,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 109.1264,
      "step": 100
    },
    {
      "epoch": 28.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 109.16484832763672,
      "eval_runtime": 0.5956,
      "eval_samples_per_second": 77.228,
      "eval_steps_per_second": 5.037,
      "step": 101
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 109.06578063964844,
      "eval_runtime": 0.6146,
      "eval_samples_per_second": 74.84,
      "eval_steps_per_second": 4.881,
      "step": 105
    },
    {
      "epoch": 30.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 109.2845687866211,
      "eval_runtime": 0.6191,
      "eval_samples_per_second": 74.297,
      "eval_steps_per_second": 4.845,
      "step": 108
    },
    {
      "epoch": 31.43,
      "learning_rate": 2.4999999999999998e-05,
      "loss": 110.2885,
      "step": 110
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 109.02674865722656,
      "eval_runtime": 0.5961,
      "eval_samples_per_second": 77.162,
      "eval_steps_per_second": 5.032,
      "step": 112
    },
    {
      "epoch": 32.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 109.09725189208984,
      "eval_runtime": 0.6096,
      "eval_samples_per_second": 75.454,
      "eval_steps_per_second": 4.921,
      "step": 115
    },
    {
      "epoch": 34.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 108.87687683105469,
      "eval_runtime": 0.6301,
      "eval_samples_per_second": 73.0,
      "eval_steps_per_second": 4.761,
      "step": 119
    },
    {
      "epoch": 34.29,
      "learning_rate": 0.0,
      "loss": 110.1122,
      "step": 120
    },
    {
      "epoch": 34.29,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 108.8197250366211,
      "eval_runtime": 0.7547,
      "eval_samples_per_second": 60.953,
      "eval_steps_per_second": 3.975,
      "step": 120
    },
    {
      "epoch": 34.29,
      "step": 120,
      "total_flos": 2.0027429927092224e+16,
      "train_loss": 111.46265258789063,
      "train_runtime": 130.8746,
      "train_samples_per_second": 65.1,
      "train_steps_per_second": 0.917
    }
  ],
  "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
}