{
  "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": 125514790469632.0,
      "eval_runtime": 0.6752,
      "eval_samples_per_second": 68.133,
      "eval_steps_per_second": 4.443,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6336,
      "eval_samples_per_second": 72.596,
      "eval_steps_per_second": 4.734,
      "step": 7
    },
    {
      "epoch": 2.86,
      "learning_rate": 1.3983050847457627e-05,
      "loss": 125815215043379.2,
      "step": 10
    },
    {
      "epoch": 2.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.5891,
      "eval_samples_per_second": 78.08,
      "eval_steps_per_second": 5.092,
      "step": 10
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6282,
      "eval_samples_per_second": 73.224,
      "eval_steps_per_second": 4.775,
      "step": 14
    },
    {
      "epoch": 4.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.7697,
      "eval_samples_per_second": 59.765,
      "eval_steps_per_second": 3.898,
      "step": 17
    },
    {
      "epoch": 5.71,
      "learning_rate": 1.2711864406779661e-05,
      "loss": 125111108842291.2,
      "step": 20
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6382,
      "eval_samples_per_second": 72.082,
      "eval_steps_per_second": 4.701,
      "step": 21
    },
    {
      "epoch": 6.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6992,
      "eval_samples_per_second": 65.792,
      "eval_steps_per_second": 4.291,
      "step": 24
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.5911,
      "eval_samples_per_second": 77.815,
      "eval_steps_per_second": 5.075,
      "step": 28
    },
    {
      "epoch": 8.57,
      "learning_rate": 1.1440677966101694e-05,
      "loss": 123174816789299.2,
      "step": 30
    },
    {
      "epoch": 8.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6712,
      "eval_samples_per_second": 68.539,
      "eval_steps_per_second": 4.47,
      "step": 31
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6397,
      "eval_samples_per_second": 71.913,
      "eval_steps_per_second": 4.69,
      "step": 35
    },
    {
      "epoch": 10.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.5671,
      "eval_samples_per_second": 81.109,
      "eval_steps_per_second": 5.29,
      "step": 38
    },
    {
      "epoch": 11.43,
      "learning_rate": 1.016949152542373e-05,
      "loss": 127795517089382.4,
      "step": 40
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6006,
      "eval_samples_per_second": 76.585,
      "eval_steps_per_second": 4.995,
      "step": 42
    },
    {
      "epoch": 12.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6276,
      "eval_samples_per_second": 73.289,
      "eval_steps_per_second": 4.78,
      "step": 45
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.7082,
      "eval_samples_per_second": 64.957,
      "eval_steps_per_second": 4.236,
      "step": 49
    },
    {
      "epoch": 14.29,
      "learning_rate": 8.898305084745763e-06,
      "loss": 123834899575603.2,
      "step": 50
    },
    {
      "epoch": 14.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6297,
      "eval_samples_per_second": 73.056,
      "eval_steps_per_second": 4.765,
      "step": 52
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.5916,
      "eval_samples_per_second": 77.75,
      "eval_steps_per_second": 5.071,
      "step": 56
    },
    {
      "epoch": 16.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6366,
      "eval_samples_per_second": 72.253,
      "eval_steps_per_second": 4.712,
      "step": 59
    },
    {
      "epoch": 17.14,
      "learning_rate": 7.627118644067796e-06,
      "loss": 124803052312985.6,
      "step": 60
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.5896,
      "eval_samples_per_second": 78.013,
      "eval_steps_per_second": 5.088,
      "step": 63
    },
    {
      "epoch": 18.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6182,
      "eval_samples_per_second": 74.415,
      "eval_steps_per_second": 4.853,
      "step": 66
    },
    {
      "epoch": 20.0,
      "learning_rate": 6.3559322033898304e-06,
      "loss": 125771218472140.8,
      "step": 70
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6432,
      "eval_samples_per_second": 71.522,
      "eval_steps_per_second": 4.664,
      "step": 70
    },
    {
      "epoch": 20.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6051,
      "eval_samples_per_second": 76.016,
      "eval_steps_per_second": 4.958,
      "step": 73
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6517,
      "eval_samples_per_second": 70.59,
      "eval_steps_per_second": 4.604,
      "step": 77
    },
    {
      "epoch": 22.86,
      "learning_rate": 5.084745762711865e-06,
      "loss": 126299284701184.0,
      "step": 80
    },
    {
      "epoch": 22.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6347,
      "eval_samples_per_second": 72.481,
      "eval_steps_per_second": 4.727,
      "step": 80
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6672,
      "eval_samples_per_second": 68.95,
      "eval_steps_per_second": 4.497,
      "step": 84
    },
    {
      "epoch": 24.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.5776,
      "eval_samples_per_second": 79.634,
      "eval_steps_per_second": 5.194,
      "step": 87
    },
    {
      "epoch": 25.71,
      "learning_rate": 3.813559322033898e-06,
      "loss": 126299271279411.2,
      "step": 90
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6411,
      "eval_samples_per_second": 71.747,
      "eval_steps_per_second": 4.679,
      "step": 91
    },
    {
      "epoch": 26.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.8482,
      "eval_samples_per_second": 54.233,
      "eval_steps_per_second": 3.537,
      "step": 94
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6537,
      "eval_samples_per_second": 70.374,
      "eval_steps_per_second": 4.59,
      "step": 98
    },
    {
      "epoch": 28.57,
      "learning_rate": 2.5423728813559323e-06,
      "loss": 124362979226419.2,
      "step": 100
    },
    {
      "epoch": 28.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6962,
      "eval_samples_per_second": 66.075,
      "eval_steps_per_second": 4.309,
      "step": 101
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6326,
      "eval_samples_per_second": 72.71,
      "eval_steps_per_second": 4.742,
      "step": 105
    },
    {
      "epoch": 30.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6402,
      "eval_samples_per_second": 71.857,
      "eval_steps_per_second": 4.686,
      "step": 108
    },
    {
      "epoch": 31.43,
      "learning_rate": 1.2711864406779662e-06,
      "loss": 126035251586662.4,
      "step": 110
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6121,
      "eval_samples_per_second": 75.147,
      "eval_steps_per_second": 4.901,
      "step": 112
    },
    {
      "epoch": 32.86,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6086,
      "eval_samples_per_second": 75.578,
      "eval_steps_per_second": 4.929,
      "step": 115
    },
    {
      "epoch": 34.0,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.6832,
      "eval_samples_per_second": 67.335,
      "eval_steps_per_second": 4.391,
      "step": 119
    },
    {
      "epoch": 34.29,
      "learning_rate": 0.0,
      "loss": 125815215043379.2,
      "step": 120
    },
    {
      "epoch": 34.29,
      "eval_accuracy": 0.10869565217391304,
      "eval_loss": 125514790469632.0,
      "eval_runtime": 0.7702,
      "eval_samples_per_second": 59.727,
      "eval_steps_per_second": 3.895,
      "step": 120
    },
    {
      "epoch": 34.29,
      "step": 120,
      "total_flos": 2.0027429927092224e+16,
      "train_loss": 125426485830178.14,
      "train_runtime": 118.5658,
      "train_samples_per_second": 71.859,
      "train_steps_per_second": 1.012
    }
  ],
  "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
}