{
  "best_metric": 0.7608695652173914,
  "best_model_checkpoint": "swiftformer-xs-DMAE\\checkpoint-98",
  "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": 0.5434782608695652,
      "eval_loss": 1.3706265687942505,
      "eval_runtime": 0.7927,
      "eval_samples_per_second": 58.03,
      "eval_steps_per_second": 3.785,
      "step": 3
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6304347826086957,
      "eval_loss": 1.1672464609146118,
      "eval_runtime": 0.7267,
      "eval_samples_per_second": 63.3,
      "eval_steps_per_second": 4.128,
      "step": 7
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.004166666666666667,
      "loss": 1.2937,
      "step": 10
    },
    {
      "epoch": 2.86,
      "eval_accuracy": 0.6086956521739131,
      "eval_loss": 1.2248375415802002,
      "eval_runtime": 0.6077,
      "eval_samples_per_second": 75.7,
      "eval_steps_per_second": 4.937,
      "step": 10
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.34782608695652173,
      "eval_loss": 2.698575973510742,
      "eval_runtime": 0.6071,
      "eval_samples_per_second": 75.764,
      "eval_steps_per_second": 4.941,
      "step": 14
    },
    {
      "epoch": 4.86,
      "eval_accuracy": 0.45652173913043476,
      "eval_loss": 2.600794792175293,
      "eval_runtime": 0.6206,
      "eval_samples_per_second": 74.116,
      "eval_steps_per_second": 4.834,
      "step": 17
    },
    {
      "epoch": 5.71,
      "learning_rate": 0.004629629629629629,
      "loss": 1.2355,
      "step": 20
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.41304347826086957,
      "eval_loss": 1.8899880647659302,
      "eval_runtime": 0.6442,
      "eval_samples_per_second": 71.411,
      "eval_steps_per_second": 4.657,
      "step": 21
    },
    {
      "epoch": 6.86,
      "eval_accuracy": 0.5,
      "eval_loss": 1.595796823501587,
      "eval_runtime": 0.6131,
      "eval_samples_per_second": 75.024,
      "eval_steps_per_second": 4.893,
      "step": 24
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.5652173913043478,
      "eval_loss": 1.3846951723098755,
      "eval_runtime": 0.8307,
      "eval_samples_per_second": 55.373,
      "eval_steps_per_second": 3.611,
      "step": 28
    },
    {
      "epoch": 8.57,
      "learning_rate": 0.004166666666666667,
      "loss": 1.1548,
      "step": 30
    },
    {
      "epoch": 8.86,
      "eval_accuracy": 0.717391304347826,
      "eval_loss": 0.8761585354804993,
      "eval_runtime": 0.6322,
      "eval_samples_per_second": 72.767,
      "eval_steps_per_second": 4.746,
      "step": 31
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.5434782608695652,
      "eval_loss": 1.0870667695999146,
      "eval_runtime": 0.6561,
      "eval_samples_per_second": 70.106,
      "eval_steps_per_second": 4.572,
      "step": 35
    },
    {
      "epoch": 10.86,
      "eval_accuracy": 0.5434782608695652,
      "eval_loss": 0.9779139757156372,
      "eval_runtime": 0.5857,
      "eval_samples_per_second": 78.544,
      "eval_steps_per_second": 5.122,
      "step": 38
    },
    {
      "epoch": 11.43,
      "learning_rate": 0.0037037037037037034,
      "loss": 1.0561,
      "step": 40
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.5434782608695652,
      "eval_loss": 1.2454442977905273,
      "eval_runtime": 0.6291,
      "eval_samples_per_second": 73.116,
      "eval_steps_per_second": 4.768,
      "step": 42
    },
    {
      "epoch": 12.86,
      "eval_accuracy": 0.5652173913043478,
      "eval_loss": 1.227651834487915,
      "eval_runtime": 0.6021,
      "eval_samples_per_second": 76.395,
      "eval_steps_per_second": 4.982,
      "step": 45
    },
    {
      "epoch": 14.0,
      "eval_accuracy": 0.6086956521739131,
      "eval_loss": 0.9526649713516235,
      "eval_runtime": 0.6019,
      "eval_samples_per_second": 76.422,
      "eval_steps_per_second": 4.984,
      "step": 49
    },
    {
      "epoch": 14.29,
      "learning_rate": 0.0032407407407407406,
      "loss": 1.0546,
      "step": 50
    },
    {
      "epoch": 14.86,
      "eval_accuracy": 0.6304347826086957,
      "eval_loss": 0.8797388672828674,
      "eval_runtime": 0.6531,
      "eval_samples_per_second": 70.428,
      "eval_steps_per_second": 4.593,
      "step": 52
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.6304347826086957,
      "eval_loss": 0.9479212760925293,
      "eval_runtime": 0.5991,
      "eval_samples_per_second": 76.776,
      "eval_steps_per_second": 5.007,
      "step": 56
    },
    {
      "epoch": 16.86,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 0.869612991809845,
      "eval_runtime": 0.7437,
      "eval_samples_per_second": 61.854,
      "eval_steps_per_second": 4.034,
      "step": 59
    },
    {
      "epoch": 17.14,
      "learning_rate": 0.002777777777777778,
      "loss": 0.9493,
      "step": 60
    },
    {
      "epoch": 18.0,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 0.9347758293151855,
      "eval_runtime": 0.6096,
      "eval_samples_per_second": 75.454,
      "eval_steps_per_second": 4.921,
      "step": 63
    },
    {
      "epoch": 18.86,
      "eval_accuracy": 0.5434782608695652,
      "eval_loss": 0.9889930486679077,
      "eval_runtime": 0.6462,
      "eval_samples_per_second": 71.19,
      "eval_steps_per_second": 4.643,
      "step": 66
    },
    {
      "epoch": 20.0,
      "learning_rate": 0.0023148148148148147,
      "loss": 0.9354,
      "step": 70
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.5869565217391305,
      "eval_loss": 0.9073047041893005,
      "eval_runtime": 0.6136,
      "eval_samples_per_second": 74.962,
      "eval_steps_per_second": 4.889,
      "step": 70
    },
    {
      "epoch": 20.86,
      "eval_accuracy": 0.6304347826086957,
      "eval_loss": 0.8763116598129272,
      "eval_runtime": 0.6322,
      "eval_samples_per_second": 72.766,
      "eval_steps_per_second": 4.746,
      "step": 73
    },
    {
      "epoch": 22.0,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 0.9592300653457642,
      "eval_runtime": 0.6382,
      "eval_samples_per_second": 72.082,
      "eval_steps_per_second": 4.701,
      "step": 77
    },
    {
      "epoch": 22.86,
      "learning_rate": 0.0018518518518518517,
      "loss": 0.8791,
      "step": 80
    },
    {
      "epoch": 22.86,
      "eval_accuracy": 0.6521739130434783,
      "eval_loss": 0.8940117955207825,
      "eval_runtime": 0.7087,
      "eval_samples_per_second": 64.911,
      "eval_steps_per_second": 4.233,
      "step": 80
    },
    {
      "epoch": 24.0,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.8165251016616821,
      "eval_runtime": 0.6012,
      "eval_samples_per_second": 76.52,
      "eval_steps_per_second": 4.99,
      "step": 84
    },
    {
      "epoch": 24.86,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.8249245285987854,
      "eval_runtime": 0.6311,
      "eval_samples_per_second": 72.884,
      "eval_steps_per_second": 4.753,
      "step": 87
    },
    {
      "epoch": 25.71,
      "learning_rate": 0.001388888888888889,
      "loss": 0.8017,
      "step": 90
    },
    {
      "epoch": 26.0,
      "eval_accuracy": 0.6739130434782609,
      "eval_loss": 0.8946475386619568,
      "eval_runtime": 0.7282,
      "eval_samples_per_second": 63.173,
      "eval_steps_per_second": 4.12,
      "step": 91
    },
    {
      "epoch": 26.86,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.8210282325744629,
      "eval_runtime": 0.6431,
      "eval_samples_per_second": 71.524,
      "eval_steps_per_second": 4.665,
      "step": 94
    },
    {
      "epoch": 28.0,
      "eval_accuracy": 0.7608695652173914,
      "eval_loss": 0.7653754949569702,
      "eval_runtime": 0.9337,
      "eval_samples_per_second": 49.265,
      "eval_steps_per_second": 3.213,
      "step": 98
    },
    {
      "epoch": 28.57,
      "learning_rate": 0.0009259259259259259,
      "loss": 0.8532,
      "step": 100
    },
    {
      "epoch": 28.86,
      "eval_accuracy": 0.7391304347826086,
      "eval_loss": 0.7491888999938965,
      "eval_runtime": 0.6161,
      "eval_samples_per_second": 74.659,
      "eval_steps_per_second": 4.869,
      "step": 101
    },
    {
      "epoch": 30.0,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.7725396156311035,
      "eval_runtime": 0.6542,
      "eval_samples_per_second": 70.319,
      "eval_steps_per_second": 4.586,
      "step": 105
    },
    {
      "epoch": 30.86,
      "eval_accuracy": 0.717391304347826,
      "eval_loss": 0.7931932210922241,
      "eval_runtime": 0.6467,
      "eval_samples_per_second": 71.135,
      "eval_steps_per_second": 4.639,
      "step": 108
    },
    {
      "epoch": 31.43,
      "learning_rate": 0.0004629629629629629,
      "loss": 0.8205,
      "step": 110
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 0.7391304347826086,
      "eval_loss": 0.8129280209541321,
      "eval_runtime": 0.6256,
      "eval_samples_per_second": 73.524,
      "eval_steps_per_second": 4.795,
      "step": 112
    },
    {
      "epoch": 32.86,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.8089176416397095,
      "eval_runtime": 0.6011,
      "eval_samples_per_second": 76.522,
      "eval_steps_per_second": 4.991,
      "step": 115
    },
    {
      "epoch": 34.0,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.8150961399078369,
      "eval_runtime": 0.8342,
      "eval_samples_per_second": 55.142,
      "eval_steps_per_second": 3.596,
      "step": 119
    },
    {
      "epoch": 34.29,
      "learning_rate": 0.0,
      "loss": 0.8112,
      "step": 120
    },
    {
      "epoch": 34.29,
      "eval_accuracy": 0.6956521739130435,
      "eval_loss": 0.8074415326118469,
      "eval_runtime": 0.6487,
      "eval_samples_per_second": 70.916,
      "eval_steps_per_second": 4.625,
      "step": 120
    },
    {
      "epoch": 34.29,
      "step": 120,
      "total_flos": 2.0027429927092224e+16,
      "train_loss": 0.9870913426081339,
      "train_runtime": 135.9591,
      "train_samples_per_second": 62.666,
      "train_steps_per_second": 0.883
    }
  ],
  "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
}