trainer_state.json

{
  "best_metric": 0.6422849181469871,
  "best_model_checkpoint": "beit-base-patch16-224-pt22k-ft22k-finetuned-FER2013-9e-05/checkpoint-202",
  "epoch": 1.0,
  "global_step": 202,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 1.9259,
      "step": 10
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.6569,
      "step": 20
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.552486187845305e-05,
      "loss": 1.4853,
      "step": 30
    },
    {
      "epoch": 0.2,
      "learning_rate": 8.055248618784531e-05,
      "loss": 1.512,
      "step": 40
    },
    {
      "epoch": 0.25,
      "learning_rate": 7.558011049723757e-05,
      "loss": 1.395,
      "step": 50
    },
    {
      "epoch": 0.3,
      "learning_rate": 7.060773480662983e-05,
      "loss": 1.3225,
      "step": 60
    },
    {
      "epoch": 0.35,
      "learning_rate": 6.563535911602211e-05,
      "loss": 1.3529,
      "step": 70
    },
    {
      "epoch": 0.4,
      "learning_rate": 6.0662983425414375e-05,
      "loss": 1.3234,
      "step": 80
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.569060773480663e-05,
      "loss": 1.2544,
      "step": 90
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.07182320441989e-05,
      "loss": 1.2481,
      "step": 100
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.5745856353591164e-05,
      "loss": 1.2172,
      "step": 110
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.077348066298343e-05,
      "loss": 1.249,
      "step": 120
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.580110497237569e-05,
      "loss": 1.2136,
      "step": 130
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.082872928176796e-05,
      "loss": 1.1581,
      "step": 140
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.585635359116022e-05,
      "loss": 1.1803,
      "step": 150
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.0883977900552486e-05,
      "loss": 1.2273,
      "step": 160
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.591160220994475e-05,
      "loss": 1.1976,
      "step": 170
    },
    {
      "epoch": 0.89,
      "learning_rate": 1.0939226519337016e-05,
      "loss": 1.1569,
      "step": 180
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.966850828729282e-06,
      "loss": 1.178,
      "step": 190
    },
    {
      "epoch": 0.99,
      "learning_rate": 9.944751381215469e-07,
      "loss": 1.1404,
      "step": 200
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6422849181469871,
      "eval_loss": 0.9593217372894287,
      "eval_runtime": 24.866,
      "eval_samples_per_second": 115.459,
      "eval_steps_per_second": 3.619,
      "step": 202
    },
    {
      "epoch": 1.0,
      "step": 202,
      "total_flos": 2.0014719749914337e+18,
      "train_loss": 1.316133418885788,
      "train_runtime": 615.4563,
      "train_samples_per_second": 41.982,
      "train_steps_per_second": 0.328
    }
  ],
  "max_steps": 202,
  "num_train_epochs": 1,
  "total_flos": 2.0014719749914337e+18,
  "trial_name": null,
  "trial_params": null
}