trainer_state.json

{
  "best_metric": 0.47560975609756095,
  "best_model_checkpoint": "MRR_image_classification_dit_29_jan_small75-finetuned-eurosat/checkpoint-30",
  "epoch": 2.926829268292683,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.98,
      "learning_rate": 3.7037037037037037e-05,
      "loss": 1.8795,
      "step": 10
    },
    {
      "epoch": 0.98,
      "eval_accuracy": 0.3048780487804878,
      "eval_loss": 1.643699288368225,
      "eval_runtime": 4.9921,
      "eval_samples_per_second": 16.426,
      "eval_steps_per_second": 2.203,
      "step": 10
    },
    {
      "epoch": 1.95,
      "learning_rate": 1.8518518518518518e-05,
      "loss": 1.6681,
      "step": 20
    },
    {
      "epoch": 1.95,
      "eval_accuracy": 0.4146341463414634,
      "eval_loss": 1.6445565223693848,
      "eval_runtime": 3.6492,
      "eval_samples_per_second": 22.471,
      "eval_steps_per_second": 3.014,
      "step": 20
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.0,
      "loss": 1.5603,
      "step": 30
    },
    {
      "epoch": 2.93,
      "eval_accuracy": 0.47560975609756095,
      "eval_loss": 1.578503131866455,
      "eval_runtime": 3.4871,
      "eval_samples_per_second": 23.515,
      "eval_steps_per_second": 3.154,
      "step": 30
    },
    {
      "epoch": 2.93,
      "step": 30,
      "total_flos": 2.613596809351127e+17,
      "train_loss": 1.7026190439860025,
      "train_runtime": 204.8067,
      "train_samples_per_second": 4.761,
      "train_steps_per_second": 0.146
    }
  ],
  "logging_steps": 10,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2.613596809351127e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}