trainer_state.json

{
  "best_metric": 0.7948717948717948,
  "best_model_checkpoint": "swinv2-tiny-patch4-window8-256-prueba2/checkpoint-11",
  "epoch": 2.7272727272727275,
  "eval_steps": 500,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.9090909090909091,
      "eval_accuracy": 0.7692307692307693,
      "eval_loss": 0.58552485704422,
      "eval_runtime": 0.5582,
      "eval_samples_per_second": 139.732,
      "eval_steps_per_second": 5.374,
      "step": 5
    },
    {
      "epoch": 1.8181818181818183,
      "grad_norm": 2.9700989723205566,
      "learning_rate": 1.923076923076923e-05,
      "loss": 0.6548,
      "step": 10
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7948717948717948,
      "eval_loss": 0.4983014762401581,
      "eval_runtime": 0.561,
      "eval_samples_per_second": 139.032,
      "eval_steps_per_second": 5.347,
      "step": 11
    },
    {
      "epoch": 2.7272727272727275,
      "eval_accuracy": 0.7692307692307693,
      "eval_loss": 0.49411284923553467,
      "eval_runtime": 0.5477,
      "eval_samples_per_second": 142.403,
      "eval_steps_per_second": 5.477,
      "step": 15
    },
    {
      "epoch": 2.7272727272727275,
      "step": 15,
      "total_flos": 4.767600833578598e+16,
      "train_loss": 0.6202580610911052,
      "train_runtime": 32.385,
      "train_samples_per_second": 64.937,
      "train_steps_per_second": 0.463
    }
  ],
  "logging_steps": 10,
  "max_steps": 15,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 4.767600833578598e+16,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}