trainer_state.json

{
  "best_metric": 0.12673677504062653,
  "best_model_checkpoint": "vit-large-patch16-224-new-dungeon-geo-morphs-020/checkpoint-30",
  "epoch": 23.333333333333332,
  "eval_steps": 10,
  "global_step": 35,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.666666666666667,
      "grad_norm": 17.276561737060547,
      "learning_rate": 1.6774193548387098e-05,
      "loss": 1.1059,
      "step": 10
    },
    {
      "epoch": 6.666666666666667,
      "eval_accuracy": 0.8867924528301887,
      "eval_loss": 0.5386238098144531,
      "eval_runtime": 0.9261,
      "eval_samples_per_second": 57.23,
      "eval_steps_per_second": 4.319,
      "step": 10
    },
    {
      "epoch": 13.333333333333334,
      "grad_norm": 8.874366760253906,
      "learning_rate": 1.0322580645161291e-05,
      "loss": 0.3385,
      "step": 20
    },
    {
      "epoch": 13.333333333333334,
      "eval_accuracy": 0.9433962264150944,
      "eval_loss": 0.18484610319137573,
      "eval_runtime": 0.9154,
      "eval_samples_per_second": 57.9,
      "eval_steps_per_second": 4.37,
      "step": 20
    },
    {
      "epoch": 20.0,
      "grad_norm": 5.337092876434326,
      "learning_rate": 3.870967741935484e-06,
      "loss": 0.1115,
      "step": 30
    },
    {
      "epoch": 20.0,
      "eval_accuracy": 0.9811320754716981,
      "eval_loss": 0.12673677504062653,
      "eval_runtime": 0.8326,
      "eval_samples_per_second": 63.653,
      "eval_steps_per_second": 4.804,
      "step": 30
    },
    {
      "epoch": 23.333333333333332,
      "step": 35,
      "total_flos": 5.3801036558902886e+17,
      "train_loss": 0.4527590223721096,
      "train_runtime": 348.6632,
      "train_samples_per_second": 8.432,
      "train_steps_per_second": 0.1
    }
  ],
  "logging_steps": 10,
  "max_steps": 35,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 35,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.3801036558902886e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}