trainer_state.json

{
  "best_metric": 0.8477333333333333,
  "best_model_checkpoint": "./vit_finetuned_models_dataset/CIFAR100/50_from_100/facebook_vit-mae-base/model_idx_0722/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": Infinity,
      "learning_rate": 0.0002800215775878589,
      "loss": 2.4949,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5845333333333333,
      "eval_loss": 1.4193830490112305,
      "eval_runtime": 6.5399,
      "eval_samples_per_second": 573.405,
      "eval_steps_per_second": 9.022,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": Infinity,
      "learning_rate": 0.00022540814184580826,
      "loss": 0.9443,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7298666666666667,
      "eval_loss": 0.8436718583106995,
      "eval_runtime": 13.3344,
      "eval_samples_per_second": 281.228,
      "eval_steps_per_second": 4.425,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.3959880769252777,
      "learning_rate": 0.00015047170983116046,
      "loss": 0.4265,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8021333333333334,
      "eval_loss": 0.6165886521339417,
      "eval_runtime": 6.5054,
      "eval_samples_per_second": 576.446,
      "eval_steps_per_second": 9.069,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 5.760054111480713,
      "learning_rate": 7.540888354819138e-05,
      "loss": 0.1427,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8258666666666666,
      "eval_loss": 0.5902865529060364,
      "eval_runtime": 6.5702,
      "eval_samples_per_second": 570.762,
      "eval_steps_per_second": 8.98,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.38269755244255066,
      "learning_rate": 2.0332686681020267e-05,
      "loss": 0.027,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8432,
      "eval_loss": 0.5467883348464966,
      "eval_runtime": 6.7682,
      "eval_samples_per_second": 554.065,
      "eval_steps_per_second": 8.717,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.02732141502201557,
      "learning_rate": 7.417023831113311e-10,
      "loss": 0.0066,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8477333333333333,
      "eval_loss": 0.5370863676071167,
      "eval_runtime": 6.5273,
      "eval_samples_per_second": 574.509,
      "eval_steps_per_second": 9.039,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 9.88447923735552e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}