trainer_state.json

{
  "best_metric": 0.8864,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0575/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": 1318.55029296875,
      "learning_rate": 7e-05,
      "loss": 3.287,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6450666666666667,
      "eval_loss": 1.848702073097229,
      "eval_runtime": 13.3937,
      "eval_samples_per_second": 279.982,
      "eval_steps_per_second": 4.405,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 152.0831298828125,
      "learning_rate": 7e-05,
      "loss": 1.0186,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8210666666666666,
      "eval_loss": 0.6583036184310913,
      "eval_runtime": 13.3958,
      "eval_samples_per_second": 279.939,
      "eval_steps_per_second": 4.404,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 72.17105102539062,
      "learning_rate": 7e-05,
      "loss": 0.5648,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8453333333333334,
      "eval_loss": 0.5181624889373779,
      "eval_runtime": 13.3994,
      "eval_samples_per_second": 279.863,
      "eval_steps_per_second": 4.403,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 108.21542358398438,
      "learning_rate": 7e-05,
      "loss": 0.4321,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8656,
      "eval_loss": 0.4437653720378876,
      "eval_runtime": 13.5081,
      "eval_samples_per_second": 277.611,
      "eval_steps_per_second": 4.368,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 65.9017562866211,
      "learning_rate": 7e-05,
      "loss": 0.3346,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8834666666666666,
      "eval_loss": 0.4000467360019684,
      "eval_runtime": 13.2576,
      "eval_samples_per_second": 282.857,
      "eval_steps_per_second": 4.45,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 127.94257354736328,
      "learning_rate": 7e-05,
      "loss": 0.2753,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8864,
      "eval_loss": 0.39259016513824463,
      "eval_runtime": 13.4294,
      "eval_samples_per_second": 279.238,
      "eval_steps_per_second": 4.393,
      "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": 4.9058575437312e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}