trainer_state.json

{
  "best_metric": 0.9058666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0308/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 154.8057098388672,
      "learning_rate": 9e-05,
      "loss": 2.6851,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7834666666666666,
      "eval_loss": 0.8318279385566711,
      "eval_runtime": 7.3354,
      "eval_samples_per_second": 511.221,
      "eval_steps_per_second": 8.043,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 140.7826690673828,
      "learning_rate": 9e-05,
      "loss": 0.6025,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8770666666666667,
      "eval_loss": 0.42964237928390503,
      "eval_runtime": 7.4358,
      "eval_samples_per_second": 504.316,
      "eval_steps_per_second": 7.935,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 124.61080169677734,
      "learning_rate": 9e-05,
      "loss": 0.3647,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8909333333333334,
      "eval_loss": 0.3645421862602234,
      "eval_runtime": 7.7105,
      "eval_samples_per_second": 486.349,
      "eval_steps_per_second": 7.652,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 67.32157135009766,
      "learning_rate": 9e-05,
      "loss": 0.2666,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8992,
      "eval_loss": 0.3198939561843872,
      "eval_runtime": 7.6071,
      "eval_samples_per_second": 492.96,
      "eval_steps_per_second": 7.756,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 73.16848754882812,
      "learning_rate": 9e-05,
      "loss": 0.1902,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9058666666666667,
      "eval_loss": 0.3064344823360443,
      "eval_runtime": 7.4673,
      "eval_samples_per_second": 502.19,
      "eval_steps_per_second": 7.901,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}