trainer_state.json

{
  "best_metric": 0.8496,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0850/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": 103.09232330322266,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.181,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6576,
      "eval_loss": 1.5456207990646362,
      "eval_runtime": 14.1847,
      "eval_samples_per_second": 264.37,
      "eval_steps_per_second": 4.159,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 297.19976806640625,
      "learning_rate": 6e-05,
      "loss": 0.9593,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7978666666666666,
      "eval_loss": 0.6729821562767029,
      "eval_runtime": 13.9282,
      "eval_samples_per_second": 269.238,
      "eval_steps_per_second": 4.236,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 134.07325744628906,
      "learning_rate": 4.5e-05,
      "loss": 0.6114,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8261333333333334,
      "eval_loss": 0.5594390630722046,
      "eval_runtime": 13.9195,
      "eval_samples_per_second": 269.405,
      "eval_steps_per_second": 4.239,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 99.31814575195312,
      "learning_rate": 3e-05,
      "loss": 0.4836,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8322666666666667,
      "eval_loss": 0.5323724746704102,
      "eval_runtime": 14.1534,
      "eval_samples_per_second": 264.954,
      "eval_steps_per_second": 4.169,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 145.4357452392578,
      "learning_rate": 1.5e-05,
      "loss": 0.4345,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8496,
      "eval_loss": 0.50067538022995,
      "eval_runtime": 13.5807,
      "eval_samples_per_second": 276.128,
      "eval_steps_per_second": 4.344,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}