trainer_state.json

{
  "best_metric": 0.8773333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0662/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": 27.824064254760742,
      "learning_rate": 0.0005,
      "loss": 1.239,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8352,
      "eval_loss": 0.5201711654663086,
      "eval_runtime": 17.3222,
      "eval_samples_per_second": 216.485,
      "eval_steps_per_second": 3.406,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 48.94361114501953,
      "learning_rate": 0.0005,
      "loss": 0.4111,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8586666666666667,
      "eval_loss": 0.46603891253471375,
      "eval_runtime": 17.4832,
      "eval_samples_per_second": 214.492,
      "eval_steps_per_second": 3.375,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 26.453020095825195,
      "learning_rate": 0.0005,
      "loss": 0.2478,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8562666666666666,
      "eval_loss": 0.49588099122047424,
      "eval_runtime": 17.4397,
      "eval_samples_per_second": 215.027,
      "eval_steps_per_second": 3.383,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 31.941299438476562,
      "learning_rate": 0.0005,
      "loss": 0.1773,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8664,
      "eval_loss": 0.5125500559806824,
      "eval_runtime": 17.3734,
      "eval_samples_per_second": 215.848,
      "eval_steps_per_second": 3.396,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 32.0032958984375,
      "learning_rate": 0.0005,
      "loss": 0.1247,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8773333333333333,
      "eval_loss": 0.4973210394382477,
      "eval_runtime": 17.5322,
      "eval_samples_per_second": 213.892,
      "eval_steps_per_second": 3.365,
      "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
}