trainer_state.json

{
  "best_metric": 0.9045333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0058/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": 84.99761199951172,
      "learning_rate": 0.0001,
      "loss": 2.7223,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7909333333333334,
      "eval_loss": 0.7857730984687805,
      "eval_runtime": 12.4268,
      "eval_samples_per_second": 301.768,
      "eval_steps_per_second": 4.748,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 110.44107818603516,
      "learning_rate": 0.0001,
      "loss": 0.5922,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.45760098099708557,
      "eval_runtime": 12.538,
      "eval_samples_per_second": 299.09,
      "eval_steps_per_second": 4.706,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 108.54678344726562,
      "learning_rate": 0.0001,
      "loss": 0.3416,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8818666666666667,
      "eval_loss": 0.4022009074687958,
      "eval_runtime": 12.6432,
      "eval_samples_per_second": 296.602,
      "eval_steps_per_second": 4.667,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 76.8812026977539,
      "learning_rate": 0.0001,
      "loss": 0.2172,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8933333333333333,
      "eval_loss": 0.38896188139915466,
      "eval_runtime": 12.6423,
      "eval_samples_per_second": 296.622,
      "eval_steps_per_second": 4.667,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 81.68563079833984,
      "learning_rate": 0.0001,
      "loss": 0.1365,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9045333333333333,
      "eval_loss": 0.3615218698978424,
      "eval_runtime": 12.3842,
      "eval_samples_per_second": 302.804,
      "eval_steps_per_second": 4.764,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2331,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 7,
  "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
}