trainer_state.json

{
  "best_metric": 0.8914666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0258/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": 37.13827896118164,
      "learning_rate": 0.0003,
      "loss": 1.5963,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8370666666666666,
      "eval_loss": 0.5480788350105286,
      "eval_runtime": 15.5036,
      "eval_samples_per_second": 241.879,
      "eval_steps_per_second": 3.806,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 39.52515411376953,
      "learning_rate": 0.0003,
      "loss": 0.4506,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8690666666666667,
      "eval_loss": 0.43741729855537415,
      "eval_runtime": 15.6272,
      "eval_samples_per_second": 239.967,
      "eval_steps_per_second": 3.775,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 28.873302459716797,
      "learning_rate": 0.0003,
      "loss": 0.3076,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8714666666666666,
      "eval_loss": 0.4213346242904663,
      "eval_runtime": 15.5646,
      "eval_samples_per_second": 240.931,
      "eval_steps_per_second": 3.791,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 38.95281219482422,
      "learning_rate": 0.0003,
      "loss": 0.2251,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8901333333333333,
      "eval_loss": 0.41385626792907715,
      "eval_runtime": 15.5131,
      "eval_samples_per_second": 241.731,
      "eval_steps_per_second": 3.803,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 27.28551483154297,
      "learning_rate": 0.0003,
      "loss": 0.1615,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8914666666666666,
      "eval_loss": 0.3862021863460541,
      "eval_runtime": 15.4634,
      "eval_samples_per_second": 242.508,
      "eval_steps_per_second": 3.815,
      "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
}