trainer_state.json

{
  "best_metric": 0.8690666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0944/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": 56.13623046875,
      "learning_rate": 0.0005,
      "loss": 1.4702,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7994666666666667,
      "eval_loss": 0.6734762787818909,
      "eval_runtime": 8.8999,
      "eval_samples_per_second": 421.354,
      "eval_steps_per_second": 6.629,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 35.6712646484375,
      "learning_rate": 0.0005,
      "loss": 0.5083,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8448,
      "eval_loss": 0.5208959579467773,
      "eval_runtime": 8.2687,
      "eval_samples_per_second": 453.52,
      "eval_steps_per_second": 7.135,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 31.60681915283203,
      "learning_rate": 0.0005,
      "loss": 0.3365,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8482666666666666,
      "eval_loss": 0.5370188355445862,
      "eval_runtime": 8.2975,
      "eval_samples_per_second": 451.944,
      "eval_steps_per_second": 7.111,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 18.453964233398438,
      "learning_rate": 0.0005,
      "loss": 0.2278,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8546666666666667,
      "eval_loss": 0.5242474675178528,
      "eval_runtime": 9.2121,
      "eval_samples_per_second": 407.074,
      "eval_steps_per_second": 6.405,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 21.497133255004883,
      "learning_rate": 0.0005,
      "loss": 0.1727,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8690666666666667,
      "eval_loss": 0.5133369565010071,
      "eval_runtime": 8.176,
      "eval_samples_per_second": 458.661,
      "eval_steps_per_second": 7.216,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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
}