trainer_state.json

{
  "best_metric": 0.8933333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0476/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": 57.249813079833984,
      "learning_rate": 9e-05,
      "loss": 2.9066,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.72,
      "eval_loss": 1.0608433485031128,
      "eval_runtime": 8.7542,
      "eval_samples_per_second": 428.364,
      "eval_steps_per_second": 6.74,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 133.57400512695312,
      "learning_rate": 9e-05,
      "loss": 0.7616,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8410666666666666,
      "eval_loss": 0.5496656894683838,
      "eval_runtime": 8.2579,
      "eval_samples_per_second": 454.11,
      "eval_steps_per_second": 7.145,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 106.07511901855469,
      "learning_rate": 9e-05,
      "loss": 0.4586,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8730666666666667,
      "eval_loss": 0.42769742012023926,
      "eval_runtime": 8.845,
      "eval_samples_per_second": 423.968,
      "eval_steps_per_second": 6.67,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 87.30406188964844,
      "learning_rate": 9e-05,
      "loss": 0.3229,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.884,
      "eval_loss": 0.38104259967803955,
      "eval_runtime": 8.7397,
      "eval_samples_per_second": 429.075,
      "eval_steps_per_second": 6.751,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 151.7662353515625,
      "learning_rate": 9e-05,
      "loss": 0.2442,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8933333333333333,
      "eval_loss": 0.37900856137275696,
      "eval_runtime": 8.6874,
      "eval_samples_per_second": 431.661,
      "eval_steps_per_second": 6.791,
      "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
}