trainer_state.json

{
  "best_metric": 0.8594666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0339/checkpoints/checkpoint-1998",
  "epoch": 6.0,
  "eval_steps": 500,
  "global_step": 1998,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 77.30116271972656,
      "learning_rate": 4.166666666666667e-05,
      "loss": 3.6245,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5925333333333334,
      "eval_loss": 2.944798469543457,
      "eval_runtime": 4.9377,
      "eval_samples_per_second": 759.466,
      "eval_steps_per_second": 11.949,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 285.3720397949219,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.8052,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7674666666666666,
      "eval_loss": 1.0851962566375732,
      "eval_runtime": 4.8917,
      "eval_samples_per_second": 766.604,
      "eval_steps_per_second": 12.061,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 168.07073974609375,
      "learning_rate": 2.5e-05,
      "loss": 0.8026,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8317333333333333,
      "eval_loss": 0.6546621322631836,
      "eval_runtime": 4.9193,
      "eval_samples_per_second": 762.297,
      "eval_steps_per_second": 11.993,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 239.86181640625,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5608,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8408,
      "eval_loss": 0.5560846328735352,
      "eval_runtime": 4.8475,
      "eval_samples_per_second": 773.601,
      "eval_steps_per_second": 12.171,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 159.40414428710938,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.4545,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8565333333333334,
      "eval_loss": 0.5039497017860413,
      "eval_runtime": 4.8393,
      "eval_samples_per_second": 774.901,
      "eval_steps_per_second": 12.192,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 180.72093200683594,
      "learning_rate": 0.0,
      "loss": 0.4109,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8594666666666667,
      "eval_loss": 0.4889149069786072,
      "eval_runtime": 4.8275,
      "eval_samples_per_second": 776.794,
      "eval_steps_per_second": 12.222,
      "step": 1998
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.9058575437312e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}