trainer_state.json

{
  "best_metric": 0.9042666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0272/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": 52.275943756103516,
      "learning_rate": 0.0002851453301853628,
      "loss": 1.5115,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8482666666666666,
      "eval_loss": 0.5020545721054077,
      "eval_runtime": 14.5308,
      "eval_samples_per_second": 258.072,
      "eval_steps_per_second": 4.06,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 26.45831298828125,
      "learning_rate": 0.00024352347027881003,
      "loss": 0.4027,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8861333333333333,
      "eval_loss": 0.3673299551010132,
      "eval_runtime": 14.5741,
      "eval_samples_per_second": 257.306,
      "eval_steps_per_second": 4.048,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 41.212371826171875,
      "learning_rate": 0.00018337814009344714,
      "loss": 0.2164,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.892,
      "eval_loss": 0.3791162073612213,
      "eval_runtime": 14.455,
      "eval_samples_per_second": 259.426,
      "eval_steps_per_second": 4.082,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 40.18310546875,
      "learning_rate": 0.00011662185990655284,
      "loss": 0.1064,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9008,
      "eval_loss": 0.38382044434547424,
      "eval_runtime": 14.4506,
      "eval_samples_per_second": 259.504,
      "eval_steps_per_second": 4.083,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 83.92516326904297,
      "learning_rate": 5.6476529721189974e-05,
      "loss": 0.0578,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9042666666666667,
      "eval_loss": 0.3794889450073242,
      "eval_runtime": 14.3969,
      "eval_samples_per_second": 260.473,
      "eval_steps_per_second": 4.098,
      "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
}