trainer_state.json

{
  "best_metric": 0.8389333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0163/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": 111.56989288330078,
      "learning_rate": 6.531088913245535e-05,
      "loss": 3.2939,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5869333333333333,
      "eval_loss": 1.8618040084838867,
      "eval_runtime": 7.8435,
      "eval_samples_per_second": 478.102,
      "eval_steps_per_second": 7.522,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 166.7516326904297,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 1.1278,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7632,
      "eval_loss": 0.7907904982566833,
      "eval_runtime": 8.0485,
      "eval_samples_per_second": 465.923,
      "eval_steps_per_second": 7.331,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 66.3589096069336,
      "learning_rate": 3.5e-05,
      "loss": 0.7016,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8088,
      "eval_loss": 0.6577746272087097,
      "eval_runtime": 7.9017,
      "eval_samples_per_second": 474.581,
      "eval_steps_per_second": 7.467,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 79.81852722167969,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.5602,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8272,
      "eval_loss": 0.5727164149284363,
      "eval_runtime": 7.8772,
      "eval_samples_per_second": 476.056,
      "eval_steps_per_second": 7.49,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 112.7228012084961,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.495,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8389333333333333,
      "eval_loss": 0.5409944653511047,
      "eval_runtime": 7.8324,
      "eval_samples_per_second": 478.783,
      "eval_steps_per_second": 7.533,
      "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
}