trainer_state.json

{
  "best_metric": 0.84,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0189/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": 239.90182495117188,
      "learning_rate": 6.531088913245535e-05,
      "loss": 3.438,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5437333333333333,
      "eval_loss": 2.24526309967041,
      "eval_runtime": 7.663,
      "eval_samples_per_second": 489.363,
      "eval_steps_per_second": 7.699,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 107.13384246826172,
      "learning_rate": 5.2499999999999995e-05,
      "loss": 1.2721,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7733333333333333,
      "eval_loss": 0.7837801575660706,
      "eval_runtime": 7.4498,
      "eval_samples_per_second": 503.369,
      "eval_steps_per_second": 7.92,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 70.94762420654297,
      "learning_rate": 3.5e-05,
      "loss": 0.7076,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.82,
      "eval_loss": 0.6434798240661621,
      "eval_runtime": 7.4766,
      "eval_samples_per_second": 501.564,
      "eval_steps_per_second": 7.891,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 449.5133972167969,
      "learning_rate": 1.7500000000000005e-05,
      "loss": 0.5593,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8269333333333333,
      "eval_loss": 0.5563554763793945,
      "eval_runtime": 7.5083,
      "eval_samples_per_second": 499.447,
      "eval_steps_per_second": 7.858,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 142.5426025390625,
      "learning_rate": 4.689110867544645e-06,
      "loss": 0.4863,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8381333333333333,
      "eval_loss": 0.5499968528747559,
      "eval_runtime": 7.4426,
      "eval_samples_per_second": 503.858,
      "eval_steps_per_second": 7.927,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 216.91993713378906,
      "learning_rate": 0.0,
      "loss": 0.4727,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.84,
      "eval_loss": 0.5412729978561401,
      "eval_runtime": 7.5022,
      "eval_samples_per_second": 499.853,
      "eval_steps_per_second": 7.864,
      "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
}