trainer_state.json

{
  "best_metric": 0.9117333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0341/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": 37.78038024902344,
      "learning_rate": 0.00046650635094610973,
      "loss": 1.2368,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8517333333333333,
      "eval_loss": 0.52646803855896,
      "eval_runtime": 8.5539,
      "eval_samples_per_second": 438.397,
      "eval_steps_per_second": 6.897,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 31.962112426757812,
      "learning_rate": 0.000375,
      "loss": 0.3975,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8744,
      "eval_loss": 0.40813469886779785,
      "eval_runtime": 8.1552,
      "eval_samples_per_second": 459.83,
      "eval_steps_per_second": 7.235,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 27.46190643310547,
      "learning_rate": 0.00025,
      "loss": 0.2123,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8890666666666667,
      "eval_loss": 0.379594087600708,
      "eval_runtime": 8.2023,
      "eval_samples_per_second": 457.191,
      "eval_steps_per_second": 7.193,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 16.03727912902832,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.1012,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.908,
      "eval_loss": 0.3396272659301758,
      "eval_runtime": 8.3537,
      "eval_samples_per_second": 448.901,
      "eval_steps_per_second": 7.063,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 14.993875503540039,
      "learning_rate": 3.3493649053890325e-05,
      "loss": 0.0506,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9117333333333333,
      "eval_loss": 0.3650542199611664,
      "eval_runtime": 8.1512,
      "eval_samples_per_second": 460.055,
      "eval_steps_per_second": 7.238,
      "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
}