trainer_state.json

{
  "best_metric": 0.852,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0664/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": 157.14605712890625,
      "learning_rate": 4.665063509461097e-05,
      "loss": 3.6562,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.5658666666666666,
      "eval_loss": 2.970956563949585,
      "eval_runtime": 7.1847,
      "eval_samples_per_second": 521.943,
      "eval_steps_per_second": 8.212,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 178.8596954345703,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 1.6347,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7794666666666666,
      "eval_loss": 0.904301643371582,
      "eval_runtime": 7.1074,
      "eval_samples_per_second": 527.615,
      "eval_steps_per_second": 8.301,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 174.5675048828125,
      "learning_rate": 2.5e-05,
      "loss": 0.786,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8173333333333334,
      "eval_loss": 0.6642544269561768,
      "eval_runtime": 7.1033,
      "eval_samples_per_second": 527.923,
      "eval_steps_per_second": 8.306,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 225.46075439453125,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 0.6046,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8288,
      "eval_loss": 0.5818068981170654,
      "eval_runtime": 7.1047,
      "eval_samples_per_second": 527.818,
      "eval_steps_per_second": 8.304,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 112.08016204833984,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 0.527,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.852,
      "eval_loss": 0.5532756447792053,
      "eval_runtime": 7.101,
      "eval_samples_per_second": 528.093,
      "eval_steps_per_second": 8.309,
      "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
}