trainer_state.json

{
  "best_metric": 0.9085333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0750/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": 31.257272720336914,
      "learning_rate": 0.0004166666666666667,
      "loss": 1.2574,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8437333333333333,
      "eval_loss": 0.5411213040351868,
      "eval_runtime": 7.5214,
      "eval_samples_per_second": 498.576,
      "eval_steps_per_second": 7.844,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 35.85286331176758,
      "learning_rate": 0.0003333333333333333,
      "loss": 0.3667,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8864,
      "eval_loss": 0.38830623030662537,
      "eval_runtime": 6.987,
      "eval_samples_per_second": 536.709,
      "eval_steps_per_second": 8.444,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 24.75374412536621,
      "learning_rate": 0.00025,
      "loss": 0.1772,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8906666666666667,
      "eval_loss": 0.40797096490859985,
      "eval_runtime": 6.9528,
      "eval_samples_per_second": 539.351,
      "eval_steps_per_second": 8.486,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 20.895597457885742,
      "learning_rate": 0.00016666666666666666,
      "loss": 0.0802,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8992,
      "eval_loss": 0.39833417534828186,
      "eval_runtime": 6.987,
      "eval_samples_per_second": 536.71,
      "eval_steps_per_second": 8.444,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 36.12598419189453,
      "learning_rate": 8.333333333333333e-05,
      "loss": 0.0426,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9085333333333333,
      "eval_loss": 0.37745532393455505,
      "eval_runtime": 7.0185,
      "eval_samples_per_second": 534.3,
      "eval_steps_per_second": 8.406,
      "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
}