trainer_state.json

{
  "best_metric": 0.8821333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0133/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": 264.1073913574219,
      "learning_rate": 9e-05,
      "loss": 3.0707,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6581333333333333,
      "eval_loss": 1.3443596363067627,
      "eval_runtime": 13.4404,
      "eval_samples_per_second": 279.01,
      "eval_steps_per_second": 4.39,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 75.44406127929688,
      "learning_rate": 9e-05,
      "loss": 0.9211,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8074666666666667,
      "eval_loss": 0.6633490324020386,
      "eval_runtime": 12.9603,
      "eval_samples_per_second": 289.346,
      "eval_steps_per_second": 4.552,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 207.4242401123047,
      "learning_rate": 9e-05,
      "loss": 0.5529,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8469333333333333,
      "eval_loss": 0.5177444815635681,
      "eval_runtime": 12.8946,
      "eval_samples_per_second": 290.819,
      "eval_steps_per_second": 4.576,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 75.84886169433594,
      "learning_rate": 9e-05,
      "loss": 0.4062,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8557333333333333,
      "eval_loss": 0.4714207053184509,
      "eval_runtime": 12.8827,
      "eval_samples_per_second": 291.088,
      "eval_steps_per_second": 4.58,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 273.1382141113281,
      "learning_rate": 9e-05,
      "loss": 0.3176,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8704,
      "eval_loss": 0.4399421215057373,
      "eval_runtime": 12.8941,
      "eval_samples_per_second": 290.831,
      "eval_steps_per_second": 4.576,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 115.34156799316406,
      "learning_rate": 9e-05,
      "loss": 0.2379,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8821333333333333,
      "eval_loss": 0.4069563150405884,
      "eval_runtime": 13.0351,
      "eval_samples_per_second": 287.686,
      "eval_steps_per_second": 4.526,
      "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
}