trainer_state.json

{
  "best_metric": 0.8850666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0077/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": 46.58636474609375,
      "learning_rate": 0.0003,
      "loss": 1.6052,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8234666666666667,
      "eval_loss": 0.5636258721351624,
      "eval_runtime": 7.4418,
      "eval_samples_per_second": 503.912,
      "eval_steps_per_second": 7.928,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 35.149635314941406,
      "learning_rate": 0.0003,
      "loss": 0.453,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8688,
      "eval_loss": 0.4433870315551758,
      "eval_runtime": 7.3705,
      "eval_samples_per_second": 508.784,
      "eval_steps_per_second": 8.005,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 41.15940475463867,
      "learning_rate": 0.0003,
      "loss": 0.3062,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8725333333333334,
      "eval_loss": 0.4235723912715912,
      "eval_runtime": 7.3322,
      "eval_samples_per_second": 511.441,
      "eval_steps_per_second": 8.047,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 53.99800109863281,
      "learning_rate": 0.0003,
      "loss": 0.2053,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8786666666666667,
      "eval_loss": 0.43450361490249634,
      "eval_runtime": 7.3048,
      "eval_samples_per_second": 513.359,
      "eval_steps_per_second": 8.077,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.225058555603027,
      "learning_rate": 0.0003,
      "loss": 0.1417,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8850666666666667,
      "eval_loss": 0.4219737946987152,
      "eval_runtime": 7.3212,
      "eval_samples_per_second": 512.209,
      "eval_steps_per_second": 8.059,
      "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
}