trainer_state.json

{
  "best_metric": 0.912,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0587/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": 34.883995056152344,
      "learning_rate": 0.0004166666666666667,
      "loss": 1.2418,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8477333333333333,
      "eval_loss": 0.5148667097091675,
      "eval_runtime": 7.2596,
      "eval_samples_per_second": 516.559,
      "eval_steps_per_second": 8.127,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 25.59684944152832,
      "learning_rate": 0.0003333333333333333,
      "loss": 0.3537,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8877333333333334,
      "eval_loss": 0.39156919717788696,
      "eval_runtime": 7.1546,
      "eval_samples_per_second": 524.135,
      "eval_steps_per_second": 8.246,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 62.28602981567383,
      "learning_rate": 0.00025,
      "loss": 0.1715,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8933333333333333,
      "eval_loss": 0.38549095392227173,
      "eval_runtime": 7.2104,
      "eval_samples_per_second": 520.084,
      "eval_steps_per_second": 8.183,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 37.69584274291992,
      "learning_rate": 0.00016666666666666666,
      "loss": 0.0768,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8984,
      "eval_loss": 0.4060770273208618,
      "eval_runtime": 7.2147,
      "eval_samples_per_second": 519.776,
      "eval_steps_per_second": 8.178,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 24.953853607177734,
      "learning_rate": 8.333333333333333e-05,
      "loss": 0.0389,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.912,
      "eval_loss": 0.36722806096076965,
      "eval_runtime": 8.0528,
      "eval_samples_per_second": 465.679,
      "eval_steps_per_second": 7.327,
      "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
}