trainer_state.json

{
  "best_metric": 0.8738666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0329/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": 93.15570831298828,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.6363,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7634666666666666,
      "eval_loss": 0.8639039993286133,
      "eval_runtime": 7.3836,
      "eval_samples_per_second": 507.884,
      "eval_steps_per_second": 7.991,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 133.83767700195312,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.6389,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8338666666666666,
      "eval_loss": 0.5215594172477722,
      "eval_runtime": 7.4014,
      "eval_samples_per_second": 506.661,
      "eval_steps_per_second": 7.971,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 102.92909240722656,
      "learning_rate": 5e-05,
      "loss": 0.4096,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8557333333333333,
      "eval_loss": 0.43351104855537415,
      "eval_runtime": 7.4016,
      "eval_samples_per_second": 506.644,
      "eval_steps_per_second": 7.971,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 63.61332702636719,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.3027,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.4124622344970703,
      "eval_runtime": 7.3798,
      "eval_samples_per_second": 508.144,
      "eval_steps_per_second": 7.995,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 96.52046966552734,
      "learning_rate": 6.698729810778065e-06,
      "loss": 0.2541,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8696,
      "eval_loss": 0.39962559938430786,
      "eval_runtime": 7.3783,
      "eval_samples_per_second": 508.247,
      "eval_steps_per_second": 7.996,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 110.64306640625,
      "learning_rate": 0.0,
      "loss": 0.236,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8738666666666667,
      "eval_loss": 0.38741469383239746,
      "eval_runtime": 7.395,
      "eval_samples_per_second": 507.101,
      "eval_steps_per_second": 7.978,
      "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
}