trainer_state.json

{
  "best_metric": 0.9077333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0289/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": 68.48475646972656,
      "learning_rate": 0.0002713525491562421,
      "loss": 1.4828,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8568,
      "eval_loss": 0.4646778702735901,
      "eval_runtime": 8.7399,
      "eval_samples_per_second": 429.065,
      "eval_steps_per_second": 6.751,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 71.28968048095703,
      "learning_rate": 0.0001963525491562421,
      "loss": 0.3877,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8877333333333334,
      "eval_loss": 0.35738247632980347,
      "eval_runtime": 7.8064,
      "eval_samples_per_second": 480.373,
      "eval_steps_per_second": 7.558,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 63.44658660888672,
      "learning_rate": 0.0001036474508437579,
      "loss": 0.2179,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8952,
      "eval_loss": 0.32447290420532227,
      "eval_runtime": 8.0233,
      "eval_samples_per_second": 467.387,
      "eval_steps_per_second": 7.354,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 38.778507232666016,
      "learning_rate": 2.8647450843757897e-05,
      "loss": 0.1292,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9072,
      "eval_loss": 0.30292433500289917,
      "eval_runtime": 8.8413,
      "eval_samples_per_second": 424.147,
      "eval_steps_per_second": 6.673,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 37.90837478637695,
      "learning_rate": 0.0,
      "loss": 0.0914,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9077333333333333,
      "eval_loss": 0.30815237760543823,
      "eval_runtime": 7.8239,
      "eval_samples_per_second": 479.299,
      "eval_steps_per_second": 7.541,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1665,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}