trainer_state.json

{
  "best_metric": 0.8805333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0375/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": 41.30685043334961,
      "learning_rate": 0.0005,
      "loss": 1.2928,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8325333333333333,
      "eval_loss": 0.5438664555549622,
      "eval_runtime": 14.1304,
      "eval_samples_per_second": 265.386,
      "eval_steps_per_second": 4.175,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 22.321109771728516,
      "learning_rate": 0.0005,
      "loss": 0.4199,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8586666666666667,
      "eval_loss": 0.465839147567749,
      "eval_runtime": 14.1442,
      "eval_samples_per_second": 265.127,
      "eval_steps_per_second": 4.171,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 36.37378692626953,
      "learning_rate": 0.0005,
      "loss": 0.2648,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8597333333333333,
      "eval_loss": 0.46708017587661743,
      "eval_runtime": 14.0821,
      "eval_samples_per_second": 266.296,
      "eval_steps_per_second": 4.19,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 42.733009338378906,
      "learning_rate": 0.0005,
      "loss": 0.1858,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8776,
      "eval_loss": 0.4373081922531128,
      "eval_runtime": 14.0968,
      "eval_samples_per_second": 266.018,
      "eval_steps_per_second": 4.185,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 21.233661651611328,
      "learning_rate": 0.0005,
      "loss": 0.1331,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8725333333333334,
      "eval_loss": 0.5173125863075256,
      "eval_runtime": 14.0864,
      "eval_samples_per_second": 266.214,
      "eval_steps_per_second": 4.188,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 27.461641311645508,
      "learning_rate": 0.0005,
      "loss": 0.101,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8805333333333333,
      "eval_loss": 0.49902865290641785,
      "eval_runtime": 14.0263,
      "eval_samples_per_second": 267.355,
      "eval_steps_per_second": 4.206,
      "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
}