trainer_state.json

{
  "best_metric": 0.8274666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0995/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": 114.27075958251953,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 3.7188,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.46853333333333336,
      "eval_loss": 3.2045304775238037,
      "eval_runtime": 7.5589,
      "eval_samples_per_second": 496.106,
      "eval_steps_per_second": 7.805,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 287.4230651855469,
      "learning_rate": 4.267766952966369e-05,
      "loss": 1.9057,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7144,
      "eval_loss": 1.0915652513504028,
      "eval_runtime": 7.5583,
      "eval_samples_per_second": 496.141,
      "eval_steps_per_second": 7.806,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 157.75949096679688,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.9203,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7824,
      "eval_loss": 0.7651212811470032,
      "eval_runtime": 7.526,
      "eval_samples_per_second": 498.275,
      "eval_steps_per_second": 7.84,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 94.21107482910156,
      "learning_rate": 2.5e-05,
      "loss": 0.7023,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8173333333333334,
      "eval_loss": 0.6153745055198669,
      "eval_runtime": 7.6773,
      "eval_samples_per_second": 488.456,
      "eval_steps_per_second": 7.685,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 88.65756225585938,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.5957,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8202666666666667,
      "eval_loss": 0.5966047048568726,
      "eval_runtime": 7.5218,
      "eval_samples_per_second": 498.554,
      "eval_steps_per_second": 7.844,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 325.0043640136719,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.5442,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8274666666666667,
      "eval_loss": 0.5712250471115112,
      "eval_runtime": 7.4965,
      "eval_samples_per_second": 500.232,
      "eval_steps_per_second": 7.87,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 4.9058575437312e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}