trainer_state.json

{
  "best_metric": 0.9016,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0023/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": 123.46312713623047,
      "learning_rate": 7e-05,
      "loss": 3.1575,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6746666666666666,
      "eval_loss": 1.397975206375122,
      "eval_runtime": 7.6666,
      "eval_samples_per_second": 489.133,
      "eval_steps_per_second": 7.696,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 71.82424926757812,
      "learning_rate": 7e-05,
      "loss": 0.8813,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8384,
      "eval_loss": 0.5764047503471375,
      "eval_runtime": 7.778,
      "eval_samples_per_second": 482.129,
      "eval_steps_per_second": 7.585,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 79.69744873046875,
      "learning_rate": 7e-05,
      "loss": 0.4964,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8693333333333333,
      "eval_loss": 0.446013867855072,
      "eval_runtime": 7.9106,
      "eval_samples_per_second": 474.048,
      "eval_steps_per_second": 7.458,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 50.50783920288086,
      "learning_rate": 7e-05,
      "loss": 0.3536,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8773333333333333,
      "eval_loss": 0.3914264440536499,
      "eval_runtime": 7.9973,
      "eval_samples_per_second": 468.909,
      "eval_steps_per_second": 7.378,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 80.49609375,
      "learning_rate": 7e-05,
      "loss": 0.2705,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8872,
      "eval_loss": 0.380067378282547,
      "eval_runtime": 8.0023,
      "eval_samples_per_second": 468.613,
      "eval_steps_per_second": 7.373,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 91.1989974975586,
      "learning_rate": 7e-05,
      "loss": 0.2085,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9016,
      "eval_loss": 0.334468275308609,
      "eval_runtime": 7.8767,
      "eval_samples_per_second": 476.087,
      "eval_steps_per_second": 7.49,
      "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
}