trainer_state.json

{
  "best_metric": 0.8797333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0963/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": 167.7349395751953,
      "learning_rate": 8.397114317029975e-05,
      "loss": 2.9954,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6954666666666667,
      "eval_loss": 1.2690622806549072,
      "eval_runtime": 8.1091,
      "eval_samples_per_second": 462.441,
      "eval_steps_per_second": 7.276,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 98.91895294189453,
      "learning_rate": 6.75e-05,
      "loss": 0.8933,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8232,
      "eval_loss": 0.6110825538635254,
      "eval_runtime": 8.2589,
      "eval_samples_per_second": 454.057,
      "eval_steps_per_second": 7.144,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 90.64159393310547,
      "learning_rate": 4.5e-05,
      "loss": 0.5464,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8554666666666667,
      "eval_loss": 0.4716441333293915,
      "eval_runtime": 8.1981,
      "eval_samples_per_second": 457.425,
      "eval_steps_per_second": 7.197,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 109.95480346679688,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.4253,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.876,
      "eval_loss": 0.4268736243247986,
      "eval_runtime": 8.0809,
      "eval_samples_per_second": 464.06,
      "eval_steps_per_second": 7.301,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 81.21760559082031,
      "learning_rate": 6.028856829700258e-06,
      "loss": 0.3709,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8722666666666666,
      "eval_loss": 0.42148855328559875,
      "eval_runtime": 8.3264,
      "eval_samples_per_second": 450.375,
      "eval_steps_per_second": 7.086,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 87.42887878417969,
      "learning_rate": 0.0,
      "loss": 0.3513,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8797333333333334,
      "eval_loss": 0.41752415895462036,
      "eval_runtime": 8.2325,
      "eval_samples_per_second": 455.51,
      "eval_steps_per_second": 7.167,
      "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
}