trainer_state.json

{
  "best_metric": 0.924,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0125/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": 24.310382843017578,
      "learning_rate": 0.00046650635094610973,
      "loss": 1.2837,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8474666666666667,
      "eval_loss": 0.540452241897583,
      "eval_runtime": 9.5282,
      "eval_samples_per_second": 393.57,
      "eval_steps_per_second": 6.192,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 34.34645462036133,
      "learning_rate": 0.000375,
      "loss": 0.3766,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8994666666666666,
      "eval_loss": 0.363151878118515,
      "eval_runtime": 9.3204,
      "eval_samples_per_second": 402.345,
      "eval_steps_per_second": 6.33,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 19.22256088256836,
      "learning_rate": 0.00025,
      "loss": 0.2002,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9085333333333333,
      "eval_loss": 0.3203178346157074,
      "eval_runtime": 9.4205,
      "eval_samples_per_second": 398.068,
      "eval_steps_per_second": 6.263,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 23.339628219604492,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.1012,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9154666666666667,
      "eval_loss": 0.3201880156993866,
      "eval_runtime": 9.2721,
      "eval_samples_per_second": 404.437,
      "eval_steps_per_second": 6.363,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 36.69596481323242,
      "learning_rate": 3.3493649053890325e-05,
      "loss": 0.0522,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9208,
      "eval_loss": 0.3032572865486145,
      "eval_runtime": 9.5207,
      "eval_samples_per_second": 393.881,
      "eval_steps_per_second": 6.197,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 32.271854400634766,
      "learning_rate": 0.0,
      "loss": 0.0339,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.924,
      "eval_loss": 0.2865983843803406,
      "eval_runtime": 9.7172,
      "eval_samples_per_second": 385.915,
      "eval_steps_per_second": 6.072,
      "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
}