trainer_state.json

{
  "best_metric": 0.8674666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0311/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": 35.95445251464844,
      "learning_rate": 0.0005,
      "loss": 1.2913,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8416,
      "eval_loss": 0.5370098352432251,
      "eval_runtime": 7.851,
      "eval_samples_per_second": 477.645,
      "eval_steps_per_second": 7.515,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 30.10823631286621,
      "learning_rate": 0.0005,
      "loss": 0.4096,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8408,
      "eval_loss": 0.5450997948646545,
      "eval_runtime": 8.4241,
      "eval_samples_per_second": 445.149,
      "eval_steps_per_second": 7.004,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 43.859580993652344,
      "learning_rate": 0.0005,
      "loss": 0.2518,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.856,
      "eval_loss": 0.5521267652511597,
      "eval_runtime": 7.9507,
      "eval_samples_per_second": 471.655,
      "eval_steps_per_second": 7.421,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 31.150283813476562,
      "learning_rate": 0.0005,
      "loss": 0.1688,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8637333333333334,
      "eval_loss": 0.5263514518737793,
      "eval_runtime": 8.0254,
      "eval_samples_per_second": 467.264,
      "eval_steps_per_second": 7.352,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 30.756750106811523,
      "learning_rate": 0.0005,
      "loss": 0.1209,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.86,
      "eval_loss": 0.5684006214141846,
      "eval_runtime": 7.9266,
      "eval_samples_per_second": 473.094,
      "eval_steps_per_second": 7.443,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 28.391002655029297,
      "learning_rate": 0.0005,
      "loss": 0.0903,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8674666666666667,
      "eval_loss": 0.5774869322776794,
      "eval_runtime": 8.1486,
      "eval_samples_per_second": 460.201,
      "eval_steps_per_second": 7.241,
      "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
}