trainer_state.json

{
  "best_metric": 0.8832,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0137/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": 43.14672088623047,
      "learning_rate": 0.00025,
      "loss": 1.6995,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8069333333333333,
      "eval_loss": 0.6541579365730286,
      "eval_runtime": 8.8541,
      "eval_samples_per_second": 423.534,
      "eval_steps_per_second": 6.664,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 36.25865173339844,
      "learning_rate": 0.00019999999999999998,
      "loss": 0.5327,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8474666666666667,
      "eval_loss": 0.5191962122917175,
      "eval_runtime": 8.8034,
      "eval_samples_per_second": 425.973,
      "eval_steps_per_second": 6.702,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 75.20829772949219,
      "learning_rate": 0.00015,
      "loss": 0.3195,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8586666666666667,
      "eval_loss": 0.47784778475761414,
      "eval_runtime": 8.6548,
      "eval_samples_per_second": 433.286,
      "eval_steps_per_second": 6.817,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 58.545467376708984,
      "learning_rate": 9.999999999999999e-05,
      "loss": 0.2059,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8741333333333333,
      "eval_loss": 0.45338085293769836,
      "eval_runtime": 8.6894,
      "eval_samples_per_second": 431.562,
      "eval_steps_per_second": 6.79,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 50.54165267944336,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 0.1272,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8757333333333334,
      "eval_loss": 0.45390671491622925,
      "eval_runtime": 8.6915,
      "eval_samples_per_second": 431.456,
      "eval_steps_per_second": 6.788,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 34.24094772338867,
      "learning_rate": 0.0,
      "loss": 0.0898,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.4609937369823456,
      "eval_runtime": 8.7046,
      "eval_samples_per_second": 430.807,
      "eval_steps_per_second": 6.778,
      "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
}