trainer_state.json

{
  "best_metric": 0.8725333333333334,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0505/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 242.15829467773438,
      "learning_rate": 8.397114317029975e-05,
      "loss": 3.0001,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6877333333333333,
      "eval_loss": 1.2933989763259888,
      "eval_runtime": 8.6819,
      "eval_samples_per_second": 431.934,
      "eval_steps_per_second": 6.796,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 123.1273422241211,
      "learning_rate": 6.75e-05,
      "loss": 0.8526,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8226666666666667,
      "eval_loss": 0.6116032004356384,
      "eval_runtime": 8.3644,
      "eval_samples_per_second": 448.329,
      "eval_steps_per_second": 7.054,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 87.6818618774414,
      "learning_rate": 4.5e-05,
      "loss": 0.5212,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.852,
      "eval_loss": 0.49247655272483826,
      "eval_runtime": 8.4219,
      "eval_samples_per_second": 445.265,
      "eval_steps_per_second": 7.006,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 94.65545654296875,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.401,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8642666666666666,
      "eval_loss": 0.4585301876068115,
      "eval_runtime": 8.3967,
      "eval_samples_per_second": 446.604,
      "eval_steps_per_second": 7.027,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 216.3521270751953,
      "learning_rate": 6.028856829700258e-06,
      "loss": 0.3439,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8725333333333334,
      "eval_loss": 0.4192752540111542,
      "eval_runtime": 8.3217,
      "eval_samples_per_second": 450.627,
      "eval_steps_per_second": 7.09,
      "step": 1665
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}