trainer_state.json

{
  "best_metric": 0.6832,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0364/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": 191.69337463378906,
      "learning_rate": 2.7990381056766583e-05,
      "loss": 3.863,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.26453333333333334,
      "eval_loss": 3.791912794113159,
      "eval_runtime": 8.0496,
      "eval_samples_per_second": 465.861,
      "eval_steps_per_second": 7.33,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 140.28587341308594,
      "learning_rate": 2.25e-05,
      "loss": 3.3668,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.4944,
      "eval_loss": 2.901034355163574,
      "eval_runtime": 8.1569,
      "eval_samples_per_second": 459.733,
      "eval_steps_per_second": 7.233,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 132.14541625976562,
      "learning_rate": 1.5e-05,
      "loss": 2.1875,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6037333333333333,
      "eval_loss": 1.7228673696517944,
      "eval_runtime": 8.3113,
      "eval_samples_per_second": 451.194,
      "eval_steps_per_second": 7.099,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 98.24514770507812,
      "learning_rate": 7.500000000000004e-06,
      "loss": 1.5246,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6770666666666667,
      "eval_loss": 1.3405348062515259,
      "eval_runtime": 8.0213,
      "eval_samples_per_second": 467.505,
      "eval_steps_per_second": 7.355,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 507.60406494140625,
      "learning_rate": 2.0096189432334194e-06,
      "loss": 1.3143,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6832,
      "eval_loss": 1.241461157798767,
      "eval_runtime": 8.0887,
      "eval_samples_per_second": 463.607,
      "eval_steps_per_second": 7.294,
      "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
}