trainer_state.json

{
  "best_metric": 0.9093333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0274/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": 73.12126159667969,
      "learning_rate": 0.000288581929876693,
      "loss": 1.5878,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8424,
      "eval_loss": 0.5175034999847412,
      "eval_runtime": 13.5354,
      "eval_samples_per_second": 277.051,
      "eval_steps_per_second": 4.359,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 26.813282012939453,
      "learning_rate": 0.00025606601717798207,
      "loss": 0.4706,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8664,
      "eval_loss": 0.44078120589256287,
      "eval_runtime": 13.5753,
      "eval_samples_per_second": 276.238,
      "eval_steps_per_second": 4.346,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 49.93132781982422,
      "learning_rate": 0.00020740251485476345,
      "loss": 0.3043,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8794666666666666,
      "eval_loss": 0.41392067074775696,
      "eval_runtime": 13.4698,
      "eval_samples_per_second": 278.401,
      "eval_steps_per_second": 4.38,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 44.27360916137695,
      "learning_rate": 0.00015,
      "loss": 0.2046,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8914666666666666,
      "eval_loss": 0.3711368441581726,
      "eval_runtime": 13.4789,
      "eval_samples_per_second": 278.213,
      "eval_steps_per_second": 4.377,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 58.239891052246094,
      "learning_rate": 9.259748514523653e-05,
      "loss": 0.1425,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9034666666666666,
      "eval_loss": 0.35367611050605774,
      "eval_runtime": 13.4871,
      "eval_samples_per_second": 278.043,
      "eval_steps_per_second": 4.375,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 29.674795150756836,
      "learning_rate": 4.3933982822017876e-05,
      "loss": 0.0897,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9093333333333333,
      "eval_loss": 0.35107097029685974,
      "eval_runtime": 13.4549,
      "eval_samples_per_second": 278.708,
      "eval_steps_per_second": 4.385,
      "step": 1998
    }
  ],
  "logging_steps": 500,
  "max_steps": 2664,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "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": 4.9058575437312e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}