trainer_state.json

{
  "best_metric": 0.9082666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0342/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": 25.5684871673584,
      "learning_rate": 0.00046650635094610973,
      "loss": 1.3844,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8293333333333334,
      "eval_loss": 0.5484716296195984,
      "eval_runtime": 15.5006,
      "eval_samples_per_second": 241.926,
      "eval_steps_per_second": 3.806,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 24.57478904724121,
      "learning_rate": 0.000375,
      "loss": 0.4684,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8786666666666667,
      "eval_loss": 0.4272158145904541,
      "eval_runtime": 15.3858,
      "eval_samples_per_second": 243.732,
      "eval_steps_per_second": 3.835,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 27.24774932861328,
      "learning_rate": 0.00025,
      "loss": 0.2688,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8898666666666667,
      "eval_loss": 0.3917619287967682,
      "eval_runtime": 14.8582,
      "eval_samples_per_second": 252.386,
      "eval_steps_per_second": 3.971,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 22.70435905456543,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.153,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9010666666666667,
      "eval_loss": 0.370476096868515,
      "eval_runtime": 15.3001,
      "eval_samples_per_second": 245.097,
      "eval_steps_per_second": 3.856,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 35.75576400756836,
      "learning_rate": 3.3493649053890325e-05,
      "loss": 0.0937,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9074666666666666,
      "eval_loss": 0.3621516227722168,
      "eval_runtime": 15.3605,
      "eval_samples_per_second": 244.133,
      "eval_steps_per_second": 3.841,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 39.66212844848633,
      "learning_rate": 0.0,
      "loss": 0.0703,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9082666666666667,
      "eval_loss": 0.3443763852119446,
      "eval_runtime": 15.2389,
      "eval_samples_per_second": 246.08,
      "eval_steps_per_second": 3.872,
      "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
}