trainer_state.json

{
  "best_metric": 0.9026666666666666,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0804/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": 192.85142517089844,
      "learning_rate": 9e-05,
      "loss": 2.7625,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7642666666666666,
      "eval_loss": 0.906460165977478,
      "eval_runtime": 8.7798,
      "eval_samples_per_second": 427.118,
      "eval_steps_per_second": 6.72,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 126.95738983154297,
      "learning_rate": 9e-05,
      "loss": 0.6458,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8557333333333333,
      "eval_loss": 0.5009013414382935,
      "eval_runtime": 8.787,
      "eval_samples_per_second": 426.765,
      "eval_steps_per_second": 6.714,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 167.59616088867188,
      "learning_rate": 9e-05,
      "loss": 0.3938,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8784,
      "eval_loss": 0.40988028049468994,
      "eval_runtime": 8.7232,
      "eval_samples_per_second": 429.887,
      "eval_steps_per_second": 6.764,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 59.70851516723633,
      "learning_rate": 9e-05,
      "loss": 0.2889,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8789333333333333,
      "eval_loss": 0.4117720425128937,
      "eval_runtime": 8.9668,
      "eval_samples_per_second": 418.211,
      "eval_steps_per_second": 6.58,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 59.206783294677734,
      "learning_rate": 9e-05,
      "loss": 0.2105,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8952,
      "eval_loss": 0.3737916052341461,
      "eval_runtime": 8.5998,
      "eval_samples_per_second": 436.055,
      "eval_steps_per_second": 6.861,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 80.03447723388672,
      "learning_rate": 9e-05,
      "loss": 0.1639,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.9026666666666666,
      "eval_loss": 0.34539562463760376,
      "eval_runtime": 8.6127,
      "eval_samples_per_second": 435.402,
      "eval_steps_per_second": 6.85,
      "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
}