trainer_state.json

{
  "best_metric": 0.8901333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0545/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": 164.752685546875,
      "learning_rate": 9e-05,
      "loss": 2.8495,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7429333333333333,
      "eval_loss": 0.9701327085494995,
      "eval_runtime": 7.3752,
      "eval_samples_per_second": 508.464,
      "eval_steps_per_second": 8.0,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 205.5715789794922,
      "learning_rate": 9e-05,
      "loss": 0.6459,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.856,
      "eval_loss": 0.47999393939971924,
      "eval_runtime": 7.1302,
      "eval_samples_per_second": 525.934,
      "eval_steps_per_second": 8.275,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 89.14253997802734,
      "learning_rate": 9e-05,
      "loss": 0.3555,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8765333333333334,
      "eval_loss": 0.3982950448989868,
      "eval_runtime": 7.1063,
      "eval_samples_per_second": 527.699,
      "eval_steps_per_second": 8.302,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 54.09440231323242,
      "learning_rate": 9e-05,
      "loss": 0.2341,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8832,
      "eval_loss": 0.3865821361541748,
      "eval_runtime": 7.0042,
      "eval_samples_per_second": 535.393,
      "eval_steps_per_second": 8.424,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 103.13557434082031,
      "learning_rate": 9e-05,
      "loss": 0.1492,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8901333333333333,
      "eval_loss": 0.38369888067245483,
      "eval_runtime": 7.0192,
      "eval_samples_per_second": 534.249,
      "eval_steps_per_second": 8.406,
      "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
}