trainer_state.json

{
  "best_metric": 0.804,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0724/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": 348.7849426269531,
      "learning_rate": 4.166666666666667e-05,
      "loss": 3.6189,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.544,
      "eval_loss": 3.089111089706421,
      "eval_runtime": 7.0919,
      "eval_samples_per_second": 528.772,
      "eval_steps_per_second": 8.319,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 168.7998504638672,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.7746,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7234666666666667,
      "eval_loss": 1.032719612121582,
      "eval_runtime": 7.056,
      "eval_samples_per_second": 531.459,
      "eval_steps_per_second": 8.362,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 256.2583312988281,
      "learning_rate": 2.5e-05,
      "loss": 0.8698,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7848,
      "eval_loss": 0.7606624960899353,
      "eval_runtime": 7.1217,
      "eval_samples_per_second": 526.562,
      "eval_steps_per_second": 8.285,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 231.1844024658203,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.6647,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7965333333333333,
      "eval_loss": 0.6756935119628906,
      "eval_runtime": 7.0289,
      "eval_samples_per_second": 533.515,
      "eval_steps_per_second": 8.394,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 258.7714538574219,
      "learning_rate": 8.333333333333334e-06,
      "loss": 0.5694,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.804,
      "eval_loss": 0.645366907119751,
      "eval_runtime": 7.0387,
      "eval_samples_per_second": 532.767,
      "eval_steps_per_second": 8.382,
      "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
}