trainer_state.json

{
  "best_metric": 0.8744,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0764/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": 112.50154113769531,
      "learning_rate": 0.0001,
      "loss": 2.8635,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7344,
      "eval_loss": 0.9987666606903076,
      "eval_runtime": 5.5663,
      "eval_samples_per_second": 673.693,
      "eval_steps_per_second": 10.599,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 64.88934326171875,
      "learning_rate": 0.0001,
      "loss": 0.7698,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8245333333333333,
      "eval_loss": 0.5576139688491821,
      "eval_runtime": 5.6163,
      "eval_samples_per_second": 667.705,
      "eval_steps_per_second": 10.505,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 141.32388305664062,
      "learning_rate": 0.0001,
      "loss": 0.5147,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.848,
      "eval_loss": 0.48772165179252625,
      "eval_runtime": 5.5488,
      "eval_samples_per_second": 675.828,
      "eval_steps_per_second": 10.633,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 63.42500686645508,
      "learning_rate": 0.0001,
      "loss": 0.3889,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8634666666666667,
      "eval_loss": 0.4281366467475891,
      "eval_runtime": 5.5104,
      "eval_samples_per_second": 680.529,
      "eval_steps_per_second": 10.707,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 119.25059509277344,
      "learning_rate": 0.0001,
      "loss": 0.309,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8730666666666667,
      "eval_loss": 0.4121638536453247,
      "eval_runtime": 5.498,
      "eval_samples_per_second": 682.062,
      "eval_steps_per_second": 10.731,
      "step": 1665
    },
    {
      "epoch": 6.0,
      "grad_norm": 62.469154357910156,
      "learning_rate": 0.0001,
      "loss": 0.2525,
      "step": 1998
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8744,
      "eval_loss": 0.4022500216960907,
      "eval_runtime": 5.5183,
      "eval_samples_per_second": 679.554,
      "eval_steps_per_second": 10.692,
      "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
}