trainer_state.json

{
  "best_metric": 0.9061333333333333,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0475/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": 19.08095359802246,
      "learning_rate": 0.00046650635094610973,
      "loss": 1.2187,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.8314666666666667,
      "eval_loss": 0.5280898213386536,
      "eval_runtime": 7.7909,
      "eval_samples_per_second": 481.334,
      "eval_steps_per_second": 7.573,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 43.69490432739258,
      "learning_rate": 0.000375,
      "loss": 0.3879,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8626666666666667,
      "eval_loss": 0.4445990324020386,
      "eval_runtime": 7.5184,
      "eval_samples_per_second": 498.778,
      "eval_steps_per_second": 7.847,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 56.36721420288086,
      "learning_rate": 0.00025,
      "loss": 0.2061,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8938666666666667,
      "eval_loss": 0.3732973337173462,
      "eval_runtime": 7.7197,
      "eval_samples_per_second": 485.77,
      "eval_steps_per_second": 7.643,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 62.05194091796875,
      "learning_rate": 0.00012500000000000006,
      "loss": 0.0946,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8954666666666666,
      "eval_loss": 0.38942375779151917,
      "eval_runtime": 7.7054,
      "eval_samples_per_second": 486.671,
      "eval_steps_per_second": 7.657,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 20.581525802612305,
      "learning_rate": 3.3493649053890325e-05,
      "loss": 0.0462,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.9061333333333333,
      "eval_loss": 0.3601526618003845,
      "eval_runtime": 7.6044,
      "eval_samples_per_second": 493.133,
      "eval_steps_per_second": 7.759,
      "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
}