checkpoint-1125/trainer_state.json

{
  "best_metric": 2.313333034515381,
  "best_model_checkpoint": "cat_breed_image_detection/checkpoint-1125",
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 1125,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 3.2299349308013916,
      "learning_rate": 2.9069767441860464e-07,
      "loss": 2.2975,
      "step": 500
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 4.116338729858398,
      "learning_rate": 5.813953488372093e-08,
      "loss": 2.2851,
      "step": 1000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.4488333333333333,
      "eval_loss": 2.313333034515381,
      "eval_runtime": 530.0302,
      "eval_samples_per_second": 90.561,
      "eval_steps_per_second": 2.83,
      "step": 1125
    }
  ],
  "logging_steps": 500,
  "max_steps": 1125,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 5.581723556118528e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}