{
  "best_metric": 0.5301018357276917,
  "best_model_checkpoint": "./Vit-GPT2-COCO2017Flickr-85k-09/checkpoint-1000",
  "epoch": 0.1866193897545955,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09330969487729775,
      "grad_norm": 1.1049598455429077,
      "learning_rate": 4.8444693293517484e-05,
      "loss": 0.2429,
      "step": 500
    },
    {
      "epoch": 0.09330969487729775,
      "eval_gen_len": 11.738,
      "eval_loss": 0.5351373553276062,
      "eval_rouge1": 39.4446,
      "eval_rouge2": 14.1599,
      "eval_rougeL": 35.6123,
      "eval_rougeLsum": 35.5846,
      "eval_runtime": 463.8252,
      "eval_samples_per_second": 8.624,
      "eval_steps_per_second": 2.156,
      "step": 500
    },
    {
      "epoch": 0.1866193897545955,
      "grad_norm": 1.1426328420639038,
      "learning_rate": 4.6889386587034965e-05,
      "loss": 0.2537,
      "step": 1000
    },
    {
      "epoch": 0.1866193897545955,
      "eval_gen_len": 12.34875,
      "eval_loss": 0.5301018357276917,
      "eval_rouge1": 39.5332,
      "eval_rouge2": 14.4745,
      "eval_rougeL": 35.644,
      "eval_rougeLsum": 35.6159,
      "eval_runtime": 451.0336,
      "eval_samples_per_second": 8.869,
      "eval_steps_per_second": 2.217,
      "step": 1000
    }
  ],
  "logging_steps": 500,
  "max_steps": 16074,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 2.887422257922048e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}