{
  "best_global_step": 504,
  "best_metric": 0.9948770491803278,
  "best_model_checkpoint": "./deberta_v3_fold_5/checkpoint-504",
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 504,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.39227038621902466,
      "eval_map@3": 0.9682377049180327,
      "eval_runtime": 67.2058,
      "eval_samples_per_second": 7.261,
      "eval_steps_per_second": 7.261,
      "step": 126
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.10894713550806046,
      "eval_map@3": 0.9897540983606558,
      "eval_runtime": 67.335,
      "eval_samples_per_second": 7.247,
      "eval_steps_per_second": 7.247,
      "step": 252
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.07791455090045929,
      "eval_map@3": 0.9938524590163934,
      "eval_runtime": 66.9841,
      "eval_samples_per_second": 7.285,
      "eval_steps_per_second": 7.285,
      "step": 378
    },
    {
      "epoch": 3.970178926441352,
      "grad_norm": 68.77577209472656,
      "learning_rate": 2.1962072489860595e-09,
      "loss": 7.847896484375,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.06077062711119652,
      "eval_map@3": 0.9948770491803278,
      "eval_runtime": 64.5074,
      "eval_samples_per_second": 7.565,
      "eval_steps_per_second": 7.565,
      "step": 504
    }
  ],
  "logging_steps": 500,
  "max_steps": 504,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "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": 4504738418300160.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}