{
  "best_global_step": 504,
  "best_metric": 0.9979508196721312,
  "best_model_checkpoint": "./deberta_v3_fold_4/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": 0.5236571431159973,
      "eval_map@3": 0.9402322404371585,
      "eval_runtime": 66.3098,
      "eval_samples_per_second": 7.359,
      "eval_steps_per_second": 7.359,
      "step": 126
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.09199661016464233,
      "eval_map@3": 0.9965846994535519,
      "eval_runtime": 66.4797,
      "eval_samples_per_second": 7.341,
      "eval_steps_per_second": 7.341,
      "step": 252
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.05789395421743393,
      "eval_map@3": 0.9969262295081968,
      "eval_runtime": 66.9553,
      "eval_samples_per_second": 7.288,
      "eval_steps_per_second": 7.288,
      "step": 378
    },
    {
      "epoch": 3.970178926441352,
      "grad_norm": 277.28802490234375,
      "learning_rate": 2.1962072489860595e-09,
      "loss": 8.3665244140625,
      "step": 500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.042627569288015366,
      "eval_map@3": 0.9979508196721312,
      "eval_runtime": 66.4447,
      "eval_samples_per_second": 7.344,
      "eval_steps_per_second": 7.344,
      "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": 4519736739255840.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}