{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 4240,
  "global_step": 4240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.589622641509434,
      "grad_norm": 8.571627616882324,
      "learning_rate": 1.9606402519023878e-05,
      "loss": 0.6209,
      "step": 500
    },
    {
      "epoch": 1.179245283018868,
      "grad_norm": 3.676194667816162,
      "learning_rate": 1.69824193125164e-05,
      "loss": 0.1483,
      "step": 1000
    },
    {
      "epoch": 1.7688679245283019,
      "grad_norm": 5.61079216003418,
      "learning_rate": 1.4358436106008921e-05,
      "loss": 0.0913,
      "step": 1500
    },
    {
      "epoch": 2.358490566037736,
      "grad_norm": 1.2366987466812134,
      "learning_rate": 1.1734452899501446e-05,
      "loss": 0.0596,
      "step": 2000
    },
    {
      "epoch": 2.94811320754717,
      "grad_norm": 3.220940351486206,
      "learning_rate": 9.110469692993965e-06,
      "loss": 0.0424,
      "step": 2500
    },
    {
      "epoch": 3.5377358490566038,
      "grad_norm": 2.3057520389556885,
      "learning_rate": 6.486486486486487e-06,
      "loss": 0.0264,
      "step": 3000
    },
    {
      "epoch": 4.127358490566038,
      "grad_norm": 2.4243733882904053,
      "learning_rate": 3.862503279979009e-06,
      "loss": 0.0238,
      "step": 3500
    },
    {
      "epoch": 4.716981132075472,
      "grad_norm": 0.6340435743331909,
      "learning_rate": 1.2385200734715299e-06,
      "loss": 0.0174,
      "step": 4000
    },
    {
      "epoch": 5.0,
      "eval_runtime": 555.4101,
      "eval_samples_per_second": 0.0,
      "eval_steps_per_second": 0.0,
      "eval_validation_ir_eval_cosine_accuracy@1": 0.6168679041268698,
      "eval_validation_ir_eval_cosine_accuracy@10": 0.9657104474188634,
      "eval_validation_ir_eval_cosine_accuracy@3": 0.8619243434525468,
      "eval_validation_ir_eval_cosine_accuracy@5": 0.9229181343075739,
      "eval_validation_ir_eval_cosine_map@100": 0.7499351289030992,
      "eval_validation_ir_eval_cosine_mrr@10": 0.7480495686208372,
      "eval_validation_ir_eval_cosine_ndcg@10": 0.8018625829452034,
      "eval_validation_ir_eval_cosine_precision@1": 0.6168679041268698,
      "eval_validation_ir_eval_cosine_precision@10": 0.09657104474188634,
      "eval_validation_ir_eval_cosine_precision@3": 0.28730811448418225,
      "eval_validation_ir_eval_cosine_precision@5": 0.18458362686151478,
      "eval_validation_ir_eval_cosine_recall@1": 0.6168679041268698,
      "eval_validation_ir_eval_cosine_recall@10": 0.9657104474188634,
      "eval_validation_ir_eval_cosine_recall@3": 0.8619243434525468,
      "eval_validation_ir_eval_cosine_recall@5": 0.9229181343075739,
      "step": 4240
    }
  ],
  "logging_steps": 500,
  "max_steps": 4240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 4240,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 72,
  "trial_name": null,
  "trial_params": null
}