{
  "best_global_step": 500,
  "best_metric": 0.37418202501961656,
  "best_model_checkpoint": "checkpoints/med-ruri-v3-310m-v2-from-ruri/checkpoint-500",
  "epoch": 0.054124269322364145,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0054124269322364145,
      "grad_norm": 39.82763671875,
      "learning_rate": 1.0606060606060608e-06,
      "loss": 2.5545263671875,
      "step": 50
    },
    {
      "epoch": 0.010824853864472829,
      "grad_norm": 22.23030662536621,
      "learning_rate": 2.1428571428571427e-06,
      "loss": 1.6219686889648437,
      "step": 100
    },
    {
      "epoch": 0.016237280796709243,
      "grad_norm": 15.578224182128906,
      "learning_rate": 3.2251082251082253e-06,
      "loss": 1.4178483581542969,
      "step": 150
    },
    {
      "epoch": 0.021649707728945658,
      "grad_norm": 15.494049072265625,
      "learning_rate": 4.3073593073593075e-06,
      "loss": 1.3550909423828126,
      "step": 200
    },
    {
      "epoch": 0.027062134661182072,
      "grad_norm": 21.17428970336914,
      "learning_rate": 5.38961038961039e-06,
      "loss": 1.2207350158691406,
      "step": 250
    },
    {
      "epoch": 0.03247456159341849,
      "grad_norm": 21.015527725219727,
      "learning_rate": 6.471861471861473e-06,
      "loss": 1.127685775756836,
      "step": 300
    },
    {
      "epoch": 0.037886988525654905,
      "grad_norm": 18.954545974731445,
      "learning_rate": 7.554112554112555e-06,
      "loss": 1.1038306427001954,
      "step": 350
    },
    {
      "epoch": 0.043299415457891316,
      "grad_norm": 32.8043212890625,
      "learning_rate": 8.636363636363637e-06,
      "loss": 1.073208770751953,
      "step": 400
    },
    {
      "epoch": 0.048711842390127734,
      "grad_norm": 19.81218147277832,
      "learning_rate": 9.71861471861472e-06,
      "loss": 1.026578369140625,
      "step": 450
    },
    {
      "epoch": 0.054124269322364145,
      "grad_norm": 65.24224090576172,
      "learning_rate": 9.957839562443026e-06,
      "loss": 1.0128096008300782,
      "step": 500
    },
    {
      "epoch": 0.054124269322364145,
      "eval_med-ir_cosine_accuracy@1": 0.213,
      "eval_med-ir_cosine_accuracy@10": 0.5545,
      "eval_med-ir_cosine_accuracy@5": 0.4565,
      "eval_med-ir_cosine_map@10": 0.31760753968253963,
      "eval_med-ir_cosine_mrr@10": 0.31760753968254,
      "eval_med-ir_cosine_ndcg@10": 0.37418202501961656,
      "eval_med-ir_cosine_precision@1": 0.213,
      "eval_med-ir_cosine_precision@10": 0.05544999999999999,
      "eval_med-ir_cosine_precision@5": 0.09129999999999998,
      "eval_med-ir_cosine_recall@1": 0.213,
      "eval_med-ir_cosine_recall@10": 0.5545,
      "eval_med-ir_cosine_recall@5": 0.4565,
      "eval_runtime": 201.9792,
      "eval_samples_per_second": 0.0,
      "eval_steps_per_second": 0.0,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 9238,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}