{
  "best_global_step": 8000,
  "best_metric": 0.8765376300834912,
  "best_model_checkpoint": "E:/ModernBERT_finetune_data/models/reranker-ModernBERT-base-s2orc\\checkpoint-8000",
  "epoch": 0.23087356786239935,
  "eval_steps": 4000,
  "global_step": 8000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.885919598279992e-05,
      "grad_norm": 7.188746452331543,
      "learning_rate": 0.0,
      "loss": 1.0682,
      "step": 1
    },
    {
      "epoch": 0.01442959799139996,
      "grad_norm": 13.780556678771973,
      "learning_rate": 2.8793998845931915e-06,
      "loss": 1.1555,
      "step": 500
    },
    {
      "epoch": 0.02885919598279992,
      "grad_norm": 52.33120346069336,
      "learning_rate": 5.76457010963647e-06,
      "loss": 0.7743,
      "step": 1000
    },
    {
      "epoch": 0.04328879397419988,
      "grad_norm": 2.325308322906494,
      "learning_rate": 8.649740334679747e-06,
      "loss": 0.538,
      "step": 1500
    },
    {
      "epoch": 0.05771839196559984,
      "grad_norm": 7.630313396453857,
      "learning_rate": 1.1534910559723025e-05,
      "loss": 0.5771,
      "step": 2000
    },
    {
      "epoch": 0.0721479899569998,
      "grad_norm": 0.15915359556674957,
      "learning_rate": 1.4420080784766301e-05,
      "loss": 0.5345,
      "step": 2500
    },
    {
      "epoch": 0.08657758794839976,
      "grad_norm": 45.458744049072266,
      "learning_rate": 1.730525100980958e-05,
      "loss": 0.4394,
      "step": 3000
    },
    {
      "epoch": 0.10100718593979972,
      "grad_norm": 1.0640169382095337,
      "learning_rate": 1.9978835978835978e-05,
      "loss": 0.4607,
      "step": 3500
    },
    {
      "epoch": 0.11543678393119967,
      "grad_norm": 0.10893326252698898,
      "learning_rate": 1.9658168991502328e-05,
      "loss": 0.3866,
      "step": 4000
    },
    {
      "epoch": 0.11543678393119967,
      "eval_NanoBEIR_R100_mean_base_map": 0.4895766320756843,
      "eval_NanoBEIR_R100_mean_base_mrr@10": 0.4775,
      "eval_NanoBEIR_R100_mean_base_ndcg@10": 0.5404259879670522,
      "eval_NanoBEIR_R100_mean_map": 0.49520150363958415,
      "eval_NanoBEIR_R100_mean_mrr@10": 0.48177777777777775,
      "eval_NanoBEIR_R100_mean_ndcg@10": 0.5468622576263062,
      "eval_NanoMSMARCO_R100_base_map": 0.4895766320756843,
      "eval_NanoMSMARCO_R100_base_mrr@10": 0.4775,
      "eval_NanoMSMARCO_R100_base_ndcg@10": 0.5404259879670522,
      "eval_NanoMSMARCO_R100_map": 0.49520150363958415,
      "eval_NanoMSMARCO_R100_mrr@10": 0.48177777777777775,
      "eval_NanoMSMARCO_R100_ndcg@10": 0.5468622576263062,
      "eval_runtime": 6161.5831,
      "eval_s2orc-dev_base_map": 0.7378771185598135,
      "eval_s2orc-dev_base_mrr@10": 0.7359269841269841,
      "eval_s2orc-dev_base_ndcg@10": 0.7659559959785154,
      "eval_s2orc-dev_map": 0.8617319597069597,
      "eval_s2orc-dev_mrr@10": 0.8613789682539682,
      "eval_s2orc-dev_ndcg@10": 0.8684642495142619,
      "eval_samples_per_second": 0.0,
      "eval_sequential_score": 0.5468622576263062,
      "eval_steps_per_second": 0.0,
      "step": 4000
    },
    {
      "epoch": 0.12986638192259964,
      "grad_norm": 3.2822253704071045,
      "learning_rate": 1.9337502004168674e-05,
      "loss": 0.4222,
      "step": 4500
    },
    {
      "epoch": 0.1442959799139996,
      "grad_norm": 0.163385272026062,
      "learning_rate": 1.9016835016835017e-05,
      "loss": 0.3734,
      "step": 5000
    },
    {
      "epoch": 0.15872557790539957,
      "grad_norm": 1.1301782131195068,
      "learning_rate": 1.8696168029501366e-05,
      "loss": 0.3558,
      "step": 5500
    },
    {
      "epoch": 0.17315517589679952,
      "grad_norm": 26.550891876220703,
      "learning_rate": 1.837550104216771e-05,
      "loss": 0.3968,
      "step": 6000
    },
    {
      "epoch": 0.18758477388819947,
      "grad_norm": 52.34437942504883,
      "learning_rate": 1.8054834054834055e-05,
      "loss": 0.3203,
      "step": 6500
    },
    {
      "epoch": 0.20201437187959945,
      "grad_norm": 0.1360524594783783,
      "learning_rate": 1.77341670675004e-05,
      "loss": 0.3354,
      "step": 7000
    },
    {
      "epoch": 0.2164439698709994,
      "grad_norm": 0.3569001853466034,
      "learning_rate": 1.7413500080166747e-05,
      "loss": 0.3579,
      "step": 7500
    },
    {
      "epoch": 0.23087356786239935,
      "grad_norm": 0.017899315804243088,
      "learning_rate": 1.7092833092833094e-05,
      "loss": 0.3349,
      "step": 8000
    },
    {
      "epoch": 0.23087356786239935,
      "eval_NanoBEIR_R100_mean_base_map": 0.4895766320756843,
      "eval_NanoBEIR_R100_mean_base_mrr@10": 0.4775,
      "eval_NanoBEIR_R100_mean_base_ndcg@10": 0.5404259879670522,
      "eval_NanoBEIR_R100_mean_map": 0.49410785900248205,
      "eval_NanoBEIR_R100_mean_mrr@10": 0.482047619047619,
      "eval_NanoBEIR_R100_mean_ndcg@10": 0.5528612484142966,
      "eval_NanoMSMARCO_R100_base_map": 0.4895766320756843,
      "eval_NanoMSMARCO_R100_base_mrr@10": 0.4775,
      "eval_NanoMSMARCO_R100_base_ndcg@10": 0.5404259879670522,
      "eval_NanoMSMARCO_R100_map": 0.49410785900248205,
      "eval_NanoMSMARCO_R100_mrr@10": 0.482047619047619,
      "eval_NanoMSMARCO_R100_ndcg@10": 0.5528612484142966,
      "eval_runtime": 4663.3621,
      "eval_s2orc-dev_base_map": 0.7378771185598135,
      "eval_s2orc-dev_base_mrr@10": 0.7359269841269841,
      "eval_s2orc-dev_base_ndcg@10": 0.7659559959785154,
      "eval_s2orc-dev_map": 0.8712208333333333,
      "eval_s2orc-dev_mrr@10": 0.871075,
      "eval_s2orc-dev_ndcg@10": 0.8765376300834912,
      "eval_samples_per_second": 0.0,
      "eval_sequential_score": 0.5528612484142966,
      "eval_steps_per_second": 0.0,
      "step": 8000
    }
  ],
  "logging_steps": 500,
  "max_steps": 34651,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 4000,
  "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": 16,
  "trial_name": null,
  "trial_params": null
}