{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.998433420365535,
  "eval_steps": 500,
  "global_step": 2871,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5221932114882507,
      "grad_norm": 6.875,
      "learning_rate": 1.856369613349391e-05,
      "loss": 0.7949,
      "step": 500
    },
    {
      "epoch": 0.5221932114882507,
      "eval_retrival_loss": 0.01873534359037876,
      "eval_retrival_runtime": 1.6428,
      "eval_retrival_samples_per_second": 608.716,
      "eval_retrival_steps_per_second": 19.479,
      "step": 500
    },
    {
      "epoch": 0.5221932114882507,
      "eval_sts_loss": 2.652181386947632,
      "eval_sts_runtime": 2.0073,
      "eval_sts_samples_per_second": 237.63,
      "eval_sts_steps_per_second": 7.473,
      "step": 500
    },
    {
      "epoch": 0.5221932114882507,
      "eval_reranking_loss": 0.2930990159511566,
      "eval_reranking_runtime": 5.9616,
      "eval_reranking_samples_per_second": 167.74,
      "eval_reranking_steps_per_second": 5.368,
      "step": 500
    },
    {
      "epoch": 1.0443864229765012,
      "grad_norm": 5.96875,
      "learning_rate": 1.4618836502727944e-05,
      "loss": 0.6813,
      "step": 1000
    },
    {
      "epoch": 1.0443864229765012,
      "eval_retrival_loss": 0.013903363607823849,
      "eval_retrival_runtime": 1.7481,
      "eval_retrival_samples_per_second": 572.037,
      "eval_retrival_steps_per_second": 18.305,
      "step": 1000
    },
    {
      "epoch": 1.0443864229765012,
      "eval_sts_loss": 2.5108530521392822,
      "eval_sts_runtime": 2.0678,
      "eval_sts_samples_per_second": 230.679,
      "eval_sts_steps_per_second": 7.254,
      "step": 1000
    },
    {
      "epoch": 1.0443864229765012,
      "eval_reranking_loss": 0.2695285677909851,
      "eval_reranking_runtime": 6.0139,
      "eval_reranking_samples_per_second": 166.28,
      "eval_reranking_steps_per_second": 5.321,
      "step": 1000
    },
    {
      "epoch": 1.566579634464752,
      "grad_norm": 15.875,
      "learning_rate": 9.32090426406817e-06,
      "loss": 0.5148,
      "step": 1500
    },
    {
      "epoch": 1.566579634464752,
      "eval_retrival_loss": 0.011771922931075096,
      "eval_retrival_runtime": 1.704,
      "eval_retrival_samples_per_second": 586.858,
      "eval_retrival_steps_per_second": 18.779,
      "step": 1500
    },
    {
      "epoch": 1.566579634464752,
      "eval_sts_loss": 2.526954412460327,
      "eval_sts_runtime": 2.021,
      "eval_sts_samples_per_second": 236.022,
      "eval_sts_steps_per_second": 7.422,
      "step": 1500
    },
    {
      "epoch": 1.566579634464752,
      "eval_reranking_loss": 0.28074678778648376,
      "eval_reranking_runtime": 5.9437,
      "eval_reranking_samples_per_second": 168.245,
      "eval_reranking_steps_per_second": 5.384,
      "step": 1500
    },
    {
      "epoch": 2.0887728459530024,
      "grad_norm": 8.625,
      "learning_rate": 4.221910835622651e-06,
      "loss": 0.48,
      "step": 2000
    },
    {
      "epoch": 2.0887728459530024,
      "eval_retrival_loss": 0.011438765563070774,
      "eval_retrival_runtime": 1.7039,
      "eval_retrival_samples_per_second": 586.897,
      "eval_retrival_steps_per_second": 18.781,
      "step": 2000
    },
    {
      "epoch": 2.0887728459530024,
      "eval_sts_loss": 2.541757106781006,
      "eval_sts_runtime": 2.0493,
      "eval_sts_samples_per_second": 232.762,
      "eval_sts_steps_per_second": 7.32,
      "step": 2000
    },
    {
      "epoch": 2.0887728459530024,
      "eval_reranking_loss": 0.27911052107810974,
      "eval_reranking_runtime": 5.9433,
      "eval_reranking_samples_per_second": 168.256,
      "eval_reranking_steps_per_second": 5.384,
      "step": 2000
    },
    {
      "epoch": 2.6109660574412534,
      "grad_norm": 10.625,
      "learning_rate": 8.155891806138993e-07,
      "loss": 0.3782,
      "step": 2500
    },
    {
      "epoch": 2.6109660574412534,
      "eval_retrival_loss": 0.01174311526119709,
      "eval_retrival_runtime": 1.6915,
      "eval_retrival_samples_per_second": 591.189,
      "eval_retrival_steps_per_second": 18.918,
      "step": 2500
    },
    {
      "epoch": 2.6109660574412534,
      "eval_sts_loss": 2.573981285095215,
      "eval_sts_runtime": 2.0103,
      "eval_sts_samples_per_second": 237.277,
      "eval_sts_steps_per_second": 7.462,
      "step": 2500
    },
    {
      "epoch": 2.6109660574412534,
      "eval_reranking_loss": 0.2787380516529083,
      "eval_reranking_runtime": 5.9757,
      "eval_reranking_samples_per_second": 167.345,
      "eval_reranking_steps_per_second": 5.355,
      "step": 2500
    }
  ],
  "logging_steps": 500,
  "max_steps": 2871,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}