{
  "best_global_step": 20,
  "best_metric": 0.043546345084905624,
  "best_model_checkpoint": "models/me5-large-retraining\\checkpoint-20",
  "epoch": 0.5405405405405406,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0,
      "eval_loss": 0.10950354486703873,
      "eval_pearson_cosine": 0.7806081242807599,
      "eval_runtime": 151.6579,
      "eval_samples_per_second": 6.633,
      "eval_spearman_cosine": 0.7843279594448466,
      "eval_steps_per_second": 0.831,
      "step": 0
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 9.38223934173584,
      "learning_rate": 1e-05,
      "loss": 0.6784,
      "step": 5
    },
    {
      "epoch": 0.13513513513513514,
      "eval_loss": 0.07647562772035599,
      "eval_pearson_cosine": 0.8193313583571735,
      "eval_runtime": 156.2929,
      "eval_samples_per_second": 6.437,
      "eval_spearman_cosine": 0.8122999445241028,
      "eval_steps_per_second": 0.806,
      "step": 5
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 8.665059089660645,
      "learning_rate": 1e-05,
      "loss": 0.5088,
      "step": 10
    },
    {
      "epoch": 0.2702702702702703,
      "eval_loss": 0.05329965054988861,
      "eval_pearson_cosine": 0.846437709431274,
      "eval_runtime": 152.6705,
      "eval_samples_per_second": 6.589,
      "eval_spearman_cosine": 0.8303112726354404,
      "eval_steps_per_second": 0.825,
      "step": 10
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 21.96602439880371,
      "learning_rate": 1e-05,
      "loss": 0.4364,
      "step": 15
    },
    {
      "epoch": 0.40540540540540543,
      "eval_loss": 0.047497160732746124,
      "eval_pearson_cosine": 0.8497791216636505,
      "eval_runtime": 150.8647,
      "eval_samples_per_second": 6.668,
      "eval_spearman_cosine": 0.8338916292060913,
      "eval_steps_per_second": 0.835,
      "step": 15
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 10.698002815246582,
      "learning_rate": 1e-05,
      "loss": 0.3456,
      "step": 20
    },
    {
      "epoch": 0.5405405405405406,
      "eval_loss": 0.043546345084905624,
      "eval_pearson_cosine": 0.8481768671521202,
      "eval_runtime": 151.8674,
      "eval_samples_per_second": 6.624,
      "eval_spearman_cosine": 0.8344803713886917,
      "eval_steps_per_second": 0.83,
      "step": 20
    }
  ],
  "logging_steps": 5,
  "max_steps": 37,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "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": 8,
  "trial_name": null,
  "trial_params": null
}