{
  "best_global_step": 80,
  "best_metric": 0.04149133339524269,
  "best_model_checkpoint": "models/me5-large-retraining\\checkpoint-80",
  "epoch": 4.0,
  "eval_steps": 5,
  "global_step": 148,
  "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": 154.7907,
      "eval_samples_per_second": 6.499,
      "eval_spearman_cosine": 0.7843279594448466,
      "eval_steps_per_second": 0.814,
      "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": 154.4069,
      "eval_samples_per_second": 6.515,
      "eval_spearman_cosine": 0.8122999445241028,
      "eval_steps_per_second": 0.816,
      "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": 157.2408,
      "eval_samples_per_second": 6.398,
      "eval_spearman_cosine": 0.8303112726354404,
      "eval_steps_per_second": 0.801,
      "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": 153.8649,
      "eval_samples_per_second": 6.538,
      "eval_spearman_cosine": 0.8338916292060913,
      "eval_steps_per_second": 0.819,
      "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": 154.4013,
      "eval_samples_per_second": 6.515,
      "eval_spearman_cosine": 0.8344803713886917,
      "eval_steps_per_second": 0.816,
      "step": 20
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.1423,
      "step": 25
    },
    {
      "epoch": 0.6756756756756757,
      "eval_loss": 0.042350731790065765,
      "eval_pearson_cosine": 0.8419294236114762,
      "eval_runtime": 153.4308,
      "eval_samples_per_second": 6.557,
      "eval_spearman_cosine": 0.8324197823497284,
      "eval_steps_per_second": 0.821,
      "step": 25
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 11.502903938293457,
      "learning_rate": 1e-05,
      "loss": 0.2852,
      "step": 30
    },
    {
      "epoch": 0.8108108108108109,
      "eval_loss": 0.04431174322962761,
      "eval_pearson_cosine": 0.8311833878571917,
      "eval_runtime": 153.1117,
      "eval_samples_per_second": 6.57,
      "eval_spearman_cosine": 0.8270800450821792,
      "eval_steps_per_second": 0.823,
      "step": 30
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 13.956666946411133,
      "learning_rate": 1e-05,
      "loss": 0.2616,
      "step": 35
    },
    {
      "epoch": 0.9459459459459459,
      "eval_loss": 0.05144113302230835,
      "eval_pearson_cosine": 0.8323883964862309,
      "eval_runtime": 153.6257,
      "eval_samples_per_second": 6.548,
      "eval_spearman_cosine": 0.8261627064456549,
      "eval_steps_per_second": 0.82,
      "step": 35
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.1451,
      "step": 40
    },
    {
      "epoch": 1.0810810810810811,
      "eval_loss": 0.052108317613601685,
      "eval_pearson_cosine": 0.8322596480425719,
      "eval_runtime": 152.7732,
      "eval_samples_per_second": 6.585,
      "eval_spearman_cosine": 0.8232463910787938,
      "eval_steps_per_second": 0.825,
      "step": 40
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 11.031551361083984,
      "learning_rate": 1e-05,
      "loss": 0.2046,
      "step": 45
    },
    {
      "epoch": 1.2162162162162162,
      "eval_loss": 0.049648430198431015,
      "eval_pearson_cosine": 0.8345968763719022,
      "eval_runtime": 151.5419,
      "eval_samples_per_second": 6.638,
      "eval_spearman_cosine": 0.8220928743948337,
      "eval_steps_per_second": 0.831,
      "step": 45
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.055,
      "step": 50
    },
    {
      "epoch": 1.3513513513513513,
      "eval_loss": 0.05155247077345848,
      "eval_pearson_cosine": 0.8295312877735412,
      "eval_runtime": 152.4645,
      "eval_samples_per_second": 6.598,
      "eval_spearman_cosine": 0.8197002635410278,
      "eval_steps_per_second": 0.826,
      "step": 50
    },
    {
      "epoch": 1.4864864864864864,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0956,
      "step": 55
    },
    {
      "epoch": 1.4864864864864864,
      "eval_loss": 0.05453842505812645,
      "eval_pearson_cosine": 0.8258612961974536,
      "eval_runtime": 151.2464,
      "eval_samples_per_second": 6.651,
      "eval_spearman_cosine": 0.8190362223126076,
      "eval_steps_per_second": 0.833,
      "step": 55
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 10.073129653930664,
      "learning_rate": 1e-05,
      "loss": 0.1213,
      "step": 60
    },
    {
      "epoch": 1.6216216216216215,
      "eval_loss": 0.05331311747431755,
      "eval_pearson_cosine": 0.8280490163439709,
      "eval_runtime": 151.9002,
      "eval_samples_per_second": 6.623,
      "eval_spearman_cosine": 0.8212679517806181,
      "eval_steps_per_second": 0.829,
      "step": 60
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 8.610294342041016,
      "learning_rate": 1e-05,
      "loss": 0.2378,
      "step": 65
    },
    {
      "epoch": 1.7567567567567568,
      "eval_loss": 0.04638493061065674,
      "eval_pearson_cosine": 0.8348764332747338,
      "eval_runtime": 151.3483,
      "eval_samples_per_second": 6.647,
      "eval_spearman_cosine": 0.8253343633484949,
      "eval_steps_per_second": 0.833,
      "step": 65
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 7.2265729904174805,
      "learning_rate": 1e-05,
      "loss": 0.2723,
      "step": 70
    },
    {
      "epoch": 1.8918918918918919,
      "eval_loss": 0.04580773040652275,
      "eval_pearson_cosine": 0.8327080612027193,
      "eval_runtime": 151.0951,
      "eval_samples_per_second": 6.658,
      "eval_spearman_cosine": 0.8249373111883099,
      "eval_steps_per_second": 0.834,
      "step": 70
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0603,
      "step": 75
    },
    {
      "epoch": 2.027027027027027,
      "eval_loss": 0.04667947068810463,
      "eval_pearson_cosine": 0.8292172905350813,
      "eval_runtime": 150.817,
      "eval_samples_per_second": 6.67,
      "eval_spearman_cosine": 0.8226234223032437,
      "eval_steps_per_second": 0.835,
      "step": 75
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 7.278922080993652,
      "learning_rate": 1e-05,
      "loss": 0.1089,
      "step": 80
    },
    {
      "epoch": 2.1621621621621623,
      "eval_loss": 0.04149133339524269,
      "eval_pearson_cosine": 0.8348787263877363,
      "eval_runtime": 151.9077,
      "eval_samples_per_second": 6.622,
      "eval_spearman_cosine": 0.8262517044196894,
      "eval_steps_per_second": 0.829,
      "step": 80
    },
    {
      "epoch": 2.2972972972972974,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0813,
      "step": 85
    },
    {
      "epoch": 2.2972972972972974,
      "eval_loss": 0.041691090911626816,
      "eval_pearson_cosine": 0.834739922043313,
      "eval_runtime": 151.4069,
      "eval_samples_per_second": 6.644,
      "eval_spearman_cosine": 0.8269978977904043,
      "eval_steps_per_second": 0.832,
      "step": 85
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 90
    },
    {
      "epoch": 2.4324324324324325,
      "eval_loss": 0.043681543320417404,
      "eval_pearson_cosine": 0.8300953895591171,
      "eval_runtime": 151.2024,
      "eval_samples_per_second": 6.653,
      "eval_spearman_cosine": 0.8249920776743955,
      "eval_steps_per_second": 0.833,
      "step": 90
    },
    {
      "epoch": 2.5675675675675675,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0436,
      "step": 95
    },
    {
      "epoch": 2.5675675675675675,
      "eval_loss": 0.04666070267558098,
      "eval_pearson_cosine": 0.8280036278693699,
      "eval_runtime": 150.6994,
      "eval_samples_per_second": 6.676,
      "eval_spearman_cosine": 0.8241911129581995,
      "eval_steps_per_second": 0.836,
      "step": 95
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 100
    },
    {
      "epoch": 2.7027027027027026,
      "eval_loss": 0.04513184353709221,
      "eval_pearson_cosine": 0.827662426497365,
      "eval_runtime": 151.7254,
      "eval_samples_per_second": 6.63,
      "eval_spearman_cosine": 0.8241911153867979,
      "eval_steps_per_second": 0.83,
      "step": 100
    },
    {
      "epoch": 2.8378378378378377,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 105
    },
    {
      "epoch": 2.8378378378378377,
      "eval_loss": 0.045100126415491104,
      "eval_pearson_cosine": 0.8271686930217653,
      "eval_runtime": 150.6791,
      "eval_samples_per_second": 6.676,
      "eval_spearman_cosine": 0.8242595734942031,
      "eval_steps_per_second": 0.836,
      "step": 105
    },
    {
      "epoch": 2.972972972972973,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0271,
      "step": 110
    },
    {
      "epoch": 2.972972972972973,
      "eval_loss": 0.04326998442411423,
      "eval_pearson_cosine": 0.8242998475213165,
      "eval_runtime": 151.5644,
      "eval_samples_per_second": 6.637,
      "eval_spearman_cosine": 0.8243348749833265,
      "eval_steps_per_second": 0.831,
      "step": 110
    },
    {
      "epoch": 3.108108108108108,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.007,
      "step": 115
    },
    {
      "epoch": 3.108108108108108,
      "eval_loss": 0.050163887441158295,
      "eval_pearson_cosine": 0.8100599157021782,
      "eval_runtime": 149.8939,
      "eval_samples_per_second": 6.711,
      "eval_spearman_cosine": 0.8195085832550942,
      "eval_steps_per_second": 0.841,
      "step": 115
    },
    {
      "epoch": 3.2432432432432434,
      "grad_norm": 5.909173011779785,
      "learning_rate": 1e-05,
      "loss": 0.1025,
      "step": 120
    },
    {
      "epoch": 3.2432432432432434,
      "eval_loss": 0.052336592227220535,
      "eval_pearson_cosine": 0.8092739374985023,
      "eval_runtime": 151.2544,
      "eval_samples_per_second": 6.651,
      "eval_spearman_cosine": 0.8194743493718913,
      "eval_steps_per_second": 0.833,
      "step": 120
    },
    {
      "epoch": 3.3783783783783785,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.1244,
      "step": 125
    },
    {
      "epoch": 3.3783783783783785,
      "eval_loss": 0.05269436165690422,
      "eval_pearson_cosine": 0.8212737827789367,
      "eval_runtime": 150.843,
      "eval_samples_per_second": 6.669,
      "eval_spearman_cosine": 0.8250605382131625,
      "eval_steps_per_second": 0.835,
      "step": 125
    },
    {
      "epoch": 3.5135135135135136,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0,
      "step": 130
    },
    {
      "epoch": 3.5135135135135136,
      "eval_loss": 0.05343884229660034,
      "eval_pearson_cosine": 0.8257663666576973,
      "eval_runtime": 150.9582,
      "eval_samples_per_second": 6.664,
      "eval_spearman_cosine": 0.8261900896885362,
      "eval_steps_per_second": 0.835,
      "step": 130
    },
    {
      "epoch": 3.6486486486486487,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0259,
      "step": 135
    },
    {
      "epoch": 3.6486486486486487,
      "eval_loss": 0.05709109827876091,
      "eval_pearson_cosine": 0.8294106767298322,
      "eval_runtime": 151.0358,
      "eval_samples_per_second": 6.661,
      "eval_spearman_cosine": 0.826217475365987,
      "eval_steps_per_second": 0.834,
      "step": 135
    },
    {
      "epoch": 3.7837837837837838,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 0.0939,
      "step": 140
    },
    {
      "epoch": 3.7837837837837838,
      "eval_loss": 0.05264894291758537,
      "eval_pearson_cosine": 0.8333850683405307,
      "eval_runtime": 151.069,
      "eval_samples_per_second": 6.659,
      "eval_spearman_cosine": 0.8273128026466706,
      "eval_steps_per_second": 0.834,
      "step": 140
    },
    {
      "epoch": 3.918918918918919,
      "grad_norm": 7.900262832641602,
      "learning_rate": 1e-05,
      "loss": 0.1038,
      "step": 145
    },
    {
      "epoch": 3.918918918918919,
      "eval_loss": 0.0527377724647522,
      "eval_pearson_cosine": 0.8334934833047165,
      "eval_runtime": 150.8011,
      "eval_samples_per_second": 6.671,
      "eval_spearman_cosine": 0.8261353280714282,
      "eval_steps_per_second": 0.836,
      "step": 145
    }
  ],
  "logging_steps": 5,
  "max_steps": 148,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 10,
  "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
}