{
  "best_global_step": 69,
  "best_metric": 2.295596122741699,
  "best_model_checkpoint": "bert_base_km_50_v2_stsb/checkpoint-69",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 184,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 17.046415328979492,
      "learning_rate": 4.9e-05,
      "loss": 2.863,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.11022757076138598,
      "eval_loss": 2.954624652862549,
      "eval_pearson": 0.10621902790907634,
      "eval_runtime": 0.9626,
      "eval_samples_per_second": 1558.269,
      "eval_spearmanr": 0.11423611361369562,
      "eval_steps_per_second": 6.233,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 8.909213066101074,
      "learning_rate": 4.8e-05,
      "loss": 1.9987,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.21967186923790719,
      "eval_loss": 2.301198959350586,
      "eval_pearson": 0.2302422038395849,
      "eval_runtime": 0.9783,
      "eval_samples_per_second": 1533.331,
      "eval_spearmanr": 0.20910153463622946,
      "eval_steps_per_second": 6.133,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 9.068346977233887,
      "learning_rate": 4.7e-05,
      "loss": 1.7872,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.25946579574832196,
      "eval_loss": 2.295596122741699,
      "eval_pearson": 0.26604068473527165,
      "eval_runtime": 0.9809,
      "eval_samples_per_second": 1529.141,
      "eval_spearmanr": 0.2528909067613722,
      "eval_steps_per_second": 6.117,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.815414905548096,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.5246,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.2652376965809504,
      "eval_loss": 2.4770748615264893,
      "eval_pearson": 0.27355910877078093,
      "eval_runtime": 0.9467,
      "eval_samples_per_second": 1584.501,
      "eval_spearmanr": 0.2569162843911199,
      "eval_steps_per_second": 6.338,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 7.333630084991455,
      "learning_rate": 4.5e-05,
      "loss": 1.247,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.2428239034972313,
      "eval_loss": 2.5711724758148193,
      "eval_pearson": 0.2504539148046029,
      "eval_runtime": 0.9559,
      "eval_samples_per_second": 1569.248,
      "eval_spearmanr": 0.2351938921898597,
      "eval_steps_per_second": 6.277,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.800529479980469,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.9895,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.3224796672583917,
      "eval_loss": 2.4369499683380127,
      "eval_pearson": 0.3222249478005458,
      "eval_runtime": 0.9675,
      "eval_samples_per_second": 1550.459,
      "eval_spearmanr": 0.3227343867162377,
      "eval_steps_per_second": 6.202,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 9.350067138671875,
      "learning_rate": 4.3e-05,
      "loss": 0.77,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.3373918120551995,
      "eval_loss": 2.3281149864196777,
      "eval_pearson": 0.3366276702266456,
      "eval_runtime": 0.9437,
      "eval_samples_per_second": 1589.556,
      "eval_spearmanr": 0.33815595388375347,
      "eval_steps_per_second": 6.358,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 5.430957317352295,
      "learning_rate": 4.2e-05,
      "loss": 0.6098,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.3229817061959226,
      "eval_loss": 2.4814047813415527,
      "eval_pearson": 0.32553319798556846,
      "eval_runtime": 0.9753,
      "eval_samples_per_second": 1537.963,
      "eval_spearmanr": 0.3204302144062767,
      "eval_steps_per_second": 6.152,
      "step": 184
    },
    {
      "epoch": 8.0,
      "step": 184,
      "total_flos": 6050447504044032.0,
      "train_loss": 1.4737238676651665,
      "train_runtime": 98.6117,
      "train_samples_per_second": 2914.968,
      "train_steps_per_second": 11.662
    }
  ],
  "logging_steps": 1,
  "max_steps": 1150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 50,
  "save_steps": 500,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 5,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 5
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6050447504044032.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}