{
  "best_global_step": 92,
  "best_metric": 2.189281463623047,
  "best_model_checkpoint": "distilbert_km_5_v1_stsb/checkpoint-92",
  "epoch": 9.0,
  "eval_steps": 500,
  "global_step": 207,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 4.11783504486084,
      "learning_rate": 4.9e-05,
      "loss": 2.8255,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.2071850591812329,
      "eval_loss": 2.234788179397583,
      "eval_pearson": 0.2162152508056493,
      "eval_runtime": 0.6229,
      "eval_samples_per_second": 2408.205,
      "eval_spearmanr": 0.1981548675568165,
      "eval_steps_per_second": 9.633,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 4.195613861083984,
      "learning_rate": 4.8e-05,
      "loss": 1.9258,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.19755601622597602,
      "eval_loss": 2.5031092166900635,
      "eval_pearson": 0.20473311330028518,
      "eval_runtime": 0.6536,
      "eval_samples_per_second": 2294.929,
      "eval_spearmanr": 0.19037891915166683,
      "eval_steps_per_second": 9.18,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 11.821038246154785,
      "learning_rate": 4.7e-05,
      "loss": 1.6928,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.2849028465663729,
      "eval_loss": 2.266059637069702,
      "eval_pearson": 0.28792995624455686,
      "eval_runtime": 0.649,
      "eval_samples_per_second": 2311.164,
      "eval_spearmanr": 0.28187573688818884,
      "eval_steps_per_second": 9.245,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.876267910003662,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.3472,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.32560636812711885,
      "eval_loss": 2.189281463623047,
      "eval_pearson": 0.3284320731778106,
      "eval_runtime": 0.6153,
      "eval_samples_per_second": 2437.706,
      "eval_spearmanr": 0.32278066307642705,
      "eval_steps_per_second": 9.751,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 8.5341215133667,
      "learning_rate": 4.5e-05,
      "loss": 0.9832,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.31615577483041546,
      "eval_loss": 2.3848366737365723,
      "eval_pearson": 0.31629146028697624,
      "eval_runtime": 0.6585,
      "eval_samples_per_second": 2277.838,
      "eval_spearmanr": 0.3160200893738546,
      "eval_steps_per_second": 9.111,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 8.762033462524414,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.7173,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.3137237121126545,
      "eval_loss": 2.4738118648529053,
      "eval_pearson": 0.3161300205855296,
      "eval_runtime": 0.6477,
      "eval_samples_per_second": 2315.795,
      "eval_spearmanr": 0.31131740363977944,
      "eval_steps_per_second": 9.263,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 8.431158065795898,
      "learning_rate": 4.3e-05,
      "loss": 0.5115,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.3123262298171129,
      "eval_loss": 2.7082085609436035,
      "eval_pearson": 0.3146525013660125,
      "eval_runtime": 0.6196,
      "eval_samples_per_second": 2420.82,
      "eval_spearmanr": 0.30999995826821325,
      "eval_steps_per_second": 9.683,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 6.920312881469727,
      "learning_rate": 4.2e-05,
      "loss": 0.4004,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.3518642711826053,
      "eval_loss": 2.4273622035980225,
      "eval_pearson": 0.3545582764181515,
      "eval_runtime": 0.6691,
      "eval_samples_per_second": 2241.657,
      "eval_spearmanr": 0.3491702659470591,
      "eval_steps_per_second": 8.967,
      "step": 184
    },
    {
      "epoch": 9.0,
      "grad_norm": 10.069851875305176,
      "learning_rate": 4.1e-05,
      "loss": 0.3309,
      "step": 207
    },
    {
      "epoch": 9.0,
      "eval_combined_score": 0.32842703004752094,
      "eval_loss": 2.58251690864563,
      "eval_pearson": 0.3324576769081914,
      "eval_runtime": 0.6702,
      "eval_samples_per_second": 2238.215,
      "eval_spearmanr": 0.32439638318685043,
      "eval_steps_per_second": 8.953,
      "step": 207
    },
    {
      "epoch": 9.0,
      "step": 207,
      "total_flos": 3426936721288704.0,
      "train_loss": 1.1927402814229329,
      "train_runtime": 64.9094,
      "train_samples_per_second": 4428.482,
      "train_steps_per_second": 17.717
    }
  ],
  "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": 3426936721288704.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}