{
  "best_global_step": 92,
  "best_metric": 1.9508870840072632,
  "best_model_checkpoint": "distilbert_km_5_v2_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": 4.214046955108643,
      "learning_rate": 4.9e-05,
      "loss": 2.855,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.15681051893615638,
      "eval_loss": 2.3395814895629883,
      "eval_pearson": 0.15975818069114664,
      "eval_runtime": 0.638,
      "eval_samples_per_second": 2351.257,
      "eval_spearmanr": 0.15386285718116616,
      "eval_steps_per_second": 9.405,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 10.74160385131836,
      "learning_rate": 4.8e-05,
      "loss": 1.8792,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.2542018452927103,
      "eval_loss": 2.2082157135009766,
      "eval_pearson": 0.2598550550881701,
      "eval_runtime": 0.6368,
      "eval_samples_per_second": 2355.376,
      "eval_spearmanr": 0.24854863549725048,
      "eval_steps_per_second": 9.422,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 8.557888984680176,
      "learning_rate": 4.7e-05,
      "loss": 1.531,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.36344823522664726,
      "eval_loss": 2.102039337158203,
      "eval_pearson": 0.3664600691916206,
      "eval_runtime": 0.6132,
      "eval_samples_per_second": 2446.291,
      "eval_spearmanr": 0.3604364012616739,
      "eval_steps_per_second": 9.785,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 10.786069869995117,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.1221,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.42787495392400654,
      "eval_loss": 1.9508870840072632,
      "eval_pearson": 0.42928426972158884,
      "eval_runtime": 0.6454,
      "eval_samples_per_second": 2324.136,
      "eval_spearmanr": 0.42646563812642424,
      "eval_steps_per_second": 9.297,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 9.451976776123047,
      "learning_rate": 4.5e-05,
      "loss": 0.7863,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.4231247107902911,
      "eval_loss": 2.1920552253723145,
      "eval_pearson": 0.4220805532940873,
      "eval_runtime": 0.6247,
      "eval_samples_per_second": 2401.046,
      "eval_spearmanr": 0.424168868286495,
      "eval_steps_per_second": 9.604,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 8.174893379211426,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.5364,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.44982265620344597,
      "eval_loss": 2.103825092315674,
      "eval_pearson": 0.4495877020353542,
      "eval_runtime": 0.6663,
      "eval_samples_per_second": 2251.296,
      "eval_spearmanr": 0.45005761037153774,
      "eval_steps_per_second": 9.005,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 12.101842880249023,
      "learning_rate": 4.3e-05,
      "loss": 0.4273,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.45187776761981563,
      "eval_loss": 2.0297229290008545,
      "eval_pearson": 0.4534507769776595,
      "eval_runtime": 0.6633,
      "eval_samples_per_second": 2261.348,
      "eval_spearmanr": 0.45030475826197175,
      "eval_steps_per_second": 9.045,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 14.183196067810059,
      "learning_rate": 4.2e-05,
      "loss": 0.3516,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.4247591404417475,
      "eval_loss": 2.1971278190612793,
      "eval_pearson": 0.42786080337820087,
      "eval_runtime": 0.6371,
      "eval_samples_per_second": 2354.419,
      "eval_spearmanr": 0.42165747750529414,
      "eval_steps_per_second": 9.418,
      "step": 184
    },
    {
      "epoch": 9.0,
      "grad_norm": 6.7153120040893555,
      "learning_rate": 4.1e-05,
      "loss": 0.2901,
      "step": 207
    },
    {
      "epoch": 9.0,
      "eval_combined_score": 0.4264679127133874,
      "eval_loss": 2.068239688873291,
      "eval_pearson": 0.4296080302204635,
      "eval_runtime": 0.6532,
      "eval_samples_per_second": 2296.252,
      "eval_spearmanr": 0.4233277952063113,
      "eval_steps_per_second": 9.185,
      "step": 207
    },
    {
      "epoch": 9.0,
      "step": 207,
      "total_flos": 3426936721288704.0,
      "train_loss": 1.0865587059426423,
      "train_runtime": 65.4278,
      "train_samples_per_second": 4393.389,
      "train_steps_per_second": 17.577
    }
  ],
  "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
}