{
  "best_global_step": 69,
  "best_metric": 2.2146897315979004,
  "best_model_checkpoint": "distilbert_km_20_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": 7.309730052947998,
      "learning_rate": 4.9e-05,
      "loss": 3.0221,
      "step": 23
    },
    {
      "epoch": 1.0,
      "eval_combined_score": 0.11851146074576263,
      "eval_loss": 2.382185459136963,
      "eval_pearson": 0.1213584115373974,
      "eval_runtime": 0.6454,
      "eval_samples_per_second": 2324.299,
      "eval_spearmanr": 0.11566450995412787,
      "eval_steps_per_second": 9.297,
      "step": 23
    },
    {
      "epoch": 2.0,
      "grad_norm": 9.577908515930176,
      "learning_rate": 4.8e-05,
      "loss": 1.9542,
      "step": 46
    },
    {
      "epoch": 2.0,
      "eval_combined_score": 0.16662698961381206,
      "eval_loss": 2.466871976852417,
      "eval_pearson": 0.17639717427505217,
      "eval_runtime": 0.6955,
      "eval_samples_per_second": 2156.59,
      "eval_spearmanr": 0.15685680495257198,
      "eval_steps_per_second": 8.626,
      "step": 46
    },
    {
      "epoch": 3.0,
      "grad_norm": 5.299047470092773,
      "learning_rate": 4.7e-05,
      "loss": 1.6966,
      "step": 69
    },
    {
      "epoch": 3.0,
      "eval_combined_score": 0.2672288404727735,
      "eval_loss": 2.2146897315979004,
      "eval_pearson": 0.2748382674330702,
      "eval_runtime": 0.7149,
      "eval_samples_per_second": 2098.166,
      "eval_spearmanr": 0.25961941351247675,
      "eval_steps_per_second": 8.393,
      "step": 69
    },
    {
      "epoch": 4.0,
      "grad_norm": 7.806900978088379,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.4275,
      "step": 92
    },
    {
      "epoch": 4.0,
      "eval_combined_score": 0.2591766229236492,
      "eval_loss": 2.387739658355713,
      "eval_pearson": 0.2651861237142098,
      "eval_runtime": 0.6162,
      "eval_samples_per_second": 2434.375,
      "eval_spearmanr": 0.2531671221330886,
      "eval_steps_per_second": 9.738,
      "step": 92
    },
    {
      "epoch": 5.0,
      "grad_norm": 13.103901863098145,
      "learning_rate": 4.5e-05,
      "loss": 1.0925,
      "step": 115
    },
    {
      "epoch": 5.0,
      "eval_combined_score": 0.3001932315838545,
      "eval_loss": 2.5098586082458496,
      "eval_pearson": 0.30425697861957673,
      "eval_runtime": 0.6338,
      "eval_samples_per_second": 2366.576,
      "eval_spearmanr": 0.2961294845481323,
      "eval_steps_per_second": 9.466,
      "step": 115
    },
    {
      "epoch": 6.0,
      "grad_norm": 13.206256866455078,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.8164,
      "step": 138
    },
    {
      "epoch": 6.0,
      "eval_combined_score": 0.32158630845141123,
      "eval_loss": 2.48075008392334,
      "eval_pearson": 0.3245658724722176,
      "eval_runtime": 0.676,
      "eval_samples_per_second": 2218.819,
      "eval_spearmanr": 0.3186067444306048,
      "eval_steps_per_second": 8.875,
      "step": 138
    },
    {
      "epoch": 7.0,
      "grad_norm": 8.210938453674316,
      "learning_rate": 4.3e-05,
      "loss": 0.6226,
      "step": 161
    },
    {
      "epoch": 7.0,
      "eval_combined_score": 0.33364485043499603,
      "eval_loss": 2.448601245880127,
      "eval_pearson": 0.33487429814507286,
      "eval_runtime": 0.6134,
      "eval_samples_per_second": 2445.399,
      "eval_spearmanr": 0.33241540272491915,
      "eval_steps_per_second": 9.782,
      "step": 161
    },
    {
      "epoch": 8.0,
      "grad_norm": 18.73587989807129,
      "learning_rate": 4.2e-05,
      "loss": 0.5022,
      "step": 184
    },
    {
      "epoch": 8.0,
      "eval_combined_score": 0.30731098603290685,
      "eval_loss": 2.527529239654541,
      "eval_pearson": 0.31154148966746664,
      "eval_runtime": 0.6317,
      "eval_samples_per_second": 2374.364,
      "eval_spearmanr": 0.30308048239834706,
      "eval_steps_per_second": 9.497,
      "step": 184
    },
    {
      "epoch": 8.0,
      "step": 184,
      "total_flos": 3046165974478848.0,
      "train_loss": 1.3917618316152822,
      "train_runtime": 59.1028,
      "train_samples_per_second": 4863.558,
      "train_steps_per_second": 19.458
    }
  ],
  "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": 3046165974478848.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}