{
  "best_metric": 0.5939152240753174,
  "best_model_checkpoint": "add_BERT_no_pretrain_qqp/checkpoint-11372",
  "epoch": 9.0,
  "global_step": 25587,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 3.9200000000000004e-05,
      "loss": 0.657,
      "step": 2843
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6490477368290873,
      "eval_combined_score": 0.4049047757310398,
      "eval_f1": 0.16076181463299224,
      "eval_loss": 0.6437851786613464,
      "eval_runtime": 75.6371,
      "eval_samples_per_second": 534.526,
      "eval_steps_per_second": 4.178,
      "step": 2843
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.8400000000000005e-05,
      "loss": 0.6273,
      "step": 5686
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6442987880286916,
      "eval_combined_score": 0.4180752158744188,
      "eval_f1": 0.1918516437201461,
      "eval_loss": 0.6302036643028259,
      "eval_runtime": 75.8685,
      "eval_samples_per_second": 532.896,
      "eval_steps_per_second": 4.165,
      "step": 5686
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.76e-05,
      "loss": 0.6273,
      "step": 8529
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6526589166460549,
      "eval_combined_score": 0.5064287794766108,
      "eval_f1": 0.36019864230716664,
      "eval_loss": 0.6264548897743225,
      "eval_runtime": 75.7943,
      "eval_samples_per_second": 533.417,
      "eval_steps_per_second": 4.169,
      "step": 8529
    },
    {
      "epoch": 4.0,
      "learning_rate": 3.680000000000001e-05,
      "loss": 0.6093,
      "step": 11372
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6823893148651992,
      "eval_combined_score": 0.5764208523272344,
      "eval_f1": 0.4704523897892697,
      "eval_loss": 0.5939152240753174,
      "eval_runtime": 75.7663,
      "eval_samples_per_second": 533.615,
      "eval_steps_per_second": 4.171,
      "step": 11372
    },
    {
      "epoch": 5.0,
      "learning_rate": 3.6e-05,
      "loss": 0.5932,
      "step": 14215
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.680187979223349,
      "eval_combined_score": 0.5486151798731713,
      "eval_f1": 0.41704238052299364,
      "eval_loss": 0.5961658358573914,
      "eval_runtime": 75.7813,
      "eval_samples_per_second": 533.509,
      "eval_steps_per_second": 4.17,
      "step": 14215
    },
    {
      "epoch": 6.0,
      "learning_rate": 3.52e-05,
      "loss": 0.599,
      "step": 17058
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.675735839722978,
      "eval_combined_score": 0.5776042813321474,
      "eval_f1": 0.4794727229413166,
      "eval_loss": 0.5981380343437195,
      "eval_runtime": 75.8673,
      "eval_samples_per_second": 532.904,
      "eval_steps_per_second": 4.165,
      "step": 17058
    },
    {
      "epoch": 7.0,
      "learning_rate": 3.44e-05,
      "loss": 0.6063,
      "step": 19901
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6318327974276527,
      "eval_combined_score": 0.3159163987138264,
      "eval_f1": 0.0,
      "eval_loss": 0.6510685086250305,
      "eval_runtime": 75.7196,
      "eval_samples_per_second": 533.944,
      "eval_steps_per_second": 4.173,
      "step": 19901
    },
    {
      "epoch": 8.0,
      "learning_rate": 3.3600000000000004e-05,
      "loss": 0.6264,
      "step": 22744
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.6531783329210982,
      "eval_combined_score": 0.4303083615769859,
      "eval_f1": 0.2074383902328736,
      "eval_loss": 0.6261195540428162,
      "eval_runtime": 75.7764,
      "eval_samples_per_second": 533.543,
      "eval_steps_per_second": 4.17,
      "step": 22744
    },
    {
      "epoch": 9.0,
      "learning_rate": 3.28e-05,
      "loss": 0.6348,
      "step": 25587
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.6318327974276527,
      "eval_combined_score": 0.3159163987138264,
      "eval_f1": 0.0,
      "eval_loss": 0.6774410605430603,
      "eval_runtime": 75.9165,
      "eval_samples_per_second": 532.559,
      "eval_steps_per_second": 4.162,
      "step": 25587
    },
    {
      "epoch": 9.0,
      "step": 25587,
      "total_flos": 4.676933727069143e+17,
      "train_loss": 0.6200644320571725,
      "train_runtime": 19316.7897,
      "train_samples_per_second": 941.787,
      "train_steps_per_second": 7.359
    }
  ],
  "max_steps": 142150,
  "num_train_epochs": 50,
  "total_flos": 4.676933727069143e+17,
  "trial_name": null,
  "trial_params": null
}