{
  "best_metric": 0.6033744215965271,
  "best_model_checkpoint": "bert_base_lda_50_v1_mrpc/checkpoint-30",
  "epoch": 7.0,
  "eval_steps": 500,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 0.8829944133758545,
      "learning_rate": 4.9e-05,
      "loss": 0.669,
      "step": 15
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6813725490196079,
      "eval_combined_score": 0.744247105370338,
      "eval_f1": 0.8071216617210681,
      "eval_loss": 0.6216921210289001,
      "eval_runtime": 0.273,
      "eval_samples_per_second": 1494.435,
      "eval_steps_per_second": 7.326,
      "step": 15
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.7580305337905884,
      "learning_rate": 4.8e-05,
      "loss": 0.6174,
      "step": 30
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6936274509803921,
      "eval_combined_score": 0.7511016274810076,
      "eval_f1": 0.8085758039816232,
      "eval_loss": 0.6033744215965271,
      "eval_runtime": 0.2839,
      "eval_samples_per_second": 1437.191,
      "eval_steps_per_second": 7.045,
      "step": 30
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.2845402956008911,
      "learning_rate": 4.7e-05,
      "loss": 0.5792,
      "step": 45
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7009803921568627,
      "eval_combined_score": 0.7594454199590284,
      "eval_f1": 0.817910447761194,
      "eval_loss": 0.6052736639976501,
      "eval_runtime": 0.2747,
      "eval_samples_per_second": 1485.166,
      "eval_steps_per_second": 7.28,
      "step": 45
    },
    {
      "epoch": 4.0,
      "grad_norm": 2.5384278297424316,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.5085,
      "step": 60
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6740196078431373,
      "eval_combined_score": 0.7140892863614947,
      "eval_f1": 0.7541589648798522,
      "eval_loss": 0.6419196128845215,
      "eval_runtime": 0.2836,
      "eval_samples_per_second": 1438.409,
      "eval_steps_per_second": 7.051,
      "step": 60
    },
    {
      "epoch": 5.0,
      "grad_norm": 5.037930488586426,
      "learning_rate": 4.5e-05,
      "loss": 0.373,
      "step": 75
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7083333333333334,
      "eval_combined_score": 0.7592703349282297,
      "eval_f1": 0.810207336523126,
      "eval_loss": 0.749921441078186,
      "eval_runtime": 0.2767,
      "eval_samples_per_second": 1474.352,
      "eval_steps_per_second": 7.227,
      "step": 75
    },
    {
      "epoch": 6.0,
      "grad_norm": 6.258988857269287,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.2611,
      "step": 90
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6495098039215687,
      "eval_combined_score": 0.6911100421477001,
      "eval_f1": 0.7327102803738317,
      "eval_loss": 0.907718300819397,
      "eval_runtime": 0.2843,
      "eval_samples_per_second": 1434.985,
      "eval_steps_per_second": 7.034,
      "step": 90
    },
    {
      "epoch": 7.0,
      "grad_norm": 10.116829872131348,
      "learning_rate": 4.3e-05,
      "loss": 0.1835,
      "step": 105
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.696078431372549,
      "eval_combined_score": 0.7429544699235626,
      "eval_f1": 0.7898305084745764,
      "eval_loss": 1.00290048122406,
      "eval_runtime": 0.281,
      "eval_samples_per_second": 1451.74,
      "eval_steps_per_second": 7.116,
      "step": 105
    },
    {
      "epoch": 7.0,
      "step": 105,
      "total_flos": 3377819728711680.0,
      "train_loss": 0.4559453896113804,
      "train_runtime": 63.2715,
      "train_samples_per_second": 2898.617,
      "train_steps_per_second": 11.854
    }
  ],
  "logging_steps": 1,
  "max_steps": 750,
  "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": 3377819728711680.0,
  "train_batch_size": 256,
  "trial_name": null,
  "trial_params": null
}