{
  "best_metric": 0.6229463219642639,
  "best_model_checkpoint": "bert_base_lda_100_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": 0.3839820325374603,
      "learning_rate": 0.00098,
      "loss": 1.6608,
      "step": 15
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6274126768112183,
      "eval_runtime": 0.3333,
      "eval_samples_per_second": 1224.147,
      "eval_steps_per_second": 6.001,
      "step": 15
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.8113455772399902,
      "learning_rate": 0.00096,
      "loss": 0.6437,
      "step": 30
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6229463219642639,
      "eval_runtime": 0.2779,
      "eval_samples_per_second": 1467.932,
      "eval_steps_per_second": 7.196,
      "step": 30
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.1818019151687622,
      "learning_rate": 0.00094,
      "loss": 0.6306,
      "step": 45
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6274126768112183,
      "eval_runtime": 0.2695,
      "eval_samples_per_second": 1513.829,
      "eval_steps_per_second": 7.421,
      "step": 45
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.0649493932724,
      "learning_rate": 0.00092,
      "loss": 0.637,
      "step": 60
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6244111061096191,
      "eval_runtime": 0.2681,
      "eval_samples_per_second": 1521.562,
      "eval_steps_per_second": 7.459,
      "step": 60
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.477798730134964,
      "learning_rate": 0.0009000000000000001,
      "loss": 0.6341,
      "step": 75
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6260770559310913,
      "eval_runtime": 0.2813,
      "eval_samples_per_second": 1450.245,
      "eval_steps_per_second": 7.109,
      "step": 75
    },
    {
      "epoch": 6.0,
      "grad_norm": 0.7583205699920654,
      "learning_rate": 0.00088,
      "loss": 0.6342,
      "step": 90
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6254164576530457,
      "eval_runtime": 0.27,
      "eval_samples_per_second": 1511.199,
      "eval_steps_per_second": 7.408,
      "step": 90
    },
    {
      "epoch": 7.0,
      "grad_norm": 0.5159490704536438,
      "learning_rate": 0.00086,
      "loss": 0.6328,
      "step": 105
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.6838235294117647,
      "eval_combined_score": 0.7480253018237863,
      "eval_f1": 0.8122270742358079,
      "eval_loss": 0.6252872347831726,
      "eval_runtime": 0.2806,
      "eval_samples_per_second": 1454.165,
      "eval_steps_per_second": 7.128,
      "step": 105
    },
    {
      "epoch": 7.0,
      "step": 105,
      "total_flos": 3377819728711680.0,
      "train_loss": 0.7818594705490839,
      "train_runtime": 61.1043,
      "train_samples_per_second": 3001.426,
      "train_steps_per_second": 12.274
    }
  ],
  "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
}