{
  "best_metric": 0.3558782637119293,
  "best_model_checkpoint": "output_pipe/H3/origin/checkpoint-200",
  "epoch": 4.0,
  "eval_steps": 200,
  "global_step": 752,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5319148936170213,
      "grad_norm": 4.111964225769043,
      "learning_rate": 2.786324786324786e-05,
      "loss": 0.4901,
      "step": 100
    },
    {
      "epoch": 1.0638297872340425,
      "grad_norm": 5.464111804962158,
      "learning_rate": 2.358974358974359e-05,
      "loss": 0.3282,
      "step": 200
    },
    {
      "epoch": 1.0638297872340425,
      "eval_accuracy": 0.8657314629258517,
      "eval_f1": 0.8657120478782159,
      "eval_loss": 0.3558782637119293,
      "eval_matthews_correlation": 0.7314866960585986,
      "eval_precision": 0.8656904639506491,
      "eval_recall": 0.8657962397557448,
      "eval_runtime": 0.9151,
      "eval_samples_per_second": 1635.904,
      "eval_steps_per_second": 26.227,
      "step": 200
    },
    {
      "epoch": 1.5957446808510638,
      "grad_norm": 3.8978500366210938,
      "learning_rate": 1.9316239316239317e-05,
      "loss": 0.2287,
      "step": 300
    },
    {
      "epoch": 2.127659574468085,
      "grad_norm": 4.608195781707764,
      "learning_rate": 1.5042735042735045e-05,
      "loss": 0.1864,
      "step": 400
    },
    {
      "epoch": 2.127659574468085,
      "eval_accuracy": 0.8857715430861723,
      "eval_f1": 0.8857707275301618,
      "eval_loss": 0.3828310966491699,
      "eval_matthews_correlation": 0.7719597395149407,
      "eval_precision": 0.8859481721359178,
      "eval_recall": 0.8860115699823237,
      "eval_runtime": 0.9136,
      "eval_samples_per_second": 1638.577,
      "eval_steps_per_second": 26.27,
      "step": 400
    },
    {
      "epoch": 2.6595744680851063,
      "grad_norm": 5.584474563598633,
      "learning_rate": 1.076923076923077e-05,
      "loss": 0.0894,
      "step": 500
    },
    {
      "epoch": 3.1914893617021276,
      "grad_norm": 0.09788764268159866,
      "learning_rate": 6.4957264957264955e-06,
      "loss": 0.0693,
      "step": 600
    },
    {
      "epoch": 3.1914893617021276,
      "eval_accuracy": 0.8851035404141616,
      "eval_f1": 0.8850973364130648,
      "eval_loss": 0.49768728017807007,
      "eval_matthews_correlation": 0.7713361532420879,
      "eval_precision": 0.8858120760758471,
      "eval_recall": 0.8855241309122075,
      "eval_runtime": 0.913,
      "eval_samples_per_second": 1639.667,
      "eval_steps_per_second": 26.287,
      "step": 600
    },
    {
      "epoch": 3.723404255319149,
      "grad_norm": 0.34859994053840637,
      "learning_rate": 2.222222222222222e-06,
      "loss": 0.0325,
      "step": 700
    },
    {
      "epoch": 4.0,
      "step": 752,
      "total_flos": 1.219355426831076e+16,
      "train_loss": 0.19133086613518127,
      "train_runtime": 115.1289,
      "train_samples_per_second": 415.917,
      "train_steps_per_second": 6.532
    }
  ],
  "logging_steps": 100,
  "max_steps": 752,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.219355426831076e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}