{
  "best_metric": 0.6877643727244785,
  "best_model_checkpoint": "training_dir/checkpoint-4000",
  "epoch": 0.4238635159478648,
  "eval_steps": 1000,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.1059658789869662,
      "grad_norm": 15.513019561767578,
      "learning_rate": 9.946734846063707e-06,
      "loss": 0.8105,
      "step": 1000
    },
    {
      "epoch": 0.1059658789869662,
      "eval_accuracy": 0.6267482517482518,
      "eval_f1": 0.5486997676789124,
      "eval_loss": 0.8523119688034058,
      "eval_precision": 0.6663256334906192,
      "eval_recall": 0.6267482517482518,
      "eval_runtime": 26.6488,
      "eval_samples_per_second": 85.857,
      "eval_steps_per_second": 10.732,
      "step": 1000
    },
    {
      "epoch": 0.2119317579739324,
      "grad_norm": 14.981549263000488,
      "learning_rate": 9.840204538191116e-06,
      "loss": 0.5828,
      "step": 2000
    },
    {
      "epoch": 0.2119317579739324,
      "eval_accuracy": 0.6682692307692307,
      "eval_f1": 0.6366336108184594,
      "eval_loss": 0.9371851086616516,
      "eval_precision": 0.6852715704153842,
      "eval_recall": 0.6682692307692307,
      "eval_runtime": 25.9805,
      "eval_samples_per_second": 88.066,
      "eval_steps_per_second": 11.008,
      "step": 2000
    },
    {
      "epoch": 0.31789763696089857,
      "grad_norm": 8.239383697509766,
      "learning_rate": 9.733674230318526e-06,
      "loss": 0.5349,
      "step": 3000
    },
    {
      "epoch": 0.31789763696089857,
      "eval_accuracy": 0.6914335664335665,
      "eval_f1": 0.669233772837662,
      "eval_loss": 0.8858013153076172,
      "eval_precision": 0.6967032053774095,
      "eval_recall": 0.6914335664335665,
      "eval_runtime": 25.9486,
      "eval_samples_per_second": 88.174,
      "eval_steps_per_second": 11.022,
      "step": 3000
    },
    {
      "epoch": 0.4238635159478648,
      "grad_norm": 9.338201522827148,
      "learning_rate": 9.627143922445936e-06,
      "loss": 0.5233,
      "step": 4000
    },
    {
      "epoch": 0.4238635159478648,
      "eval_accuracy": 0.7023601398601399,
      "eval_f1": 0.6877643727244785,
      "eval_loss": 0.9143859148025513,
      "eval_precision": 0.7132978004907108,
      "eval_recall": 0.7023601398601399,
      "eval_runtime": 26.1039,
      "eval_samples_per_second": 87.65,
      "eval_steps_per_second": 10.956,
      "step": 4000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 94370,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3879664659350064.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}