{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 868,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.11530700490054771,
      "grad_norm": 2.9323058128356934,
      "learning_rate": 4.9970880369844344e-05,
      "loss": 2.995,
      "step": 100
    },
    {
      "epoch": 0.23061400980109542,
      "grad_norm": 2.415233612060547,
      "learning_rate": 4.7505488501875907e-05,
      "loss": 2.809,
      "step": 200
    },
    {
      "epoch": 0.3459210147016431,
      "grad_norm": 1.7806472778320312,
      "learning_rate": 4.1447386246547995e-05,
      "loss": 2.7775,
      "step": 300
    },
    {
      "epoch": 0.46122801960219084,
      "grad_norm": 1.9444694519042969,
      "learning_rate": 3.27636713364243e-05,
      "loss": 2.7791,
      "step": 400
    },
    {
      "epoch": 0.5765350245027385,
      "grad_norm": 2.093379020690918,
      "learning_rate": 2.2840586632035014e-05,
      "loss": 2.7299,
      "step": 500
    },
    {
      "epoch": 0.6918420294032862,
      "grad_norm": 1.8663088083267212,
      "learning_rate": 1.3262224364443493e-05,
      "loss": 2.7359,
      "step": 600
    },
    {
      "epoch": 0.807149034303834,
      "grad_norm": 2.0475974082946777,
      "learning_rate": 5.557646282733725e-06,
      "loss": 2.7394,
      "step": 700
    },
    {
      "epoch": 0.9224560392043817,
      "grad_norm": 1.9257546663284302,
      "learning_rate": 9.56788706753814e-07,
      "loss": 2.7317,
      "step": 800
    }
  ],
  "logging_steps": 100,
  "max_steps": 868,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5361727389638400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}