{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.960573476702509,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.7921146953405018,
      "grad_norm": 0.5550134778022766,
      "learning_rate": 4.1039426523297493e-05,
      "loss": 1.0898,
      "step": 500
    },
    {
      "epoch": 3.5842293906810037,
      "grad_norm": 0.8247848153114319,
      "learning_rate": 3.207885304659498e-05,
      "loss": 0.866,
      "step": 1000
    },
    {
      "epoch": 5.376344086021505,
      "grad_norm": 0.9447944164276123,
      "learning_rate": 2.3118279569892472e-05,
      "loss": 0.7996,
      "step": 1500
    },
    {
      "epoch": 7.168458781362007,
      "grad_norm": 1.0575640201568604,
      "learning_rate": 1.4157706093189965e-05,
      "loss": 0.7605,
      "step": 2000
    },
    {
      "epoch": 8.960573476702509,
      "grad_norm": 1.0388325452804565,
      "learning_rate": 5.197132616487455e-06,
      "loss": 0.732,
      "step": 2500
    }
  ],
  "logging_steps": 500,
  "max_steps": 2790,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.255837538690007e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}