{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0035,
  "eval_steps": 500,
  "global_step": 3500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005,
      "grad_norm": 0.6503494381904602,
      "learning_rate": 5.654048189192757e-05,
      "loss": 9.2102,
      "num_input_tokens_seen": 249169792,
      "step": 500
    },
    {
      "epoch": 0.001,
      "grad_norm": 0.5827581882476807,
      "learning_rate": 5.651219750879004e-05,
      "loss": 7.7872,
      "num_input_tokens_seen": 497906688,
      "step": 1000
    },
    {
      "epoch": 0.0015,
      "grad_norm": 0.43762627243995667,
      "learning_rate": 5.6483913125652505e-05,
      "loss": 7.0276,
      "num_input_tokens_seen": 746696384,
      "step": 1500
    },
    {
      "epoch": 0.002,
      "grad_norm": 0.47100603580474854,
      "learning_rate": 5.645562874251497e-05,
      "loss": 6.5612,
      "num_input_tokens_seen": 994790144,
      "step": 2000
    },
    {
      "epoch": 0.0025,
      "grad_norm": 0.4795113205909729,
      "learning_rate": 5.642734435937744e-05,
      "loss": 6.2086,
      "num_input_tokens_seen": 1243917376,
      "step": 2500
    },
    {
      "epoch": 0.003,
      "grad_norm": 0.9179026484489441,
      "learning_rate": 5.63990599762399e-05,
      "loss": 5.9393,
      "num_input_tokens_seen": 1492823744,
      "step": 3000
    },
    {
      "epoch": 0.0035,
      "grad_norm": 1.1793241500854492,
      "learning_rate": 5.6370775593102374e-05,
      "loss": 5.728,
      "num_input_tokens_seen": 1742012864,
      "step": 3500
    }
  ],
  "logging_steps": 500,
  "max_steps": 1000000,
  "num_input_tokens_seen": 1742012864,
  "num_train_epochs": 9223372036854775807,
  "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": 2.689779350839296e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}