{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.009256045354622237,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0018512090709244474,
      "grad_norm": 1.2806000709533691,
      "learning_rate": 1e-05,
      "loss": 5.3029,
      "step": 1
    },
    {
      "epoch": 0.0018512090709244474,
      "eval_loss": 5.603797435760498,
      "eval_runtime": 20.6644,
      "eval_samples_per_second": 44.037,
      "eval_steps_per_second": 22.019,
      "step": 1
    },
    {
      "epoch": 0.003702418141848895,
      "grad_norm": 1.1993850469589233,
      "learning_rate": 2e-05,
      "loss": 5.3121,
      "step": 2
    },
    {
      "epoch": 0.003702418141848895,
      "eval_loss": 5.593379020690918,
      "eval_runtime": 3.0391,
      "eval_samples_per_second": 299.43,
      "eval_steps_per_second": 149.715,
      "step": 2
    },
    {
      "epoch": 0.0055536272127733426,
      "grad_norm": 1.1811679601669312,
      "learning_rate": 3e-05,
      "loss": 5.3755,
      "step": 3
    },
    {
      "epoch": 0.00740483628369779,
      "grad_norm": 1.2150002717971802,
      "learning_rate": 4e-05,
      "loss": 5.3087,
      "step": 4
    },
    {
      "epoch": 0.00740483628369779,
      "eval_loss": 5.5793657302856445,
      "eval_runtime": 3.0683,
      "eval_samples_per_second": 296.583,
      "eval_steps_per_second": 148.292,
      "step": 4
    },
    {
      "epoch": 0.009256045354622237,
      "grad_norm": 1.267248272895813,
      "learning_rate": 5e-05,
      "loss": 5.576,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 68585300951040.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}