{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08686210640608034,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01737242128121607,
      "grad_norm": 1.0366835594177246,
      "learning_rate": 1e-05,
      "loss": 14.6039,
      "step": 1
    },
    {
      "epoch": 0.01737242128121607,
      "eval_loss": 1.145350694656372,
      "eval_runtime": 33.6949,
      "eval_samples_per_second": 2.879,
      "eval_steps_per_second": 1.454,
      "step": 1
    },
    {
      "epoch": 0.03474484256243214,
      "grad_norm": 1.0584312677383423,
      "learning_rate": 2e-05,
      "loss": 15.2176,
      "step": 2
    },
    {
      "epoch": 0.03474484256243214,
      "eval_loss": 1.1441892385482788,
      "eval_runtime": 4.8866,
      "eval_samples_per_second": 19.85,
      "eval_steps_per_second": 10.027,
      "step": 2
    },
    {
      "epoch": 0.05211726384364821,
      "grad_norm": 1.145268201828003,
      "learning_rate": 3e-05,
      "loss": 15.4215,
      "step": 3
    },
    {
      "epoch": 0.06948968512486428,
      "grad_norm": 1.080140471458435,
      "learning_rate": 4e-05,
      "loss": 14.0206,
      "step": 4
    },
    {
      "epoch": 0.06948968512486428,
      "eval_loss": 1.1434835195541382,
      "eval_runtime": 4.9004,
      "eval_samples_per_second": 19.794,
      "eval_steps_per_second": 9.999,
      "step": 4
    },
    {
      "epoch": 0.08686210640608034,
      "grad_norm": 2.2628250122070312,
      "learning_rate": 5e-05,
      "loss": 17.5337,
      "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": 6433559506059264.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}