{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0030670142616163166,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006134028523232633,
      "grad_norm": 0.045473504811525345,
      "learning_rate": 1e-05,
      "loss": 10.3677,
      "step": 1
    },
    {
      "epoch": 0.0006134028523232633,
      "eval_loss": 10.366973876953125,
      "eval_runtime": 20.3836,
      "eval_samples_per_second": 134.716,
      "eval_steps_per_second": 67.358,
      "step": 1
    },
    {
      "epoch": 0.0012268057046465265,
      "grad_norm": 0.057000406086444855,
      "learning_rate": 2e-05,
      "loss": 10.3709,
      "step": 2
    },
    {
      "epoch": 0.0012268057046465265,
      "eval_loss": 10.366968154907227,
      "eval_runtime": 10.4037,
      "eval_samples_per_second": 263.945,
      "eval_steps_per_second": 131.973,
      "step": 2
    },
    {
      "epoch": 0.0018402085569697898,
      "grad_norm": 0.035671766847372055,
      "learning_rate": 3e-05,
      "loss": 10.3714,
      "step": 3
    },
    {
      "epoch": 0.002453611409293053,
      "grad_norm": 0.05280758813023567,
      "learning_rate": 4e-05,
      "loss": 10.3635,
      "step": 4
    },
    {
      "epoch": 0.002453611409293053,
      "eval_loss": 10.36693286895752,
      "eval_runtime": 10.8124,
      "eval_samples_per_second": 253.967,
      "eval_steps_per_second": 126.983,
      "step": 4
    },
    {
      "epoch": 0.0030670142616163166,
      "grad_norm": 0.04339885339140892,
      "learning_rate": 5e-05,
      "loss": 10.3733,
      "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": 258618163200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}