{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008506113769271665,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017012227538543328,
      "grad_norm": 0.11223402619361877,
      "learning_rate": 1e-05,
      "loss": 0.6312,
      "step": 1
    },
    {
      "epoch": 0.0017012227538543328,
      "eval_loss": 0.6858288645744324,
      "eval_runtime": 98.0975,
      "eval_samples_per_second": 10.092,
      "eval_steps_per_second": 5.046,
      "step": 1
    },
    {
      "epoch": 0.0034024455077086655,
      "grad_norm": 0.11157184839248657,
      "learning_rate": 2e-05,
      "loss": 0.6589,
      "step": 2
    },
    {
      "epoch": 0.0034024455077086655,
      "eval_loss": 0.684842050075531,
      "eval_runtime": 17.2457,
      "eval_samples_per_second": 57.406,
      "eval_steps_per_second": 28.703,
      "step": 2
    },
    {
      "epoch": 0.005103668261562998,
      "grad_norm": 0.11057083308696747,
      "learning_rate": 3e-05,
      "loss": 0.6654,
      "step": 3
    },
    {
      "epoch": 0.006804891015417331,
      "grad_norm": 0.11391165852546692,
      "learning_rate": 4e-05,
      "loss": 0.708,
      "step": 4
    },
    {
      "epoch": 0.006804891015417331,
      "eval_loss": 0.6835019588470459,
      "eval_runtime": 17.3697,
      "eval_samples_per_second": 56.996,
      "eval_steps_per_second": 28.498,
      "step": 4
    },
    {
      "epoch": 0.008506113769271665,
      "grad_norm": 0.10489768534898758,
      "learning_rate": 5e-05,
      "loss": 0.6557,
      "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": 1191796100038656.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}