{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0935672514619883,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01871345029239766,
      "grad_norm": 0.5666236877441406,
      "learning_rate": 1e-05,
      "loss": 2.094,
      "step": 1
    },
    {
      "epoch": 0.01871345029239766,
      "eval_loss": 2.005998134613037,
      "eval_runtime": 50.6452,
      "eval_samples_per_second": 1.777,
      "eval_steps_per_second": 0.889,
      "step": 1
    },
    {
      "epoch": 0.03742690058479532,
      "grad_norm": 0.5438487529754639,
      "learning_rate": 2e-05,
      "loss": 1.9818,
      "step": 2
    },
    {
      "epoch": 0.03742690058479532,
      "eval_loss": 1.996207356452942,
      "eval_runtime": 3.2973,
      "eval_samples_per_second": 27.295,
      "eval_steps_per_second": 13.648,
      "step": 2
    },
    {
      "epoch": 0.056140350877192984,
      "grad_norm": 0.6570996046066284,
      "learning_rate": 3e-05,
      "loss": 2.1616,
      "step": 3
    },
    {
      "epoch": 0.07485380116959064,
      "grad_norm": 0.645438551902771,
      "learning_rate": 4e-05,
      "loss": 2.0944,
      "step": 4
    },
    {
      "epoch": 0.07485380116959064,
      "eval_loss": 1.9838075637817383,
      "eval_runtime": 3.2912,
      "eval_samples_per_second": 27.345,
      "eval_steps_per_second": 13.673,
      "step": 4
    },
    {
      "epoch": 0.0935672514619883,
      "grad_norm": 0.5524792671203613,
      "learning_rate": 5e-05,
      "loss": 1.8504,
      "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": 902045682892800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}