{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.035555555555555556,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035555555555555557,
      "eval_loss": 4.701450824737549,
      "eval_runtime": 7.1119,
      "eval_samples_per_second": 16.732,
      "eval_steps_per_second": 8.437,
      "step": 1
    },
    {
      "epoch": 0.010666666666666666,
      "grad_norm": 8.527983665466309,
      "learning_rate": 6e-05,
      "loss": 4.5862,
      "step": 3
    },
    {
      "epoch": 0.021333333333333333,
      "grad_norm": 6.9240522384643555,
      "learning_rate": 0.00012,
      "loss": 3.9541,
      "step": 6
    },
    {
      "epoch": 0.028444444444444446,
      "eval_loss": 1.967842698097229,
      "eval_runtime": 7.0506,
      "eval_samples_per_second": 16.878,
      "eval_steps_per_second": 8.51,
      "step": 8
    },
    {
      "epoch": 0.032,
      "grad_norm": 4.608461856842041,
      "learning_rate": 0.00018,
      "loss": 2.5516,
      "step": 9
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1646346004070400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}