{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.003955011741441108,
  "eval_steps": 2,
  "global_step": 4,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000988752935360277,
      "grad_norm": 4.214609622955322,
      "learning_rate": 1e-05,
      "loss": 6.0793,
      "step": 1
    },
    {
      "epoch": 0.000988752935360277,
      "eval_loss": 5.788064956665039,
      "eval_runtime": 29.4768,
      "eval_samples_per_second": 57.808,
      "eval_steps_per_second": 28.904,
      "step": 1
    },
    {
      "epoch": 0.001977505870720554,
      "grad_norm": 3.2356998920440674,
      "learning_rate": 2e-05,
      "loss": 5.7093,
      "step": 2
    },
    {
      "epoch": 0.001977505870720554,
      "eval_loss": 5.781150817871094,
      "eval_runtime": 9.3481,
      "eval_samples_per_second": 182.283,
      "eval_steps_per_second": 91.141,
      "step": 2
    },
    {
      "epoch": 0.0029662588060808304,
      "grad_norm": 3.6650373935699463,
      "learning_rate": 3e-05,
      "loss": 5.992,
      "step": 3
    },
    {
      "epoch": 0.003955011741441108,
      "grad_norm": 3.548612594604492,
      "learning_rate": 4e-05,
      "loss": 5.7213,
      "step": 4
    },
    {
      "epoch": 0.003955011741441108,
      "eval_loss": 5.765260696411133,
      "eval_runtime": 9.4261,
      "eval_samples_per_second": 180.775,
      "eval_steps_per_second": 90.387,
      "step": 4
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1048936710144.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}