{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02442002442002442,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004884004884004884,
      "grad_norm": 0.006344179157167673,
      "learning_rate": 1e-05,
      "loss": 11.9332,
      "step": 1
    },
    {
      "epoch": 0.004884004884004884,
      "eval_loss": 11.934247970581055,
      "eval_runtime": 15.3823,
      "eval_samples_per_second": 22.428,
      "eval_steps_per_second": 11.247,
      "step": 1
    },
    {
      "epoch": 0.009768009768009768,
      "grad_norm": 0.007955477572977543,
      "learning_rate": 2e-05,
      "loss": 11.9346,
      "step": 2
    },
    {
      "epoch": 0.009768009768009768,
      "eval_loss": 11.934246063232422,
      "eval_runtime": 0.647,
      "eval_samples_per_second": 533.243,
      "eval_steps_per_second": 267.394,
      "step": 2
    },
    {
      "epoch": 0.014652014652014652,
      "grad_norm": 0.009232529439032078,
      "learning_rate": 3e-05,
      "loss": 11.9348,
      "step": 3
    },
    {
      "epoch": 0.019536019536019536,
      "grad_norm": 0.008595341816544533,
      "learning_rate": 4e-05,
      "loss": 11.9363,
      "step": 4
    },
    {
      "epoch": 0.019536019536019536,
      "eval_loss": 11.934242248535156,
      "eval_runtime": 0.6667,
      "eval_samples_per_second": 517.478,
      "eval_steps_per_second": 259.489,
      "step": 4
    },
    {
      "epoch": 0.02442002442002442,
      "grad_norm": 0.008456413634121418,
      "learning_rate": 5e-05,
      "loss": 11.9346,
      "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": 2363228160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}