{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006060606060606061,
  "eval_steps": 13,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001554001554001554,
      "eval_loss": 10.842114448547363,
      "eval_runtime": 8.0439,
      "eval_samples_per_second": 336.9,
      "eval_steps_per_second": 168.45,
      "step": 1
    },
    {
      "epoch": 0.001554001554001554,
      "grad_norm": 0.19285012781620026,
      "learning_rate": 0.00019396926207859084,
      "loss": 10.8416,
      "step": 10
    },
    {
      "epoch": 0.00202020202020202,
      "eval_loss": 10.830446243286133,
      "eval_runtime": 7.3453,
      "eval_samples_per_second": 368.944,
      "eval_steps_per_second": 184.472,
      "step": 13
    },
    {
      "epoch": 0.003108003108003108,
      "grad_norm": 0.30350035429000854,
      "learning_rate": 0.00015000000000000001,
      "loss": 10.8244,
      "step": 20
    },
    {
      "epoch": 0.00404040404040404,
      "eval_loss": 10.813182830810547,
      "eval_runtime": 7.4399,
      "eval_samples_per_second": 364.255,
      "eval_steps_per_second": 182.127,
      "step": 26
    },
    {
      "epoch": 0.004662004662004662,
      "grad_norm": 0.2962060272693634,
      "learning_rate": 8.263518223330697e-05,
      "loss": 10.8256,
      "step": 30
    },
    {
      "epoch": 0.006060606060606061,
      "eval_loss": 10.80303955078125,
      "eval_runtime": 7.4648,
      "eval_samples_per_second": 363.037,
      "eval_steps_per_second": 181.518,
      "step": 39
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4942281965568.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}