{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00016918183663801854,
  "eval_steps": 8,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6918183663801855e-05,
      "eval_loss": 0.2189994901418686,
      "eval_runtime": 1263.3794,
      "eval_samples_per_second": 19.7,
      "eval_steps_per_second": 9.85,
      "step": 1
    },
    {
      "epoch": 5.075455099140556e-05,
      "grad_norm": 1.5588386058807373,
      "learning_rate": 6e-05,
      "loss": 0.1905,
      "step": 3
    },
    {
      "epoch": 0.00010150910198281112,
      "grad_norm": 0.6940944790840149,
      "learning_rate": 0.00012,
      "loss": 0.1677,
      "step": 6
    },
    {
      "epoch": 0.00013534546931041484,
      "eval_loss": 0.13315555453300476,
      "eval_runtime": 1263.5211,
      "eval_samples_per_second": 19.697,
      "eval_steps_per_second": 9.849,
      "step": 8
    },
    {
      "epoch": 0.0001522636529742167,
      "grad_norm": 0.9706745147705078,
      "learning_rate": 0.00018,
      "loss": 0.3327,
      "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": 733425250074624.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}