{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0010954671535409572,
  "eval_steps": 13,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.8088901372845056e-05,
      "eval_loss": 0.7164075374603271,
      "eval_runtime": 959.5944,
      "eval_samples_per_second": 15.621,
      "eval_steps_per_second": 7.811,
      "step": 1
    },
    {
      "epoch": 0.00028088901372845055,
      "grad_norm": 0.7765677571296692,
      "learning_rate": 0.00019396926207859084,
      "loss": 0.5808,
      "step": 10
    },
    {
      "epoch": 0.0003651557178469857,
      "eval_loss": 0.4477108120918274,
      "eval_runtime": 958.6635,
      "eval_samples_per_second": 15.636,
      "eval_steps_per_second": 7.818,
      "step": 13
    },
    {
      "epoch": 0.0005617780274569011,
      "grad_norm": 0.3594229519367218,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.3801,
      "step": 20
    },
    {
      "epoch": 0.0007303114356939714,
      "eval_loss": 0.38734641671180725,
      "eval_runtime": 957.8246,
      "eval_samples_per_second": 15.65,
      "eval_steps_per_second": 7.825,
      "step": 26
    },
    {
      "epoch": 0.0008426670411853516,
      "grad_norm": 0.38002777099609375,
      "learning_rate": 8.263518223330697e-05,
      "loss": 0.3478,
      "step": 30
    },
    {
      "epoch": 0.0010954671535409572,
      "eval_loss": 0.3715435862541199,
      "eval_runtime": 958.5409,
      "eval_samples_per_second": 15.638,
      "eval_steps_per_second": 7.819,
      "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": 1.394040587157504e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}