{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.29985811130379947,
  "eval_steps": 500,
  "global_step": 3804,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03941352672237112,
      "grad_norm": 9.434146881103516,
      "learning_rate": 1.9840000000000003e-05,
      "loss": 3.5972,
      "step": 500
    },
    {
      "epoch": 0.07882705344474224,
      "grad_norm": 8.484919548034668,
      "learning_rate": 1.973587517972203e-05,
      "loss": 3.0731,
      "step": 1000
    },
    {
      "epoch": 0.11824058016711335,
      "grad_norm": 8.578750610351562,
      "learning_rate": 1.9469620320570853e-05,
      "loss": 2.9624,
      "step": 1500
    },
    {
      "epoch": 0.15765410688948447,
      "grad_norm": 6.2477827072143555,
      "learning_rate": 1.920336546141967e-05,
      "loss": 2.8351,
      "step": 2000
    },
    {
      "epoch": 0.19706763361185559,
      "grad_norm": 6.6669602394104,
      "learning_rate": 1.8937110602268492e-05,
      "loss": 2.817,
      "step": 2500
    },
    {
      "epoch": 0.2364811603342267,
      "grad_norm": 4.857083797454834,
      "learning_rate": 1.8670855743117314e-05,
      "loss": 2.7781,
      "step": 3000
    },
    {
      "epoch": 0.2758946870565978,
      "grad_norm": 5.961228847503662,
      "learning_rate": 1.8404600883966135e-05,
      "loss": 2.7681,
      "step": 3500
    }
  ],
  "logging_steps": 500,
  "max_steps": 38058,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1268,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 993954889728000.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}