{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.736842105263158,
  "eval_steps": 500,
  "global_step": 27,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 66.12335205078125,
      "learning_rate": 0.0003,
      "loss": 59.5188,
      "step": 1
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 33.92839813232422,
      "learning_rate": 0.0003,
      "loss": 37.4425,
      "step": 2
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 35.69908142089844,
      "learning_rate": 0.0003,
      "loss": 36.1151,
      "step": 3
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 25.477380752563477,
      "learning_rate": 0.0003,
      "loss": 21.9265,
      "step": 4
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 16.33018684387207,
      "learning_rate": 0.0003,
      "loss": 12.2597,
      "step": 5
    },
    {
      "epoch": 0.631578947368421,
      "grad_norm": 15.017313003540039,
      "learning_rate": 0.0003,
      "loss": 22.3761,
      "step": 6
    },
    {
      "epoch": 0.7368421052631579,
      "grad_norm": 10.749319076538086,
      "learning_rate": 0.0003,
      "loss": 17.3981,
      "step": 7
    },
    {
      "epoch": 0.8421052631578947,
      "grad_norm": 13.155961990356445,
      "learning_rate": 0.0003,
      "loss": 13.3434,
      "step": 8
    },
    {
      "epoch": 0.9473684210526315,
      "grad_norm": 8.230867385864258,
      "learning_rate": 0.0003,
      "loss": 13.3483,
      "step": 9
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.354396343231201,
      "learning_rate": 0.0003,
      "loss": 4.7253,
      "step": 10
    },
    {
      "epoch": 1.1052631578947367,
      "grad_norm": 9.160544395446777,
      "learning_rate": 0.0003,
      "loss": 17.143,
      "step": 11
    },
    {
      "epoch": 1.2105263157894737,
      "grad_norm": 7.405826091766357,
      "learning_rate": 0.0003,
      "loss": 7.7178,
      "step": 12
    },
    {
      "epoch": 1.3157894736842106,
      "grad_norm": 7.390495300292969,
      "learning_rate": 0.0003,
      "loss": 13.0078,
      "step": 13
    },
    {
      "epoch": 1.4210526315789473,
      "grad_norm": 8.60974407196045,
      "learning_rate": 0.0003,
      "loss": 13.1604,
      "step": 14
    },
    {
      "epoch": 1.526315789473684,
      "grad_norm": 8.34291934967041,
      "learning_rate": 0.0003,
      "loss": 18.2026,
      "step": 15
    },
    {
      "epoch": 1.631578947368421,
      "grad_norm": 8.343440055847168,
      "learning_rate": 0.0003,
      "loss": 10.0839,
      "step": 16
    },
    {
      "epoch": 1.736842105263158,
      "grad_norm": 6.996681213378906,
      "learning_rate": 0.0003,
      "loss": 7.4676,
      "step": 17
    },
    {
      "epoch": 1.8421052631578947,
      "grad_norm": 10.558813095092773,
      "learning_rate": 0.0003,
      "loss": 15.411,
      "step": 18
    },
    {
      "epoch": 1.9473684210526314,
      "grad_norm": 7.464992523193359,
      "learning_rate": 0.0003,
      "loss": 17.2385,
      "step": 19
    },
    {
      "epoch": 2.0,
      "grad_norm": 6.329394340515137,
      "learning_rate": 0.0003,
      "loss": 4.0205,
      "step": 20
    },
    {
      "epoch": 2.1052631578947367,
      "grad_norm": 12.035591125488281,
      "learning_rate": 0.0003,
      "loss": 14.0934,
      "step": 21
    },
    {
      "epoch": 2.2105263157894735,
      "grad_norm": 5.28068208694458,
      "learning_rate": 0.0003,
      "loss": 10.9242,
      "step": 22
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 8.603231430053711,
      "learning_rate": 0.0003,
      "loss": 10.8002,
      "step": 23
    },
    {
      "epoch": 2.4210526315789473,
      "grad_norm": 7.561744213104248,
      "learning_rate": 0.0003,
      "loss": 8.6784,
      "step": 24
    },
    {
      "epoch": 2.526315789473684,
      "grad_norm": 5.634705066680908,
      "learning_rate": 0.0003,
      "loss": 10.7642,
      "step": 25
    },
    {
      "epoch": 2.6315789473684212,
      "grad_norm": 6.18800687789917,
      "learning_rate": 0.0003,
      "loss": 8.0818,
      "step": 26
    },
    {
      "epoch": 2.736842105263158,
      "grad_norm": 5.977385997772217,
      "learning_rate": 0.0003,
      "loss": 10.3816,
      "step": 27
    },
    {
      "epoch": 2.736842105263158,
      "step": 27,
      "total_flos": 0.0,
      "train_loss": 16.134476679342765,
      "train_runtime": 122.1313,
      "train_samples_per_second": 7.369,
      "train_steps_per_second": 0.221
    }
  ],
  "logging_steps": 1,
  "max_steps": 27,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}