{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 252,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.12012012012012012,
      "grad_norm": 0.6892135739326477,
      "learning_rate": 9e-05,
      "loss": 0.7404771327972413,
      "step": 10
    },
    {
      "epoch": 0.24024024024024024,
      "grad_norm": 0.6579736471176147,
      "learning_rate": 9.965912123286424e-05,
      "loss": 0.6771039962768555,
      "step": 20
    },
    {
      "epoch": 0.36036036036036034,
      "grad_norm": 0.6196520328521729,
      "learning_rate": 9.84867408817022e-05,
      "loss": 0.5915464878082275,
      "step": 30
    },
    {
      "epoch": 0.4804804804804805,
      "grad_norm": 0.641204833984375,
      "learning_rate": 9.649837585596444e-05,
      "loss": 0.47760705947875975,
      "step": 40
    },
    {
      "epoch": 0.6006006006006006,
      "grad_norm": 0.7001290321350098,
      "learning_rate": 9.372748840448361e-05,
      "loss": 0.4462123394012451,
      "step": 50
    },
    {
      "epoch": 0.7207207207207207,
      "grad_norm": 0.8124980926513672,
      "learning_rate": 9.022070986717379e-05,
      "loss": 0.44390106201171875,
      "step": 60
    },
    {
      "epoch": 0.8408408408408409,
      "grad_norm": 0.7991748452186584,
      "learning_rate": 8.603705591494916e-05,
      "loss": 0.36723716259002687,
      "step": 70
    },
    {
      "epoch": 0.960960960960961,
      "grad_norm": 0.6478794813156128,
      "learning_rate": 8.124693337340092e-05,
      "loss": 0.35840682983398436,
      "step": 80
    },
    {
      "epoch": 1.072072072072072,
      "grad_norm": 0.6842944025993347,
      "learning_rate": 7.593095534442388e-05,
      "loss": 0.31162774562835693,
      "step": 90
    },
    {
      "epoch": 1.1921921921921923,
      "grad_norm": 0.8257659077644348,
      "learning_rate": 7.017858456614284e-05,
      "loss": 0.2912218332290649,
      "step": 100
    },
    {
      "epoch": 1.3123123123123124,
      "grad_norm": 1.2205647230148315,
      "learning_rate": 6.408662784207149e-05,
      "loss": 0.2723785638809204,
      "step": 110
    },
    {
      "epoch": 1.4324324324324325,
      "grad_norm": 0.6746923923492432,
      "learning_rate": 5.775760687679603e-05,
      "loss": 0.2832528352737427,
      "step": 120
    },
    {
      "epoch": 1.5525525525525525,
      "grad_norm": 0.7994391322135925,
      "learning_rate": 5.129803293543392e-05,
      "loss": 0.2766345262527466,
      "step": 130
    },
    {
      "epoch": 1.6726726726726726,
      "grad_norm": 1.2023299932479858,
      "learning_rate": 4.481661436267057e-05,
      "loss": 0.24401814937591554,
      "step": 140
    },
    {
      "epoch": 1.7927927927927927,
      "grad_norm": 0.793181836605072,
      "learning_rate": 3.842242712708444e-05,
      "loss": 0.2846501588821411,
      "step": 150
    },
    {
      "epoch": 1.9129129129129128,
      "grad_norm": 0.768040657043457,
      "learning_rate": 3.222307917871977e-05,
      "loss": 0.2684438467025757,
      "step": 160
    },
    {
      "epoch": 2.024024024024024,
      "grad_norm": 0.673546314239502,
      "learning_rate": 2.632289951198285e-05,
      "loss": 0.23772306442260743,
      "step": 170
    },
    {
      "epoch": 2.144144144144144,
      "grad_norm": 0.7624714374542236,
      "learning_rate": 2.0821182410171636e-05,
      "loss": 0.17041124105453492,
      "step": 180
    },
    {
      "epoch": 2.264264264264264,
      "grad_norm": 0.5443869829177856,
      "learning_rate": 1.5810516419294652e-05,
      "loss": 0.1947704553604126,
      "step": 190
    },
    {
      "epoch": 2.3843843843843846,
      "grad_norm": 1.2833149433135986,
      "learning_rate": 1.1375226172924341e-05,
      "loss": 0.19111917018890381,
      "step": 200
    },
    {
      "epoch": 2.5045045045045047,
      "grad_norm": 1.1426626443862915,
      "learning_rate": 7.589953290656532e-06,
      "loss": 0.20885732173919677,
      "step": 210
    },
    {
      "epoch": 2.6246246246246248,
      "grad_norm": 0.6546122431755066,
      "learning_rate": 4.5184002322740785e-06,
      "loss": 0.19033702611923217,
      "step": 220
    },
    {
      "epoch": 2.744744744744745,
      "grad_norm": 0.9988263249397278,
      "learning_rate": 2.212258247327059e-06,
      "loss": 0.13631391525268555,
      "step": 230
    },
    {
      "epoch": 2.864864864864865,
      "grad_norm": 1.021765112876892,
      "learning_rate": 7.103374616951042e-07,
      "loss": 0.20375282764434816,
      "step": 240
    },
    {
      "epoch": 2.984984984984985,
      "grad_norm": 0.867516815662384,
      "learning_rate": 3.791374092859679e-08,
      "loss": 0.18663368225097657,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 252,
  "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": 2.6648567674454016e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}