{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9189065012634965,
  "eval_steps": 500,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.036756260050539856,
      "grad_norm": 1.0688965320587158,
      "learning_rate": 1.0975609756097562e-05,
      "loss": 1.1745,
      "step": 10
    },
    {
      "epoch": 0.07351252010107971,
      "grad_norm": 0.6050378084182739,
      "learning_rate": 2.3170731707317075e-05,
      "loss": 0.9615,
      "step": 20
    },
    {
      "epoch": 0.11026878015161957,
      "grad_norm": 0.5260648727416992,
      "learning_rate": 3.5365853658536584e-05,
      "loss": 0.9305,
      "step": 30
    },
    {
      "epoch": 0.14702504020215942,
      "grad_norm": 0.4684043824672699,
      "learning_rate": 4.75609756097561e-05,
      "loss": 0.8995,
      "step": 40
    },
    {
      "epoch": 0.1837813002526993,
      "grad_norm": 0.4516962468624115,
      "learning_rate": 4.998685537302135e-05,
      "loss": 0.8836,
      "step": 50
    },
    {
      "epoch": 0.22053756030323915,
      "grad_norm": 0.4993128776550293,
      "learning_rate": 4.9933479014963055e-05,
      "loss": 0.8635,
      "step": 60
    },
    {
      "epoch": 0.257293820353779,
      "grad_norm": 0.4929085373878479,
      "learning_rate": 4.9839137016353147e-05,
      "loss": 0.8769,
      "step": 70
    },
    {
      "epoch": 0.29405008040431885,
      "grad_norm": 0.4800896644592285,
      "learning_rate": 4.970398438084758e-05,
      "loss": 0.9013,
      "step": 80
    },
    {
      "epoch": 0.33080634045485874,
      "grad_norm": 0.42861899733543396,
      "learning_rate": 4.952824316387163e-05,
      "loss": 0.8876,
      "step": 90
    },
    {
      "epoch": 0.3675626005053986,
      "grad_norm": 0.45206961035728455,
      "learning_rate": 4.931220210778332e-05,
      "loss": 0.8549,
      "step": 100
    },
    {
      "epoch": 0.4043188605559384,
      "grad_norm": 0.7127406597137451,
      "learning_rate": 4.905621616747054e-05,
      "loss": 0.8494,
      "step": 110
    },
    {
      "epoch": 0.4410751206064783,
      "grad_norm": 0.40425172448158264,
      "learning_rate": 4.876070592716105e-05,
      "loss": 0.8437,
      "step": 120
    },
    {
      "epoch": 0.47783138065701813,
      "grad_norm": 0.4734930992126465,
      "learning_rate": 4.842615690940373e-05,
      "loss": 0.8411,
      "step": 130
    },
    {
      "epoch": 0.514587640707558,
      "grad_norm": 0.4126618802547455,
      "learning_rate": 4.80531187773563e-05,
      "loss": 0.8658,
      "step": 140
    },
    {
      "epoch": 0.5513439007580979,
      "grad_norm": 0.4084201157093048,
      "learning_rate": 4.7642204431690206e-05,
      "loss": 0.8467,
      "step": 150
    },
    {
      "epoch": 0.5881001608086377,
      "grad_norm": 0.38719961047172546,
      "learning_rate": 4.71940890035964e-05,
      "loss": 0.8834,
      "step": 160
    },
    {
      "epoch": 0.6248564208591776,
      "grad_norm": 0.37913328409194946,
      "learning_rate": 4.6709508745546575e-05,
      "loss": 0.8286,
      "step": 170
    },
    {
      "epoch": 0.6616126809097175,
      "grad_norm": 0.35573574900627136,
      "learning_rate": 4.618925982163232e-05,
      "loss": 0.8447,
      "step": 180
    },
    {
      "epoch": 0.6983689409602573,
      "grad_norm": 0.3563328683376312,
      "learning_rate": 4.563419699946956e-05,
      "loss": 0.855,
      "step": 190
    },
    {
      "epoch": 0.7351252010107971,
      "grad_norm": 0.3638900816440582,
      "learning_rate": 4.504523224581762e-05,
      "loss": 0.864,
      "step": 200
    },
    {
      "epoch": 0.771881461061337,
      "grad_norm": 0.38919857144355774,
      "learning_rate": 4.442333322822028e-05,
      "loss": 0.8375,
      "step": 210
    },
    {
      "epoch": 0.8086377211118768,
      "grad_norm": 0.3908405303955078,
      "learning_rate": 4.376952172513046e-05,
      "loss": 0.8642,
      "step": 220
    },
    {
      "epoch": 0.8453939811624167,
      "grad_norm": 0.37455061078071594,
      "learning_rate": 4.308487194713097e-05,
      "loss": 0.8775,
      "step": 230
    },
    {
      "epoch": 0.8821502412129566,
      "grad_norm": 0.3894438147544861,
      "learning_rate": 4.2370508772009334e-05,
      "loss": 0.8454,
      "step": 240
    },
    {
      "epoch": 0.9189065012634965,
      "grad_norm": 0.40810340642929077,
      "learning_rate": 4.162760589658649e-05,
      "loss": 0.8399,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 816,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8336347341258752.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}