{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24140740517215364,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012070370258607683,
      "grad_norm": 1.453125,
      "learning_rate": 1.5087507543753772e-06,
      "loss": 2.681,
      "mean_token_accuracy": 0.5007504414767027,
      "num_input_tokens_seen": 25446880,
      "num_tokens": 10166805.0,
      "step": 50
    },
    {
      "epoch": 0.024140740517215365,
      "grad_norm": 1.4921875,
      "learning_rate": 3.0175015087507544e-06,
      "loss": 2.6838,
      "mean_token_accuracy": 0.500230128839612,
      "num_input_tokens_seen": 51020960,
      "num_tokens": 20365412.0,
      "step": 100
    },
    {
      "epoch": 0.03621111077582305,
      "grad_norm": 1.6484375,
      "learning_rate": 4.526252263126131e-06,
      "loss": 2.6811,
      "mean_token_accuracy": 0.5007199160754681,
      "num_input_tokens_seen": 76507776,
      "num_tokens": 30424121.0,
      "step": 150
    },
    {
      "epoch": 0.04828148103443073,
      "grad_norm": 1.4765625,
      "learning_rate": 6.035003017501509e-06,
      "loss": 2.6797,
      "mean_token_accuracy": 0.500353229418397,
      "num_input_tokens_seen": 101977920,
      "num_tokens": 40650709.0,
      "step": 200
    },
    {
      "epoch": 0.06035185129303841,
      "grad_norm": 1.421875,
      "learning_rate": 7.543753771876886e-06,
      "loss": 2.6464,
      "mean_token_accuracy": 0.5040991773456335,
      "num_input_tokens_seen": 127536896,
      "num_tokens": 50830609.0,
      "step": 250
    },
    {
      "epoch": 0.0724222215516461,
      "grad_norm": 1.140625,
      "learning_rate": 9.052504526252262e-06,
      "loss": 2.654,
      "mean_token_accuracy": 0.5034311909228564,
      "num_input_tokens_seen": 153048544,
      "num_tokens": 60898431.0,
      "step": 300
    },
    {
      "epoch": 0.08449259181025377,
      "grad_norm": 1.0234375,
      "learning_rate": 1.0561255280627642e-05,
      "loss": 2.625,
      "mean_token_accuracy": 0.5059863431751728,
      "num_input_tokens_seen": 178595392,
      "num_tokens": 71195944.0,
      "step": 350
    },
    {
      "epoch": 0.09656296206886146,
      "grad_norm": 0.91015625,
      "learning_rate": 1.2070006035003018e-05,
      "loss": 2.6079,
      "mean_token_accuracy": 0.5077864757180214,
      "num_input_tokens_seen": 204085184,
      "num_tokens": 81381172.0,
      "step": 400
    },
    {
      "epoch": 0.10863333232746915,
      "grad_norm": 0.78515625,
      "learning_rate": 1.3578756789378394e-05,
      "loss": 2.6083,
      "mean_token_accuracy": 0.5078243865072727,
      "num_input_tokens_seen": 229609824,
      "num_tokens": 91569720.0,
      "step": 450
    },
    {
      "epoch": 0.12070370258607682,
      "grad_norm": 0.734375,
      "learning_rate": 1.5087507543753773e-05,
      "loss": 2.591,
      "num_input_tokens_seen": 255055520,
      "step": 500
    },
    {
      "epoch": 0.12070370258607682,
      "eval_loss": 2.492645263671875,
      "eval_mean_token_accuracy": 0.5286665781386491,
      "eval_num_tokens": 101801812.0,
      "eval_runtime": 126.4646,
      "eval_samples_per_second": 84.704,
      "eval_steps_per_second": 21.176,
      "num_input_tokens_seen": 255055520,
      "step": 500
    },
    {
      "epoch": 0.1327740728446845,
      "grad_norm": 0.70703125,
      "learning_rate": 1.659625829812915e-05,
      "loss": 2.5826,
      "mean_token_accuracy": 0.5089771485328675,
      "num_input_tokens_seen": 280435680,
      "num_tokens": 111840270.0,
      "step": 550
    },
    {
      "epoch": 0.1448444431032922,
      "grad_norm": 0.65625,
      "learning_rate": 1.8105009052504525e-05,
      "loss": 2.5689,
      "mean_token_accuracy": 0.5112711164355278,
      "num_input_tokens_seen": 305931936,
      "num_tokens": 121987982.0,
      "step": 600
    },
    {
      "epoch": 0.15691481336189989,
      "grad_norm": 0.75,
      "learning_rate": 1.9613759806879906e-05,
      "loss": 2.55,
      "mean_token_accuracy": 0.5135074812173843,
      "num_input_tokens_seen": 331404160,
      "num_tokens": 132144416.0,
      "step": 650
    },
    {
      "epoch": 0.16898518362050755,
      "grad_norm": 0.58984375,
      "learning_rate": 2.1122510561255283e-05,
      "loss": 2.5497,
      "mean_token_accuracy": 0.513639942780137,
      "num_input_tokens_seen": 356956832,
      "num_tokens": 142378323.0,
      "step": 700
    },
    {
      "epoch": 0.18105555387911523,
      "grad_norm": 0.486328125,
      "learning_rate": 2.2631261315630658e-05,
      "loss": 2.5395,
      "mean_token_accuracy": 0.5144028599560261,
      "num_input_tokens_seen": 382529376,
      "num_tokens": 152623392.0,
      "step": 750
    },
    {
      "epoch": 0.19312592413772292,
      "grad_norm": 0.5234375,
      "learning_rate": 2.4140012070006035e-05,
      "loss": 2.5309,
      "mean_token_accuracy": 0.5156180351227522,
      "num_input_tokens_seen": 408021056,
      "num_tokens": 162827766.0,
      "step": 800
    },
    {
      "epoch": 0.2051962943963306,
      "grad_norm": 0.447265625,
      "learning_rate": 2.5648762824381413e-05,
      "loss": 2.5241,
      "mean_token_accuracy": 0.5165234027802944,
      "num_input_tokens_seen": 433622464,
      "num_tokens": 172979899.0,
      "step": 850
    },
    {
      "epoch": 0.2172666646549383,
      "grad_norm": 0.55078125,
      "learning_rate": 2.7157513578756787e-05,
      "loss": 2.5219,
      "mean_token_accuracy": 0.5160751658678054,
      "num_input_tokens_seen": 459074080,
      "num_tokens": 183138615.0,
      "step": 900
    },
    {
      "epoch": 0.22933703491354598,
      "grad_norm": 0.482421875,
      "learning_rate": 2.866626433313217e-05,
      "loss": 2.511,
      "mean_token_accuracy": 0.5176014001667499,
      "num_input_tokens_seen": 484598624,
      "num_tokens": 193253896.0,
      "step": 950
    },
    {
      "epoch": 0.24140740517215364,
      "grad_norm": 0.6015625,
      "learning_rate": 3.0175015087507546e-05,
      "loss": 2.4857,
      "num_input_tokens_seen": 510077440,
      "step": 1000
    },
    {
      "epoch": 0.24140740517215364,
      "eval_loss": 2.4022138118743896,
      "eval_mean_token_accuracy": 0.5380484161312853,
      "eval_num_tokens": 203431197.0,
      "eval_runtime": 126.7655,
      "eval_samples_per_second": 84.503,
      "eval_steps_per_second": 21.126,
      "num_input_tokens_seen": 510077440,
      "step": 1000
    }
  ],
  "logging_steps": 50,
  "max_steps": 8284,
  "num_input_tokens_seen": 510077440,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.364506935558144e+17,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}