{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.88786658999425,
  "eval_steps": 500,
  "global_step": 8500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2875215641173088,
      "grad_norm": 423.2573547363281,
      "learning_rate": 4.712478435882691e-05,
      "loss": 17.6035,
      "step": 500
    },
    {
      "epoch": 0.5750431282346176,
      "grad_norm": 9.149832725524902,
      "learning_rate": 4.4249568717653824e-05,
      "loss": 2.5022,
      "step": 1000
    },
    {
      "epoch": 0.8625646923519263,
      "grad_norm": 3.246171236038208,
      "learning_rate": 4.137435307648074e-05,
      "loss": 1.3833,
      "step": 1500
    },
    {
      "epoch": 1.1500862564692351,
      "grad_norm": 5.592076778411865,
      "learning_rate": 3.8499137435307647e-05,
      "loss": 1.0705,
      "step": 2000
    },
    {
      "epoch": 1.437607820586544,
      "grad_norm": 12.64777660369873,
      "learning_rate": 3.562392179413456e-05,
      "loss": 0.9577,
      "step": 2500
    },
    {
      "epoch": 1.7251293847038527,
      "grad_norm": 0.7939251065254211,
      "learning_rate": 3.2748706152961475e-05,
      "loss": 0.919,
      "step": 3000
    },
    {
      "epoch": 2.0126509488211615,
      "grad_norm": 0.4556220769882202,
      "learning_rate": 2.9873490511788386e-05,
      "loss": 0.8873,
      "step": 3500
    },
    {
      "epoch": 2.3001725129384702,
      "grad_norm": 0.45749151706695557,
      "learning_rate": 2.6998274870615297e-05,
      "loss": 0.8553,
      "step": 4000
    },
    {
      "epoch": 2.587694077055779,
      "grad_norm": 0.6427181363105774,
      "learning_rate": 2.4123059229442212e-05,
      "loss": 0.8427,
      "step": 4500
    },
    {
      "epoch": 2.875215641173088,
      "grad_norm": 0.35242655873298645,
      "learning_rate": 2.124784358826912e-05,
      "loss": 0.8227,
      "step": 5000
    },
    {
      "epoch": 3.1627372052903966,
      "grad_norm": 0.5690515041351318,
      "learning_rate": 1.8372627947096034e-05,
      "loss": 0.808,
      "step": 5500
    },
    {
      "epoch": 3.4502587694077054,
      "grad_norm": 0.46968725323677063,
      "learning_rate": 1.5497412305922945e-05,
      "loss": 0.8198,
      "step": 6000
    },
    {
      "epoch": 3.7377803335250146,
      "grad_norm": 0.4196397662162781,
      "learning_rate": 1.2622196664749858e-05,
      "loss": 0.8029,
      "step": 6500
    },
    {
      "epoch": 4.025301897642323,
      "grad_norm": 0.5571260452270508,
      "learning_rate": 9.746981023576769e-06,
      "loss": 0.8049,
      "step": 7000
    },
    {
      "epoch": 4.312823461759632,
      "grad_norm": 0.5123286247253418,
      "learning_rate": 6.871765382403681e-06,
      "loss": 0.7934,
      "step": 7500
    },
    {
      "epoch": 4.6003450258769405,
      "grad_norm": 0.3241867423057556,
      "learning_rate": 3.9965497412305925e-06,
      "loss": 0.796,
      "step": 8000
    },
    {
      "epoch": 4.88786658999425,
      "grad_norm": 0.4111732542514801,
      "learning_rate": 1.1213341000575044e-06,
      "loss": 0.7851,
      "step": 8500
    }
  ],
  "logging_steps": 500,
  "max_steps": 8695,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 4492786123407360.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}