{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 222,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 9.331718444824219,
      "learning_rate": 2.9985590229902075e-05,
      "loss": 0.8576,
      "step": 10
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 5.410987377166748,
      "learning_rate": 2.9730185992421254e-05,
      "loss": 0.8903,
      "step": 20
    },
    {
      "epoch": 0.40540540540540543,
      "grad_norm": 4.453158855438232,
      "learning_rate": 2.9160833414327637e-05,
      "loss": 0.8678,
      "step": 30
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 4.9962897300720215,
      "learning_rate": 2.828966725734167e-05,
      "loss": 0.794,
      "step": 40
    },
    {
      "epoch": 0.6756756756756757,
      "grad_norm": 4.173238754272461,
      "learning_rate": 2.7135254915624213e-05,
      "loss": 0.7548,
      "step": 50
    },
    {
      "epoch": 0.8108108108108109,
      "grad_norm": 3.3840322494506836,
      "learning_rate": 2.5722200684005718e-05,
      "loss": 0.8099,
      "step": 60
    },
    {
      "epoch": 0.9459459459459459,
      "grad_norm": 3.967519998550415,
      "learning_rate": 2.408062136015872e-05,
      "loss": 0.7077,
      "step": 70
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 3.9743528366088867,
      "learning_rate": 2.224550435734272e-05,
      "loss": 0.6204,
      "step": 80
    },
    {
      "epoch": 1.2162162162162162,
      "grad_norm": 3.5897064208984375,
      "learning_rate": 2.025596200843394e-05,
      "loss": 0.5407,
      "step": 90
    },
    {
      "epoch": 1.3513513513513513,
      "grad_norm": 2.8803412914276123,
      "learning_rate": 1.8154397954454996e-05,
      "loss": 0.4542,
      "step": 100
    },
    {
      "epoch": 1.4864864864864864,
      "grad_norm": 3.2254927158355713,
      "learning_rate": 1.5985603384585545e-05,
      "loss": 0.4445,
      "step": 110
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 3.189690113067627,
      "learning_rate": 1.3795802389729185e-05,
      "loss": 0.4769,
      "step": 120
    },
    {
      "epoch": 1.7567567567567568,
      "grad_norm": 3.760241746902466,
      "learning_rate": 1.1631666776267804e-05,
      "loss": 0.4827,
      "step": 130
    },
    {
      "epoch": 1.8918918918918919,
      "grad_norm": 3.4541759490966797,
      "learning_rate": 9.5393213375378e-06,
      "loss": 0.4375,
      "step": 140
    },
    {
      "epoch": 2.027027027027027,
      "grad_norm": 2.7340729236602783,
      "learning_rate": 7.563360783939724e-06,
      "loss": 0.4293,
      "step": 150
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 2.704833507537842,
      "learning_rate": 5.7458992841091544e-06,
      "loss": 0.2595,
      "step": 160
    },
    {
      "epoch": 2.2972972972972974,
      "grad_norm": 3.564445734024048,
      "learning_rate": 4.125672874528797e-06,
      "loss": 0.2311,
      "step": 170
    },
    {
      "epoch": 2.4324324324324325,
      "grad_norm": 3.1494791507720947,
      "learning_rate": 2.7372138681624246e-06,
      "loss": 0.2487,
      "step": 180
    },
    {
      "epoch": 2.5675675675675675,
      "grad_norm": 2.934964656829834,
      "learning_rate": 1.6101148581573276e-06,
      "loss": 0.2503,
      "step": 190
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 3.3121376037597656,
      "learning_rate": 7.683980030985655e-07,
      "loss": 0.2327,
      "step": 200
    },
    {
      "epoch": 2.8378378378378377,
      "grad_norm": 2.524996519088745,
      "learning_rate": 2.300030364048139e-07,
      "loss": 0.247,
      "step": 210
    },
    {
      "epoch": 2.972972972972973,
      "grad_norm": 2.5959229469299316,
      "learning_rate": 6.404912056610091e-09,
      "loss": 0.2427,
      "step": 220
    },
    {
      "epoch": 3.0,
      "step": 222,
      "total_flos": 7668873302114304.0,
      "train_loss": 0.5104640110118969,
      "train_runtime": 439.1717,
      "train_samples_per_second": 8.033,
      "train_steps_per_second": 0.505
    }
  ],
  "logging_steps": 10,
  "max_steps": 222,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7668873302114304.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}