{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9813084112149533,
  "eval_steps": 500,
  "global_step": 106,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 0.37823450565338135,
      "learning_rate": 1.9890401873221642e-05,
      "loss": 2.943,
      "step": 5
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 0.3274012804031372,
      "learning_rate": 1.9564009842765225e-05,
      "loss": 3.0203,
      "step": 10
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 0.2663849890232086,
      "learning_rate": 1.9027978299657436e-05,
      "loss": 2.8306,
      "step": 15
    },
    {
      "epoch": 0.37383177570093457,
      "grad_norm": 0.2998671233654022,
      "learning_rate": 1.829405685450202e-05,
      "loss": 2.9983,
      "step": 20
    },
    {
      "epoch": 0.4672897196261682,
      "grad_norm": 0.30643677711486816,
      "learning_rate": 1.7378332790417275e-05,
      "loss": 3.0059,
      "step": 25
    },
    {
      "epoch": 0.5607476635514018,
      "grad_norm": 0.3167150318622589,
      "learning_rate": 1.6300878435817115e-05,
      "loss": 2.845,
      "step": 30
    },
    {
      "epoch": 0.6542056074766355,
      "grad_norm": 0.29322898387908936,
      "learning_rate": 1.5085311186492206e-05,
      "loss": 2.923,
      "step": 35
    },
    {
      "epoch": 0.7476635514018691,
      "grad_norm": 0.3546823263168335,
      "learning_rate": 1.3758275821142382e-05,
      "loss": 2.9725,
      "step": 40
    },
    {
      "epoch": 0.8411214953271028,
      "grad_norm": 0.35268881916999817,
      "learning_rate": 1.234886045780984e-05,
      "loss": 2.9861,
      "step": 45
    },
    {
      "epoch": 0.9345794392523364,
      "grad_norm": 0.3079037666320801,
      "learning_rate": 1.0887958953229349e-05,
      "loss": 2.9897,
      "step": 50
    },
    {
      "epoch": 1.02803738317757,
      "grad_norm": 0.33415308594703674,
      "learning_rate": 9.407593721062858e-06,
      "loss": 2.9677,
      "step": 55
    },
    {
      "epoch": 1.1214953271028036,
      "grad_norm": 0.3114282190799713,
      "learning_rate": 7.940213812589018e-06,
      "loss": 2.962,
      "step": 60
    },
    {
      "epoch": 1.2149532710280373,
      "grad_norm": 0.3043849766254425,
      "learning_rate": 6.517983645656014e-06,
      "loss": 2.9335,
      "step": 65
    },
    {
      "epoch": 1.308411214953271,
      "grad_norm": 0.35792258381843567,
      "learning_rate": 5.172077972692553e-06,
      "loss": 2.9682,
      "step": 70
    },
    {
      "epoch": 1.4018691588785046,
      "grad_norm": 0.30202534794807434,
      "learning_rate": 3.931998541814069e-06,
      "loss": 2.9475,
      "step": 75
    },
    {
      "epoch": 1.4953271028037383,
      "grad_norm": 0.40600359439849854,
      "learning_rate": 2.8249274295566863e-06,
      "loss": 2.9373,
      "step": 80
    },
    {
      "epoch": 1.588785046728972,
      "grad_norm": 0.31094491481781006,
      "learning_rate": 1.875131219943187e-06,
      "loss": 2.9115,
      "step": 85
    },
    {
      "epoch": 1.6822429906542056,
      "grad_norm": 0.3808990716934204,
      "learning_rate": 1.1034290900525279e-06,
      "loss": 2.9237,
      "step": 90
    },
    {
      "epoch": 1.7757009345794392,
      "grad_norm": 0.33799558877944946,
      "learning_rate": 5.267364614580861e-07,
      "loss": 2.8901,
      "step": 95
    },
    {
      "epoch": 1.8691588785046729,
      "grad_norm": 0.3236595690250397,
      "learning_rate": 1.5769422052403172e-07,
      "loss": 2.8905,
      "step": 100
    },
    {
      "epoch": 1.9626168224299065,
      "grad_norm": 0.3427414000034332,
      "learning_rate": 4.39163491205652e-09,
      "loss": 2.9548,
      "step": 105
    },
    {
      "epoch": 1.9813084112149533,
      "step": 106,
      "total_flos": 1.078522514767872e+16,
      "train_loss": 2.9435044122192093,
      "train_runtime": 1048.2079,
      "train_samples_per_second": 1.631,
      "train_steps_per_second": 0.101
    }
  ],
  "logging_steps": 5,
  "max_steps": 106,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 100,
  "total_flos": 1.078522514767872e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}