{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 56,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 1e-05,
      "loss": 0.1245,
      "step": 1
    },
    {
      "epoch": 0.14,
      "learning_rate": 2e-05,
      "loss": 0.1062,
      "step": 2
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.9983081582712684e-05,
      "loss": 0.1154,
      "step": 3
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.9932383577419432e-05,
      "loss": 0.3281,
      "step": 4
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.9848077530122083e-05,
      "loss": 0.109,
      "step": 5
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.973044870579824e-05,
      "loss": 0.1197,
      "step": 6
    },
    {
      "epoch": 0.5,
      "learning_rate": 1.957989512315489e-05,
      "loss": 0.136,
      "step": 7
    },
    {
      "epoch": 0.57,
      "learning_rate": 1.9396926207859085e-05,
      "loss": 0.1214,
      "step": 8
    },
    {
      "epoch": 0.64,
      "learning_rate": 1.9182161068802742e-05,
      "loss": 0.1254,
      "step": 9
    },
    {
      "epoch": 0.71,
      "learning_rate": 1.8936326403234125e-05,
      "loss": 0.1218,
      "step": 10
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.866025403784439e-05,
      "loss": 0.1086,
      "step": 11
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.8354878114129368e-05,
      "loss": 0.1085,
      "step": 12
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.802123192755044e-05,
      "loss": 0.1115,
      "step": 13
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.766044443118978e-05,
      "loss": 0.0986,
      "step": 14
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.7273736415730488e-05,
      "loss": 0.0802,
      "step": 15
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.686241637868734e-05,
      "loss": 0.0847,
      "step": 16
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.6427876096865394e-05,
      "loss": 0.0813,
      "step": 17
    },
    {
      "epoch": 1.29,
      "learning_rate": 1.5971585917027864e-05,
      "loss": 0.0787,
      "step": 18
    },
    {
      "epoch": 1.36,
      "learning_rate": 1.5495089780708062e-05,
      "loss": 0.0816,
      "step": 19
    },
    {
      "epoch": 1.43,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0785,
      "step": 20
    },
    {
      "epoch": 1.5,
      "learning_rate": 1.4487991802004625e-05,
      "loss": 0.06,
      "step": 21
    },
    {
      "epoch": 1.57,
      "learning_rate": 1.396079766039157e-05,
      "loss": 0.0952,
      "step": 22
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.342020143325669e-05,
      "loss": 0.1109,
      "step": 23
    },
    {
      "epoch": 1.71,
      "learning_rate": 1.2868032327110904e-05,
      "loss": 0.08,
      "step": 24
    },
    {
      "epoch": 1.79,
      "learning_rate": 1.2306158707424402e-05,
      "loss": 0.0643,
      "step": 25
    },
    {
      "epoch": 1.86,
      "learning_rate": 1.1736481776669307e-05,
      "loss": 0.078,
      "step": 26
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.1160929141252303e-05,
      "loss": 0.0607,
      "step": 27
    },
    {
      "epoch": 2.0,
      "learning_rate": 1.0581448289104759e-05,
      "loss": 0.0763,
      "step": 28
    },
    {
      "epoch": 2.07,
      "learning_rate": 1e-05,
      "loss": 0.0626,
      "step": 29
    },
    {
      "epoch": 2.14,
      "learning_rate": 9.418551710895243e-06,
      "loss": 0.0508,
      "step": 30
    },
    {
      "epoch": 2.21,
      "learning_rate": 8.839070858747697e-06,
      "loss": 0.061,
      "step": 31
    },
    {
      "epoch": 2.29,
      "learning_rate": 8.263518223330698e-06,
      "loss": 0.0426,
      "step": 32
    },
    {
      "epoch": 2.36,
      "learning_rate": 7.6938412925756e-06,
      "loss": 0.0428,
      "step": 33
    },
    {
      "epoch": 2.43,
      "learning_rate": 7.131967672889101e-06,
      "loss": 0.055,
      "step": 34
    },
    {
      "epoch": 2.5,
      "learning_rate": 6.579798566743314e-06,
      "loss": 0.0583,
      "step": 35
    },
    {
      "epoch": 2.57,
      "learning_rate": 6.039202339608432e-06,
      "loss": 0.0575,
      "step": 36
    },
    {
      "epoch": 2.64,
      "learning_rate": 5.512008197995379e-06,
      "loss": 0.0355,
      "step": 37
    },
    {
      "epoch": 2.71,
      "learning_rate": 5.000000000000003e-06,
      "loss": 0.0456,
      "step": 38
    },
    {
      "epoch": 2.79,
      "learning_rate": 4.504910219291941e-06,
      "loss": 0.0467,
      "step": 39
    },
    {
      "epoch": 2.86,
      "learning_rate": 4.028414082972141e-06,
      "loss": 0.042,
      "step": 40
    },
    {
      "epoch": 2.93,
      "learning_rate": 3.5721239031346067e-06,
      "loss": 0.047,
      "step": 41
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.1375836213126653e-06,
      "loss": 0.0376,
      "step": 42
    },
    {
      "epoch": 3.07,
      "learning_rate": 2.726263584269513e-06,
      "loss": 0.0351,
      "step": 43
    },
    {
      "epoch": 3.14,
      "learning_rate": 2.339555568810221e-06,
      "loss": 0.033,
      "step": 44
    },
    {
      "epoch": 3.21,
      "learning_rate": 1.9787680724495617e-06,
      "loss": 0.0355,
      "step": 45
    },
    {
      "epoch": 3.29,
      "learning_rate": 1.6451218858706374e-06,
      "loss": 0.0272,
      "step": 46
    },
    {
      "epoch": 3.36,
      "learning_rate": 1.339745962155613e-06,
      "loss": 0.027,
      "step": 47
    },
    {
      "epoch": 3.43,
      "learning_rate": 1.0636735967658785e-06,
      "loss": 0.0165,
      "step": 48
    },
    {
      "epoch": 3.5,
      "learning_rate": 8.178389311972612e-07,
      "loss": 0.0187,
      "step": 49
    },
    {
      "epoch": 3.57,
      "learning_rate": 6.030737921409169e-07,
      "loss": 0.0268,
      "step": 50
    },
    {
      "epoch": 3.64,
      "learning_rate": 4.2010487684511105e-07,
      "loss": 0.0238,
      "step": 51
    },
    {
      "epoch": 3.71,
      "learning_rate": 2.6955129420176193e-07,
      "loss": 0.0202,
      "step": 52
    },
    {
      "epoch": 3.79,
      "learning_rate": 1.519224698779198e-07,
      "loss": 0.0259,
      "step": 53
    },
    {
      "epoch": 3.86,
      "learning_rate": 6.761642258056977e-08,
      "loss": 0.0206,
      "step": 54
    },
    {
      "epoch": 3.93,
      "learning_rate": 1.6918417287318245e-08,
      "loss": 0.0349,
      "step": 55
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.0,
      "loss": 0.0208,
      "step": 56
    },
    {
      "epoch": 4.0,
      "step": 56,
      "total_flos": 3088648765440.0,
      "train_loss": 0.07135537000639099,
      "train_runtime": 2491.5163,
      "train_samples_per_second": 1.426,
      "train_steps_per_second": 0.022
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 56,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 1000,
  "total_flos": 3088648765440.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}