{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.878419452887538,
  "eval_steps": 500,
  "global_step": 13000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3799392097264438,
      "grad_norm": 0.3757433295249939,
      "learning_rate": 1.9240121580547112e-05,
      "loss": 0.2367,
      "step": 500
    },
    {
      "epoch": 0.7598784194528876,
      "grad_norm": 0.4858400225639343,
      "learning_rate": 1.8480243161094226e-05,
      "loss": 0.1529,
      "step": 1000
    },
    {
      "epoch": 1.1398176291793314,
      "grad_norm": 0.4924967288970947,
      "learning_rate": 1.772036474164134e-05,
      "loss": 0.1399,
      "step": 1500
    },
    {
      "epoch": 1.5197568389057752,
      "grad_norm": 0.4734797775745392,
      "learning_rate": 1.6960486322188453e-05,
      "loss": 0.1275,
      "step": 2000
    },
    {
      "epoch": 1.8996960486322187,
      "grad_norm": 0.6022694110870361,
      "learning_rate": 1.6200607902735563e-05,
      "loss": 0.1247,
      "step": 2500
    },
    {
      "epoch": 2.2796352583586628,
      "grad_norm": 0.6316580772399902,
      "learning_rate": 1.5440729483282677e-05,
      "loss": 0.1151,
      "step": 3000
    },
    {
      "epoch": 2.6595744680851063,
      "grad_norm": 0.37824785709381104,
      "learning_rate": 1.4680851063829789e-05,
      "loss": 0.1107,
      "step": 3500
    },
    {
      "epoch": 3.0395136778115504,
      "grad_norm": 0.58962082862854,
      "learning_rate": 1.39209726443769e-05,
      "loss": 0.1074,
      "step": 4000
    },
    {
      "epoch": 3.419452887537994,
      "grad_norm": 0.710283637046814,
      "learning_rate": 1.3161094224924014e-05,
      "loss": 0.0996,
      "step": 4500
    },
    {
      "epoch": 3.7993920972644375,
      "grad_norm": 0.7615976333618164,
      "learning_rate": 1.2401215805471124e-05,
      "loss": 0.0987,
      "step": 5000
    },
    {
      "epoch": 4.179331306990881,
      "grad_norm": 0.5415639877319336,
      "learning_rate": 1.1641337386018238e-05,
      "loss": 0.0923,
      "step": 5500
    },
    {
      "epoch": 4.5592705167173255,
      "grad_norm": 0.765820324420929,
      "learning_rate": 1.088145896656535e-05,
      "loss": 0.0887,
      "step": 6000
    },
    {
      "epoch": 4.939209726443769,
      "grad_norm": 0.4675578773021698,
      "learning_rate": 1.0121580547112462e-05,
      "loss": 0.0887,
      "step": 6500
    },
    {
      "epoch": 5.319148936170213,
      "grad_norm": 0.5862268805503845,
      "learning_rate": 9.361702127659576e-06,
      "loss": 0.0819,
      "step": 7000
    },
    {
      "epoch": 5.699088145896656,
      "grad_norm": 0.7189024090766907,
      "learning_rate": 8.601823708206687e-06,
      "loss": 0.0779,
      "step": 7500
    },
    {
      "epoch": 6.079027355623101,
      "grad_norm": 0.48072344064712524,
      "learning_rate": 7.841945288753801e-06,
      "loss": 0.077,
      "step": 8000
    },
    {
      "epoch": 6.458966565349544,
      "grad_norm": 0.524259090423584,
      "learning_rate": 7.082066869300912e-06,
      "loss": 0.0726,
      "step": 8500
    },
    {
      "epoch": 6.838905775075988,
      "grad_norm": 0.659052312374115,
      "learning_rate": 6.322188449848025e-06,
      "loss": 0.072,
      "step": 9000
    },
    {
      "epoch": 7.218844984802431,
      "grad_norm": 0.7663692831993103,
      "learning_rate": 5.562310030395137e-06,
      "loss": 0.0687,
      "step": 9500
    },
    {
      "epoch": 7.598784194528875,
      "grad_norm": 0.5136072635650635,
      "learning_rate": 4.80243161094225e-06,
      "loss": 0.0645,
      "step": 10000
    },
    {
      "epoch": 7.9787234042553195,
      "grad_norm": 0.8392360806465149,
      "learning_rate": 4.042553191489362e-06,
      "loss": 0.068,
      "step": 10500
    },
    {
      "epoch": 8.358662613981762,
      "grad_norm": 0.6674140095710754,
      "learning_rate": 3.2826747720364744e-06,
      "loss": 0.062,
      "step": 11000
    },
    {
      "epoch": 8.738601823708207,
      "grad_norm": 0.6431790590286255,
      "learning_rate": 2.5227963525835868e-06,
      "loss": 0.0635,
      "step": 11500
    },
    {
      "epoch": 9.118541033434651,
      "grad_norm": 0.8986673355102539,
      "learning_rate": 1.7629179331306991e-06,
      "loss": 0.0604,
      "step": 12000
    },
    {
      "epoch": 9.498480243161094,
      "grad_norm": 0.5945561528205872,
      "learning_rate": 1.0030395136778117e-06,
      "loss": 0.0595,
      "step": 12500
    },
    {
      "epoch": 9.878419452887538,
      "grad_norm": 0.7079329490661621,
      "learning_rate": 2.4316109422492405e-07,
      "loss": 0.0593,
      "step": 13000
    }
  ],
  "logging_steps": 500,
  "max_steps": 13160,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 500,
  "total_flos": 2.755897861208064e+16,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}