{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.263823064770932,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 2.2e-05,
      "loss": 0.9856,
      "step": 1
    },
    {
      "epoch": 0.05,
      "learning_rate": 2.1998557720321954e-05,
      "loss": 0.8657,
      "step": 2
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.1994231259500664e-05,
      "loss": 0.7599,
      "step": 3
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.1987021752075498e-05,
      "loss": 0.6924,
      "step": 4
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.1976931088614826e-05,
      "loss": 0.818,
      "step": 5
    },
    {
      "epoch": 0.15,
      "learning_rate": 2.1963961915220263e-05,
      "loss": 1.2993,
      "step": 6
    },
    {
      "epoch": 0.18,
      "learning_rate": 2.1948117632832752e-05,
      "loss": 1.4107,
      "step": 7
    },
    {
      "epoch": 0.2,
      "learning_rate": 2.1929402396340756e-05,
      "loss": 0.8539,
      "step": 8
    },
    {
      "epoch": 0.23,
      "learning_rate": 2.1907821113490676e-05,
      "loss": 0.7822,
      "step": 9
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.1883379443599917e-05,
      "loss": 0.6498,
      "step": 10
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.777102530002594,
      "eval_runtime": 26.948,
      "eval_samples_per_second": 30.726,
      "eval_steps_per_second": 0.482,
      "step": 10
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.1856083796072795e-05,
      "loss": 0.7439,
      "step": 11
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.182594132871982e-05,
      "loss": 1.0097,
      "step": 12
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.179295994588063e-05,
      "loss": 1.3189,
      "step": 13
    },
    {
      "epoch": 0.35,
      "learning_rate": 2.175714829635128e-05,
      "loss": 0.7509,
      "step": 14
    },
    {
      "epoch": 0.38,
      "learning_rate": 2.1718515771116186e-05,
      "loss": 0.7273,
      "step": 15
    },
    {
      "epoch": 0.4,
      "learning_rate": 2.167707250088555e-05,
      "loss": 0.6242,
      "step": 16
    },
    {
      "epoch": 0.43,
      "learning_rate": 2.1632829353438724e-05,
      "loss": 0.6135,
      "step": 17
    },
    {
      "epoch": 0.45,
      "learning_rate": 2.1585797930774335e-05,
      "loss": 0.9365,
      "step": 18
    },
    {
      "epoch": 0.48,
      "learning_rate": 2.1535990566067858e-05,
      "loss": 1.4216,
      "step": 19
    },
    {
      "epoch": 0.51,
      "learning_rate": 2.148342032043747e-05,
      "loss": 0.7369,
      "step": 20
    },
    {
      "epoch": 0.51,
      "eval_loss": 0.7404242157936096,
      "eval_runtime": 26.98,
      "eval_samples_per_second": 30.689,
      "eval_steps_per_second": 0.482,
      "step": 20
    },
    {
      "epoch": 0.53,
      "learning_rate": 2.1428100979518976e-05,
      "loss": 0.7605,
      "step": 21
    },
    {
      "epoch": 0.56,
      "learning_rate": 2.1370047049850775e-05,
      "loss": 0.6095,
      "step": 22
    },
    {
      "epoch": 0.58,
      "learning_rate": 2.130927375506978e-05,
      "loss": 0.5955,
      "step": 23
    },
    {
      "epoch": 0.61,
      "learning_rate": 2.1245797031919265e-05,
      "loss": 0.851,
      "step": 24
    },
    {
      "epoch": 0.63,
      "learning_rate": 2.1179633526069748e-05,
      "loss": 1.324,
      "step": 25
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.1110800587753934e-05,
      "loss": 0.9368,
      "step": 26
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.103931626721694e-05,
      "loss": 0.7307,
      "step": 27
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.0965199309982913e-05,
      "loss": 0.6489,
      "step": 28
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.0888469151939347e-05,
      "loss": 0.536,
      "step": 29
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.0809145914240356e-05,
      "loss": 0.732,
      "step": 30
    },
    {
      "epoch": 0.76,
      "eval_loss": 0.7266919612884521,
      "eval_runtime": 26.9346,
      "eval_samples_per_second": 30.741,
      "eval_steps_per_second": 0.483,
      "step": 30
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.072725039803026e-05,
      "loss": 1.1248,
      "step": 31
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.0642804078988827e-05,
      "loss": 1.0917,
      "step": 32
    },
    {
      "epoch": 0.83,
      "learning_rate": 2.055582910169966e-05,
      "loss": 0.735,
      "step": 33
    },
    {
      "epoch": 0.86,
      "learning_rate": 2.0466348273843176e-05,
      "loss": 0.6749,
      "step": 34
    },
    {
      "epoch": 0.88,
      "learning_rate": 2.0374385060215662e-05,
      "loss": 0.5519,
      "step": 35
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.027996357657605e-05,
      "loss": 0.6593,
      "step": 36
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.018310858332198e-05,
      "loss": 0.959,
      "step": 37
    },
    {
      "epoch": 0.96,
      "learning_rate": 2.008384547899682e-05,
      "loss": 1.168,
      "step": 38
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.9982200293629318e-05,
      "loss": 0.6186,
      "step": 39
    },
    {
      "epoch": 1.01,
      "learning_rate": 1.9878199681907702e-05,
      "loss": 1.1207,
      "step": 40
    },
    {
      "epoch": 1.01,
      "eval_loss": 0.7203702926635742,
      "eval_runtime": 26.9926,
      "eval_samples_per_second": 30.675,
      "eval_steps_per_second": 0.482,
      "step": 40
    },
    {
      "epoch": 1.04,
      "learning_rate": 1.977187091618993e-05,
      "loss": 0.7095,
      "step": 41
    },
    {
      "epoch": 1.06,
      "learning_rate": 1.9663241879351998e-05,
      "loss": 0.6781,
      "step": 42
    },
    {
      "epoch": 1.09,
      "learning_rate": 1.9552341057476144e-05,
      "loss": 0.5649,
      "step": 43
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.9439197532380845e-05,
      "loss": 0.5466,
      "step": 44
    },
    {
      "epoch": 1.14,
      "learning_rate": 1.9323840973994647e-05,
      "loss": 0.8721,
      "step": 45
    },
    {
      "epoch": 1.16,
      "learning_rate": 1.9206301632575707e-05,
      "loss": 1.2152,
      "step": 46
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.9086610330779205e-05,
      "loss": 0.6863,
      "step": 47
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.8964798455574637e-05,
      "loss": 0.6792,
      "step": 48
    },
    {
      "epoch": 1.24,
      "learning_rate": 1.884089795001512e-05,
      "loss": 0.5667,
      "step": 49
    },
    {
      "epoch": 1.26,
      "learning_rate": 1.871494130486089e-05,
      "loss": 0.5256,
      "step": 50
    },
    {
      "epoch": 1.26,
      "eval_loss": 0.6949857473373413,
      "eval_runtime": 26.8774,
      "eval_samples_per_second": 30.807,
      "eval_steps_per_second": 0.484,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 195,
  "num_train_epochs": 5,
  "save_steps": 25,
  "total_flos": 1.2823585474593423e+18,
  "trial_name": null,
  "trial_params": null
}