{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9873417721518988,
  "eval_steps": 500,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 5e-05,
      "loss": 3.2449,
      "step": 1
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001,
      "loss": 3.1698,
      "step": 2
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.153,
      "step": 3
    },
    {
      "epoch": 0.1,
      "learning_rate": 9.928079551738543e-05,
      "loss": 1.2337,
      "step": 4
    },
    {
      "epoch": 0.13,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.4549,
      "step": 5
    },
    {
      "epoch": 0.15,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.271,
      "step": 6
    },
    {
      "epoch": 0.18,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.0901,
      "step": 7
    },
    {
      "epoch": 0.2,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.4414,
      "step": 8
    },
    {
      "epoch": 0.23,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.1304,
      "step": 9
    },
    {
      "epoch": 0.25,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.1406,
      "step": 10
    },
    {
      "epoch": 0.28,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.1073,
      "step": 11
    },
    {
      "epoch": 0.3,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.0964,
      "step": 12
    },
    {
      "epoch": 0.33,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.0916,
      "step": 13
    },
    {
      "epoch": 0.35,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.0802,
      "step": 14
    },
    {
      "epoch": 0.38,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.0632,
      "step": 15
    },
    {
      "epoch": 0.41,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.0674,
      "step": 16
    },
    {
      "epoch": 0.43,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.0642,
      "step": 17
    },
    {
      "epoch": 0.46,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.058,
      "step": 18
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.0622,
      "step": 19
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.0627,
      "step": 20
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.0622,
      "step": 21
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.0573,
      "step": 22
    },
    {
      "epoch": 0.58,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.0541,
      "step": 23
    },
    {
      "epoch": 0.61,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.0535,
      "step": 24
    },
    {
      "epoch": 0.63,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.0527,
      "step": 25
    },
    {
      "epoch": 0.66,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.0536,
      "step": 26
    },
    {
      "epoch": 0.68,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.0576,
      "step": 27
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.0595,
      "step": 28
    },
    {
      "epoch": 0.73,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.0547,
      "step": 29
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.0539,
      "step": 30
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.0564,
      "step": 31
    },
    {
      "epoch": 0.81,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.0547,
      "step": 32
    },
    {
      "epoch": 0.84,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.0564,
      "step": 33
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.0572,
      "step": 34
    },
    {
      "epoch": 0.89,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.0531,
      "step": 35
    },
    {
      "epoch": 0.91,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.0541,
      "step": 36
    },
    {
      "epoch": 0.94,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.0544,
      "step": 37
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.0541,
      "step": 38
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0,
      "loss": 0.053,
      "step": 39
    },
    {
      "epoch": 0.99,
      "step": 39,
      "total_flos": 0.0,
      "train_loss": 0.31117012858008725,
      "train_runtime": 1132.5716,
      "train_samples_per_second": 18.086,
      "train_steps_per_second": 0.034
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 39,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}