{
  "best_metric": 1.6611980199813843,
  "best_model_checkpoint": "output/dzhizus/checkpoint-108",
  "epoch": 1.0,
  "global_step": 108,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 0.00013647569640665277,
      "loss": 2.4321,
      "step": 5
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00013431808054484255,
      "loss": 2.1139,
      "step": 10
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001307727141907142,
      "loss": 1.9824,
      "step": 15
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00012591446386292745,
      "loss": 1.7208,
      "step": 20
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00011984591988713233,
      "loss": 1.6687,
      "step": 25
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00011269523002449659,
      "loss": 1.6941,
      "step": 30
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00010461339341095083,
      "loss": 1.7329,
      "step": 35
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.577107195028616e-05,
      "loss": 1.7829,
      "step": 40
    },
    {
      "epoch": 0.42,
      "learning_rate": 8.635498649403293e-05,
      "loss": 1.6329,
      "step": 45
    },
    {
      "epoch": 0.46,
      "learning_rate": 7.65639739089908e-05,
      "loss": 1.5783,
      "step": 50
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.660478829422256e-05,
      "loss": 1.6391,
      "step": 55
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.668773501204858e-05,
      "loss": 1.6529,
      "step": 60
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.702222972799932e-05,
      "loss": 1.5268,
      "step": 65
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.7812376238248296e-05,
      "loss": 1.5841,
      "step": 70
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.9252656466318256e-05,
      "loss": 1.6704,
      "step": 75
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.152382364220488e-05,
      "loss": 1.5718,
      "step": 80
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.4789085386517107e-05,
      "loss": 1.5881,
      "step": 85
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.190657300387505e-06,
      "loss": 1.489,
      "step": 90
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.846759838039973e-06,
      "loss": 1.6933,
      "step": 95
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.849121878224087e-06,
      "loss": 1.7571,
      "step": 100
    },
    {
      "epoch": 0.97,
      "learning_rate": 2.610437109062556e-07,
      "loss": 1.5787,
      "step": 105
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6611980199813843,
      "eval_runtime": 6.9528,
      "eval_samples_per_second": 22.149,
      "eval_steps_per_second": 2.877,
      "step": 108
    }
  ],
  "max_steps": 108,
  "num_train_epochs": 1,
  "total_flos": 112878157824000.0,
  "trial_name": null,
  "trial_params": null
}