{
  "best_metric": 2.0354697704315186,
  "best_model_checkpoint": "./qlora-out-kimiko-test2/checkpoint-40",
  "epoch": 1.0339256865912763,
  "eval_steps": 10,
  "global_step": 40,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 1e-05,
      "loss": 1.5707,
      "step": 1
    },
    {
      "epoch": 0.05,
      "learning_rate": 2e-05,
      "loss": 1.5621,
      "step": 2
    },
    {
      "epoch": 0.08,
      "learning_rate": 3e-05,
      "loss": 1.4812,
      "step": 3
    },
    {
      "epoch": 0.1,
      "learning_rate": 4e-05,
      "loss": 1.5197,
      "step": 4
    },
    {
      "epoch": 0.13,
      "learning_rate": 5e-05,
      "loss": 1.5567,
      "step": 5
    },
    {
      "epoch": 0.16,
      "learning_rate": 5e-05,
      "loss": 1.4645,
      "step": 6
    },
    {
      "epoch": 0.18,
      "learning_rate": 5e-05,
      "loss": 1.6122,
      "step": 7
    },
    {
      "epoch": 0.21,
      "learning_rate": 5e-05,
      "loss": 1.5596,
      "step": 8
    },
    {
      "epoch": 0.23,
      "learning_rate": 5e-05,
      "loss": 1.5608,
      "step": 9
    },
    {
      "epoch": 0.26,
      "learning_rate": 5e-05,
      "loss": 1.5456,
      "step": 10
    },
    {
      "epoch": 0.26,
      "eval_loss": 2.098437547683716,
      "eval_runtime": 119.6161,
      "eval_samples_per_second": 1.555,
      "eval_steps_per_second": 0.777,
      "step": 10
    },
    {
      "epoch": 0.28,
      "learning_rate": 5e-05,
      "loss": 1.5645,
      "step": 11
    },
    {
      "epoch": 0.31,
      "learning_rate": 5e-05,
      "loss": 1.538,
      "step": 12
    },
    {
      "epoch": 0.34,
      "learning_rate": 5e-05,
      "loss": 1.6388,
      "step": 13
    },
    {
      "epoch": 0.36,
      "learning_rate": 5e-05,
      "loss": 1.4943,
      "step": 14
    },
    {
      "epoch": 0.39,
      "learning_rate": 5e-05,
      "loss": 1.5469,
      "step": 15
    },
    {
      "epoch": 0.41,
      "learning_rate": 5e-05,
      "loss": 1.6149,
      "step": 16
    },
    {
      "epoch": 0.44,
      "learning_rate": 5e-05,
      "loss": 1.5345,
      "step": 17
    },
    {
      "epoch": 0.47,
      "learning_rate": 5e-05,
      "loss": 1.4903,
      "step": 18
    },
    {
      "epoch": 0.49,
      "learning_rate": 5e-05,
      "loss": 1.5499,
      "step": 19
    },
    {
      "epoch": 0.52,
      "learning_rate": 5e-05,
      "loss": 1.5934,
      "step": 20
    },
    {
      "epoch": 0.52,
      "eval_loss": 2.066981077194214,
      "eval_runtime": 119.5781,
      "eval_samples_per_second": 1.555,
      "eval_steps_per_second": 0.778,
      "step": 20
    },
    {
      "epoch": 0.54,
      "learning_rate": 5e-05,
      "loss": 1.4554,
      "step": 21
    },
    {
      "epoch": 0.57,
      "learning_rate": 5e-05,
      "loss": 1.5512,
      "step": 22
    },
    {
      "epoch": 0.59,
      "learning_rate": 5e-05,
      "loss": 1.4636,
      "step": 23
    },
    {
      "epoch": 0.62,
      "learning_rate": 5e-05,
      "loss": 1.5398,
      "step": 24
    },
    {
      "epoch": 0.65,
      "learning_rate": 5e-05,
      "loss": 1.5623,
      "step": 25
    },
    {
      "epoch": 0.67,
      "learning_rate": 5e-05,
      "loss": 1.4658,
      "step": 26
    },
    {
      "epoch": 0.7,
      "learning_rate": 5e-05,
      "loss": 1.4723,
      "step": 27
    },
    {
      "epoch": 0.72,
      "learning_rate": 5e-05,
      "loss": 1.432,
      "step": 28
    },
    {
      "epoch": 0.75,
      "learning_rate": 5e-05,
      "loss": 1.4814,
      "step": 29
    },
    {
      "epoch": 0.78,
      "learning_rate": 5e-05,
      "loss": 1.4924,
      "step": 30
    },
    {
      "epoch": 0.78,
      "eval_loss": 2.046339750289917,
      "eval_runtime": 119.5771,
      "eval_samples_per_second": 1.555,
      "eval_steps_per_second": 0.778,
      "step": 30
    },
    {
      "epoch": 0.8,
      "learning_rate": 5e-05,
      "loss": 1.5809,
      "step": 31
    },
    {
      "epoch": 0.83,
      "learning_rate": 5e-05,
      "loss": 1.4803,
      "step": 32
    },
    {
      "epoch": 0.85,
      "learning_rate": 5e-05,
      "loss": 1.4878,
      "step": 33
    },
    {
      "epoch": 0.88,
      "learning_rate": 5e-05,
      "loss": 1.3871,
      "step": 34
    },
    {
      "epoch": 0.9,
      "learning_rate": 5e-05,
      "loss": 1.5151,
      "step": 35
    },
    {
      "epoch": 0.93,
      "learning_rate": 5e-05,
      "loss": 1.4212,
      "step": 36
    },
    {
      "epoch": 0.96,
      "learning_rate": 5e-05,
      "loss": 1.6284,
      "step": 37
    },
    {
      "epoch": 0.98,
      "learning_rate": 5e-05,
      "loss": 1.5002,
      "step": 38
    },
    {
      "epoch": 1.01,
      "learning_rate": 5e-05,
      "loss": 1.4452,
      "step": 39
    },
    {
      "epoch": 1.03,
      "learning_rate": 5e-05,
      "loss": 1.4399,
      "step": 40
    },
    {
      "epoch": 1.03,
      "eval_loss": 2.0354697704315186,
      "eval_runtime": 119.5875,
      "eval_samples_per_second": 1.555,
      "eval_steps_per_second": 0.778,
      "step": 40
    }
  ],
  "logging_steps": 1,
  "max_steps": 114,
  "num_train_epochs": 3,
  "save_steps": 10,
  "total_flos": 1.8296447921160192e+17,
  "trial_name": null,
  "trial_params": null
}