{
  "best_metric": 2.098437547683716,
  "best_model_checkpoint": "./qlora-out-kimiko-test2/checkpoint-10",
  "epoch": 0.25848142164781907,
  "eval_steps": 10,
  "global_step": 10,
  "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
    }
  ],
  "logging_steps": 1,
  "max_steps": 114,
  "num_train_epochs": 3,
  "save_steps": 10,
  "total_flos": 4.582587092041728e+16,
  "trial_name": null,
  "trial_params": null
}