{
  "best_metric": 0.4093799591064453,
  "best_model_checkpoint": "../../text-generation-webui/loras/mistral-instruct-raw-format-v2-more-positive/checkpoint-24",
  "epoch": 0.8205128205128205,
  "eval_steps": 3,
  "global_step": 24,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 0.9379,
      "step": 1
    },
    {
      "epoch": 0.03,
      "eval_loss": 0.9217294454574585,
      "eval_runtime": 21.8917,
      "eval_samples_per_second": 34.259,
      "eval_steps_per_second": 8.588,
      "step": 1
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0002,
      "loss": 0.8714,
      "step": 2
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.7334,
      "step": 3
    },
    {
      "epoch": 0.1,
      "eval_loss": 0.6237823963165283,
      "eval_runtime": 22.2516,
      "eval_samples_per_second": 33.705,
      "eval_steps_per_second": 8.449,
      "step": 3
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0004,
      "loss": 0.6181,
      "step": 4
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0005,
      "loss": 0.5345,
      "step": 5
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0006,
      "loss": 0.503,
      "step": 6
    },
    {
      "epoch": 0.21,
      "eval_loss": 0.5134392976760864,
      "eval_runtime": 22.3048,
      "eval_samples_per_second": 33.625,
      "eval_steps_per_second": 8.429,
      "step": 6
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0007,
      "loss": 0.5106,
      "step": 7
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0008,
      "loss": 0.4623,
      "step": 8
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0009000000000000001,
      "loss": 0.4644,
      "step": 9
    },
    {
      "epoch": 0.31,
      "eval_loss": 0.45862117409706116,
      "eval_runtime": 22.3188,
      "eval_samples_per_second": 33.604,
      "eval_steps_per_second": 8.423,
      "step": 9
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001,
      "loss": 0.4399,
      "step": 10
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0009931806517013613,
      "loss": 0.4356,
      "step": 11
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0009729086208503173,
      "loss": 0.4636,
      "step": 12
    },
    {
      "epoch": 0.41,
      "eval_loss": 0.44031861424446106,
      "eval_runtime": 22.3297,
      "eval_samples_per_second": 33.588,
      "eval_steps_per_second": 8.419,
      "step": 12
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0009397368756032445,
      "loss": 0.4481,
      "step": 13
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0008945702546981969,
      "loss": 0.4278,
      "step": 14
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0008386407858128706,
      "loss": 0.41,
      "step": 15
    },
    {
      "epoch": 0.51,
      "eval_loss": 0.42758792638778687,
      "eval_runtime": 22.324,
      "eval_samples_per_second": 33.596,
      "eval_steps_per_second": 8.421,
      "step": 15
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0007734740790612135,
      "loss": 0.3787,
      "step": 16
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0007008477123264848,
      "loss": 0.4467,
      "step": 17
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0006227427435703996,
      "loss": 0.4248,
      "step": 18
    },
    {
      "epoch": 0.62,
      "eval_loss": 0.41894882917404175,
      "eval_runtime": 22.3349,
      "eval_samples_per_second": 33.58,
      "eval_steps_per_second": 8.417,
      "step": 18
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0005412896727361663,
      "loss": 0.3963,
      "step": 19
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0004587103272638339,
      "loss": 0.4,
      "step": 20
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00037725725642960046,
      "loss": 0.4094,
      "step": 21
    },
    {
      "epoch": 0.72,
      "eval_loss": 0.41203784942626953,
      "eval_runtime": 22.3351,
      "eval_samples_per_second": 33.579,
      "eval_steps_per_second": 8.417,
      "step": 21
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0002991522876735154,
      "loss": 0.4013,
      "step": 22
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00022652592093878665,
      "loss": 0.3854,
      "step": 23
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00016135921418712956,
      "loss": 0.3905,
      "step": 24
    },
    {
      "epoch": 0.82,
      "eval_loss": 0.4093799591064453,
      "eval_runtime": 22.3288,
      "eval_samples_per_second": 33.589,
      "eval_steps_per_second": 8.42,
      "step": 24
    }
  ],
  "logging_steps": 1,
  "max_steps": 29,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "total_flos": 1.3500086374681805e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}