{
  "best_metric": 0.568750262260437,
  "best_model_checkpoint": "./lora-alpaca/checkpoint-400",
  "epoch": 0.6683375104427736,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 2.7003,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 2.566,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.999999999999999e-05,
      "loss": 2.2648,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00011099999999999999,
      "loss": 1.657,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00014099999999999998,
      "loss": 1.1599,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00017099999999999998,
      "loss": 0.9037,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000201,
      "loss": 0.8137,
      "step": 70
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00023099999999999998,
      "loss": 0.7827,
      "step": 80
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000261,
      "loss": 0.7554,
      "step": 90
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00029099999999999997,
      "loss": 0.7357,
      "step": 100
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002957831325301205,
      "loss": 0.6893,
      "step": 110
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00028975903614457827,
      "loss": 0.6606,
      "step": 120
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002837349397590361,
      "loss": 0.6506,
      "step": 130
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00027771084337349395,
      "loss": 0.6462,
      "step": 140
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0002716867469879518,
      "loss": 0.6315,
      "step": 150
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0002656626506024096,
      "loss": 0.6337,
      "step": 160
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00025963855421686746,
      "loss": 0.6223,
      "step": 170
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00025361445783132525,
      "loss": 0.6136,
      "step": 180
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00024759036144578314,
      "loss": 0.6198,
      "step": 190
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00024156626506024095,
      "loss": 0.6084,
      "step": 200
    },
    {
      "epoch": 0.33,
      "eval_loss": 0.608456552028656,
      "eval_runtime": 123.856,
      "eval_samples_per_second": 16.148,
      "eval_steps_per_second": 1.009,
      "step": 200
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00023554216867469876,
      "loss": 0.6021,
      "step": 210
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0002295180722891566,
      "loss": 0.5949,
      "step": 220
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00022349397590361444,
      "loss": 0.5972,
      "step": 230
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00021746987951807228,
      "loss": 0.5922,
      "step": 240
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002114457831325301,
      "loss": 0.5876,
      "step": 250
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00020542168674698793,
      "loss": 0.5788,
      "step": 260
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001993975903614458,
      "loss": 0.5894,
      "step": 270
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001933734939759036,
      "loss": 0.5877,
      "step": 280
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00018734939759036142,
      "loss": 0.5835,
      "step": 290
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00018132530120481925,
      "loss": 0.5791,
      "step": 300
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00017530120481927712,
      "loss": 0.5841,
      "step": 310
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00016927710843373493,
      "loss": 0.5728,
      "step": 320
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00016325301204819274,
      "loss": 0.569,
      "step": 330
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00015722891566265058,
      "loss": 0.5709,
      "step": 340
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00015120481927710845,
      "loss": 0.5762,
      "step": 350
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00014518072289156626,
      "loss": 0.5704,
      "step": 360
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001391566265060241,
      "loss": 0.5661,
      "step": 370
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00013313253012048193,
      "loss": 0.5662,
      "step": 380
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00012710843373493975,
      "loss": 0.5674,
      "step": 390
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00012108433734939758,
      "loss": 0.5635,
      "step": 400
    },
    {
      "epoch": 0.67,
      "eval_loss": 0.568750262260437,
      "eval_runtime": 122.9061,
      "eval_samples_per_second": 16.273,
      "eval_steps_per_second": 1.017,
      "step": 400
    }
  ],
  "max_steps": 598,
  "num_train_epochs": 1,
  "total_flos": 3.4431112456647475e+17,
  "trial_name": null,
  "trial_params": null
}