{
  "best_metric": 1.3710952997207642,
  "best_model_checkpoint": "outputs/checkpoint-200",
  "epoch": 0.06844626967830253,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1e-05,
      "loss": 1.8606,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 2e-05,
      "loss": 1.8806,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 3e-05,
      "loss": 1.8434,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 1.7431,
      "step": 20
    },
    {
      "epoch": 0.01,
      "learning_rate": 5e-05,
      "loss": 1.7721,
      "step": 25
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-05,
      "loss": 1.6826,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 7e-05,
      "loss": 1.5892,
      "step": 35
    },
    {
      "epoch": 0.01,
      "learning_rate": 8e-05,
      "loss": 1.6333,
      "step": 40
    },
    {
      "epoch": 0.02,
      "learning_rate": 9e-05,
      "loss": 1.5955,
      "step": 45
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0001,
      "loss": 1.5504,
      "step": 50
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00011000000000000002,
      "loss": 1.5621,
      "step": 55
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00012,
      "loss": 1.5142,
      "step": 60
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013000000000000002,
      "loss": 1.4386,
      "step": 65
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00014,
      "loss": 1.5017,
      "step": 70
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.4666,
      "step": 75
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00016,
      "loss": 1.4295,
      "step": 80
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00017,
      "loss": 1.4402,
      "step": 85
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00018,
      "loss": 1.4795,
      "step": 90
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00019,
      "loss": 1.4138,
      "step": 95
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0002,
      "loss": 1.4493,
      "step": 100
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001998259052924791,
      "loss": 1.4918,
      "step": 105
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019965181058495822,
      "loss": 1.4659,
      "step": 110
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019947771587743734,
      "loss": 1.4573,
      "step": 115
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019930362116991646,
      "loss": 1.4274,
      "step": 120
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019912952646239555,
      "loss": 1.4064,
      "step": 125
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00019895543175487465,
      "loss": 1.4048,
      "step": 130
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019878133704735376,
      "loss": 1.4493,
      "step": 135
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019860724233983288,
      "loss": 1.3317,
      "step": 140
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019843314763231198,
      "loss": 1.4041,
      "step": 145
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001982590529247911,
      "loss": 1.4311,
      "step": 150
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0001980849582172702,
      "loss": 1.3626,
      "step": 155
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00019791086350974934,
      "loss": 1.4296,
      "step": 160
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019773676880222843,
      "loss": 1.3888,
      "step": 165
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019756267409470752,
      "loss": 1.3389,
      "step": 170
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019738857938718664,
      "loss": 1.4544,
      "step": 175
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019721448467966573,
      "loss": 1.4382,
      "step": 180
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00019704038997214485,
      "loss": 1.4953,
      "step": 185
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019686629526462397,
      "loss": 1.4026,
      "step": 190
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019669220055710306,
      "loss": 1.3757,
      "step": 195
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00019651810584958218,
      "loss": 1.3247,
      "step": 200
    },
    {
      "epoch": 0.07,
      "eval_loss": 1.3710952997207642,
      "eval_runtime": 738.1164,
      "eval_samples_per_second": 7.038,
      "eval_steps_per_second": 0.881,
      "step": 200
    }
  ],
  "max_steps": 5844,
  "num_train_epochs": 2,
  "total_flos": 1.19119709995008e+16,
  "trial_name": null,
  "trial_params": null
}