{
  "best_metric": 1.9207960367202759,
  "best_model_checkpoint": "output/mumiy-troll/checkpoint-58",
  "epoch": 1.0,
  "global_step": 58,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09,
      "learning_rate": 0.00013469952948681868,
      "loss": 2.6361,
      "step": 5
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0001273804022850966,
      "loss": 2.3605,
      "step": 10
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00011577618287734484,
      "loss": 2.2983,
      "step": 15
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00010073281903200561,
      "loss": 2.175,
      "step": 20
    },
    {
      "epoch": 0.43,
      "learning_rate": 8.334697219847626e-05,
      "loss": 2.4089,
      "step": 25
    },
    {
      "epoch": 0.52,
      "learning_rate": 6.488607087104036e-05,
      "loss": 2.117,
      "step": 30
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.6695915032671784e-05,
      "loss": 2.0639,
      "step": 35
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.0102567316140575e-05,
      "loss": 2.206,
      "step": 40
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.6315683018244145e-05,
      "loss": 2.149,
      "step": 45
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.340326210572357e-06,
      "loss": 2.0228,
      "step": 50
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.037005536513067e-07,
      "loss": 2.0298,
      "step": 55
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.9207960367202759,
      "eval_runtime": 3.4482,
      "eval_samples_per_second": 22.041,
      "eval_steps_per_second": 2.9,
      "step": 58
    }
  ],
  "max_steps": 58,
  "num_train_epochs": 1,
  "total_flos": 60227813376000.0,
  "trial_name": null,
  "trial_params": null
}