{
  "best_metric": 0.9924605488777161,
  "best_model_checkpoint": "bygpt5_quatags/medium/de/checkpoint-126920",
  "epoch": 7.999984242290541,
  "global_step": 126920,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 3.948825306755581e-05,
      "loss": 1.1845,
      "step": 15865
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.065978765487671,
      "eval_runtime": 768.0142,
      "eval_samples_per_second": 36.725,
      "eval_steps_per_second": 4.591,
      "step": 15865
    },
    {
      "epoch": 2.0,
      "learning_rate": 3.7044424560391055e-05,
      "loss": 1.0667,
      "step": 31730
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.032117247581482,
      "eval_runtime": 767.5288,
      "eval_samples_per_second": 36.748,
      "eval_steps_per_second": 4.594,
      "step": 31730
    },
    {
      "epoch": 3.0,
      "learning_rate": 3.2828277417204576e-05,
      "loss": 1.0313,
      "step": 47595
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.0152138471603394,
      "eval_runtime": 766.8529,
      "eval_samples_per_second": 36.78,
      "eval_steps_per_second": 4.598,
      "step": 47595
    },
    {
      "epoch": 4.0,
      "learning_rate": 2.7278216356653993e-05,
      "loss": 1.0059,
      "step": 63460
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.0045779943466187,
      "eval_runtime": 766.1088,
      "eval_samples_per_second": 36.816,
      "eval_steps_per_second": 4.602,
      "step": 63460
    },
    {
      "epoch": 5.0,
      "learning_rate": 2.0971349547678654e-05,
      "loss": 0.9863,
      "step": 79325
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.9978464841842651,
      "eval_runtime": 768.9099,
      "eval_samples_per_second": 36.682,
      "eval_steps_per_second": 4.586,
      "step": 79325
    },
    {
      "epoch": 6.0,
      "learning_rate": 1.4563479569054354e-05,
      "loss": 0.9709,
      "step": 95190
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.9945968389511108,
      "eval_runtime": 767.824,
      "eval_samples_per_second": 36.734,
      "eval_steps_per_second": 4.592,
      "step": 95190
    },
    {
      "epoch": 7.0,
      "learning_rate": 8.720911542440145e-06,
      "loss": 0.9593,
      "step": 111055
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.993177056312561,
      "eval_runtime": 767.6275,
      "eval_samples_per_second": 36.743,
      "eval_steps_per_second": 4.593,
      "step": 111055
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.051169186756774e-06,
      "loss": 0.9513,
      "step": 126920
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.9924605488777161,
      "eval_runtime": 766.8127,
      "eval_samples_per_second": 36.782,
      "eval_steps_per_second": 4.598,
      "step": 126920
    }
  ],
  "max_steps": 158650,
  "num_train_epochs": 10,
  "total_flos": 7.396317829251072e+17,
  "trial_name": null,
  "trial_params": null
}