{
  "best_metric": 0.860730593607306,
  "best_model_checkpoint": "tmp/tst-translation354/checkpoint-840",
  "epoch": 10.0,
  "global_step": 1050,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_accuracy": 0.3698630136986301,
      "eval_loss": 0.3618854582309723,
      "eval_runtime": 11.9681,
      "eval_samples_per_second": 36.597,
      "eval_steps_per_second": 3.092,
      "step": 105
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7351598173515982,
      "eval_loss": 0.1750085949897766,
      "eval_runtime": 13.2291,
      "eval_samples_per_second": 33.109,
      "eval_steps_per_second": 2.797,
      "step": 210
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7922374429223744,
      "eval_loss": 0.14155679941177368,
      "eval_runtime": 12.7875,
      "eval_samples_per_second": 34.252,
      "eval_steps_per_second": 2.893,
      "step": 315
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8424657534246576,
      "eval_loss": 0.12254055589437485,
      "eval_runtime": 14.2052,
      "eval_samples_per_second": 30.834,
      "eval_steps_per_second": 2.605,
      "step": 420
    },
    {
      "epoch": 4.76,
      "learning_rate": 2.6190476190476192e-05,
      "loss": 0.3579,
      "step": 500
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8515981735159818,
      "eval_loss": 0.13104116916656494,
      "eval_runtime": 12.6738,
      "eval_samples_per_second": 34.559,
      "eval_steps_per_second": 2.919,
      "step": 525
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.8424657534246576,
      "eval_loss": 0.1357753723859787,
      "eval_runtime": 12.4892,
      "eval_samples_per_second": 35.07,
      "eval_steps_per_second": 2.963,
      "step": 630
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.8493150684931506,
      "eval_loss": 0.16049088537693024,
      "eval_runtime": 12.626,
      "eval_samples_per_second": 34.69,
      "eval_steps_per_second": 2.93,
      "step": 735
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.860730593607306,
      "eval_loss": 0.1871233731508255,
      "eval_runtime": 12.5302,
      "eval_samples_per_second": 34.956,
      "eval_steps_per_second": 2.953,
      "step": 840
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.8515981735159818,
      "eval_loss": 0.19895039498806,
      "eval_runtime": 12.66,
      "eval_samples_per_second": 34.597,
      "eval_steps_per_second": 2.923,
      "step": 945
    },
    {
      "epoch": 9.52,
      "learning_rate": 2.3809523809523808e-06,
      "loss": 0.054,
      "step": 1000
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.860730593607306,
      "eval_loss": 0.2134334295988083,
      "eval_runtime": 12.5085,
      "eval_samples_per_second": 35.016,
      "eval_steps_per_second": 2.958,
      "step": 1050
    },
    {
      "epoch": 10.0,
      "step": 1050,
      "total_flos": 8482350845952000.0,
      "train_loss": 0.1974729861531939,
      "train_runtime": 785.0626,
      "train_samples_per_second": 15.973,
      "train_steps_per_second": 1.337
    }
  ],
  "max_steps": 1050,
  "num_train_epochs": 10,
  "total_flos": 8482350845952000.0,
  "trial_name": null,
  "trial_params": null
}