{
  "best_metric": 0.011942805722355843,
  "best_model_checkpoint": "/kaggle/working/checkpoint-9945",
  "epoch": 0.9999497260067367,
  "eval_steps": 500,
  "global_step": 9945,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10054798652656981,
      "grad_norm": 2.2476389408111572,
      "learning_rate": 8.994469582704878e-06,
      "loss": 0.0235,
      "step": 1000
    },
    {
      "epoch": 0.20109597305313962,
      "grad_norm": 2.1006860733032227,
      "learning_rate": 7.98994469582705e-06,
      "loss": 0.0249,
      "step": 2000
    },
    {
      "epoch": 0.3016439595797094,
      "grad_norm": 1.7575879096984863,
      "learning_rate": 6.984414278531926e-06,
      "loss": 0.0245,
      "step": 3000
    },
    {
      "epoch": 0.40219194610627923,
      "grad_norm": 2.2406935691833496,
      "learning_rate": 5.979889391654098e-06,
      "loss": 0.0245,
      "step": 4000
    },
    {
      "epoch": 0.502739932632849,
      "grad_norm": 1.5336138010025024,
      "learning_rate": 4.974358974358975e-06,
      "loss": 0.0236,
      "step": 5000
    },
    {
      "epoch": 0.6032879191594188,
      "grad_norm": 2.5202527046203613,
      "learning_rate": 3.968828557063851e-06,
      "loss": 0.0231,
      "step": 6000
    },
    {
      "epoch": 0.7038359056859886,
      "grad_norm": 1.9651978015899658,
      "learning_rate": 2.9632981397687283e-06,
      "loss": 0.0229,
      "step": 7000
    },
    {
      "epoch": 0.8043838922125585,
      "grad_norm": 1.8106822967529297,
      "learning_rate": 1.957767722473605e-06,
      "loss": 0.0221,
      "step": 8000
    },
    {
      "epoch": 0.9049318787391283,
      "grad_norm": 1.9274195432662964,
      "learning_rate": 9.532428355957768e-07,
      "loss": 0.0221,
      "step": 9000
    },
    {
      "epoch": 0.9999497260067367,
      "eval_loss": 0.011942805722355843,
      "eval_processing_time_ms": 148038.60187530518,
      "eval_runtime": 2020.6048,
      "eval_sacrebleu": 35.57162442858833,
      "eval_samples_per_second": 26.251,
      "eval_steps_per_second": 0.547,
      "step": 9945
    }
  ],
  "logging_steps": 1000,
  "max_steps": 9945,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0607417906783846e+17,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}