reproducing your results

Hi folks, thanks for your help with understanding unlimiformer so far. My team and I trying to reproduce your training results from the paper using the following:
```
python src/run.py \
src/configs/training/base_training_args.json \
src/configs/data/gov_report.json \
--output_dir output_train_bart_base_local/ \
--learning_rate 1e-5 \
--model_name_or_path facebook/bart-base \
--eval_steps 1000 --save_steps 1000 \
--per_device_eval_batch_size 1 --per_device_train_batch_size 2 \
--extra_metrics bertscore \
--unlimiformer_training \
--max_source_length 16384 \
--test_unlimiformer --eval_max_source_length 999999 --do_eval=True \
> output/output${SLURM_JOB_ID}.txt
```
My understanding is that we should be reproducing Table 4: (56.6 / 26.3 / 27.6 / 68.2) for (Rouge 1 / 2/ L/ BERTScore). Here is a link to a wandb report of a full run we have produced (it took about 11 hours):
https://api.wandb.ai/links/unlimiformer-kg/y29tbk1n

The max_source_length 16384 is a concern given that the training set has some enormous documents. The dataset has a very long tail: plenty over 50k tokens and even one with 250k tokens.

I'll let you know how a second run goes overnight. (I've just cloned your repo and, just to be sure, here is a screen shot of my slurm job:

The issue is about reproducing training results from the paper. Start by examining the provided command in src/run.py and the configuration files src/configs/training/base_training_args.json and src/configs/data/gov_report.json. Check the dataset token lengths and the max_source_length setting. Review the WandB report to compare metrics. Look at the training script and unlimiformer implementation to understand how long documents are handled. Verify the evaluation steps and metrics calculation.

Escrita pelo modelo de indexação a partir do texto da issue.