readme: add evaluation section with show-casing the best model checkpoints

README.md

@@ -25,6 +25,21 @@ Following LMs were pretrained on the (10BT subset) of the famous [FineWeb](https
 * Token Dropping BERT-based - find the [best model checkpoint here](https://huggingface.co/model-garden-lms/bert-base-token-dropping-finewebs-901k)
 * TEAMS-based - fine the [best model checkpoint here](https://huggingface.co/model-garden-lms/teams-base-finewebs-1m)
 
+# ScandEval Evaluation
+
+To find the best checkpoints and compare our FineWeb-LMs to other models (BERT, ELECTRA and RoBERTa) we perform an evaluation using the great [ScandEval](https://github.com/ScandEval/ScandEval) library.
+
+| Model ID                                                                                                                                  |   Avg. Score | CoNLL-En                    | SST5                        | ScaLA-En                    | SQuAD                       |
+|-------------------------------------------------------------------------------------------------------------------------------------------|--------------|-----------------------------|-----------------------------|-----------------------------|-----------------------------|
+| [model-garden-lms/bert-base-finewebs-951k](https://huggingface.co/model-garden-lms/bert-base-finewebs-951k)                               |        69.41 | 89.25 ± 0.4 / 88.9 ± 0.37   | 58.17 ± 1.26 / 59.86 ± 1.65 | 58.83 ± 3.46 / 78.22 ± 2.11 | 55.66 ± 1.19 / 66.36 ± 1.42 |
+| [model-garden-lms/bert-base-token-dropping-finewebs-901k](https://huggingface.co/model-garden-lms/bert-base-token-dropping-finewebs-901k) |        68.01 | 88.98 ± 0.64 / 88.67 ± 0.55 | 57.79 ± 1.31 / 58.91 ± 1.85 | 54.25 ± 6.3 / 75.73 ± 3.54  | 54.4 ± 0.72 / 65.31 ± 1.01  |
+| [model-garden-lms/teams-base-finewebs-1m](https://huggingface.co/model-garden-lms/teams-base-finewebs-1m)                                 |    **72.64** | 89.27 ± 0.41 / 88.82 ± 0.41 | 59.58 ± 0.64 / 62.63 ± 3.0  | 66.72 ± 0.94 / 83.01 ± 0.45 | 59.95 ± 0.71 / 71.13 ± 0.58 |
+| [google-bert/bert-base-cased](https://huggingface.co/google-bert/bert-base-cased)                                                         |        62.26 | 87.39 ± 0.79 / 87.11 ± 0.66 | 54.49 ± 1.36 / 53.22 ± 1.15 | 52.08 ± 2.13 / 74.52 ± 1.31 | 38.63 ± 2.1 / 50.68 ± 1.87  |
+| [google/electra-base-discriminator](https://huggingface.co/google/electra-base-discriminator)                                             |        69.26 | 87.82 ± 0.69 / 86.83 ± 0.62 | 62.3 ± 1.12 / 55.93 ± 0.67  | 62.61 ± 1.21 / 80.85 ± 0.59 | 52.51 ± 0.86 / 65.2 ± 0.85  |
+| [FacebookAI/roberta-base](https://huggingface.co/FacebookAI/roberta-base)                                                                 |        68.96 | 90.35 ± 0.23 / 90.14 ± 0.2  | 60.95 ± 1.4 / 57.52 ± 1.97  | 50.64 ± 1.69 / 74.55 ± 0.9  | 57.82 ± 1.35 / 69.68 ± 1.02 |
+
+The TEAMS model outperforms RoBERTa and ELECTRA, which were trained on much more data and pretraining steps. All detailed results can be found in [this](https://huggingface.co/datasets/model-garden-lms/finewebs-scandeval-results) dataset repository.
+
 # ❤️ Acknowledgements
 
 This repository is the outcome of the last two years of working with TPUs from the awesome [TRC program](https://sites.research.google/trc/about/) and the [TensorFlow Model Garden](https://github.com/tensorflow/models) library.