Language Modeling on BabyLM STRICT-SMALL 10M words (test)
75.8BLIMP ScoreELC-BERT
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| ELC-BERTtraining_data=10M words, track=STRICT-SMALL2023.11 | 75.8 | 73.7 | 29.4 | 65.9 | |
| Too Much Informationtraining_data=10M words, track=STRICT-SMALL2023.11 | 75.7 | 70.9 | 3.9 | 59.9 | |
| Contextualizertraining_data=10M words, track=STRICT-SMALL2023.11 | 74.3 | 69.6 | 12.7 | 60.5 | |
| MSLMtraining_data=10M words, track=STRICT-SMALL2023.11 | 72.4 | 70.6 | 17.2 | 60.8 | |
| Baby Llamatraining_data=10M words, track=STRICT-SMALL2023.11 | 69.8 | 67.6 | 24.7 | 60.1 |