metadata
datasets:
- bigscience/P3
language:
- en
An 11B T5 model trained on the P3 (T0 split) dataset for 20,000 steps with a batch size of 2048 a maximum input sequence length of 1024, a maximum output sequence length of 256, and the Adafactor optimizer with a constant learning rate of 0.001. The model is trained from the T5 v1.1 lm-adapt checkpoint and fully finetuned.
For more details, see HINT: Hypernetwork Instruction Tuning for Efficient Zero- & Few-Shot Generalisation.
Performance on T0 held-out tasks (average accuracy across prompts using rank classification):
| Model | ANLI (avg) | HellaSwag | StoryCloze | CB | COPA | RTE | WiC | WSC | WinoGrande | Average |
|---|---|---|---|---|---|---|---|---|---|---|
| T0-11B | 41.0 | 33.6 | 92.4 | 70.1 | 91.5 | 81.0 | 56.1 | 61.1 | 59.9 | 65.2 |
| hypertask_T0_11B (this model) | 46.8 | 34.1 | 98.2 | 81.2 | 96.6 | 84.0 | 52.1 | 62.6 | 64.8 | 68.9 |