smcleish's picture
Update README.md
082438f verified
metadata
library_name: transformers
license: mit
base_model:
  - google/gemma-2b

Model Details

google/gemma-2b model finetuned on 100,000 CLRS-Text examples.

Training Details

  • Learning Rate: 1e-4, 150 warmup steps then cosine decayed to 5e-06 using AdamW optimiser
  • Batch size: 128
  • Loss taken over answer only, not on question.