Text Generation
Transformers
PyTorch
English
mixformer-sequential
custom_code
bleysg commited on
Commit
01bf954
1 Parent(s): 2122e51

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -0
README.md CHANGED
@@ -39,6 +39,7 @@ oo-phi-1_5 5.03125
39
  # Training
40
 
41
  Trained with full-paramaters fine-tuning on 8x RTX A6000-48GB (Ampere) for 5 epochs for 62 hours (12.5h/epoch) at a commodity cost of $390 ($80/epoch).
 
42
 
43
  [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
44
 
 
39
  # Training
40
 
41
  Trained with full-paramaters fine-tuning on 8x RTX A6000-48GB (Ampere) for 5 epochs for 62 hours (12.5h/epoch) at a commodity cost of $390 ($80/epoch).
42
+ We did not use [MultiPack](https://github.com/imoneoi/multipack_sampler) packing, as training was begun prior to implementing support for it in Axolotl for this new model type.
43
 
44
  [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
45