README
rugpt3xl
Model was trained with 512 sequence length using Deepspeed and Megatron code by SberDevices team, on 80B tokens dataset for 4 epochs. After that model was finetuned 1 epoch with sequence length 2048.
Note! Model has sparse attention blocks.
Total training time was around 10 days on 256 GPUs.
Final perplexity on test set is 12.05.
Model parameters: 1.3B.
Contributors
Similar repos
Used in code
Linked in READMEs
README
rugpt3xl
Model was trained with 512 sequence length using Deepspeed and Megatron code by SberDevices team, on 80B tokens dataset for 4 epochs. After that model was finetuned 1 epoch with sequence length 2048.
Note! Model has sparse attention blocks.
Total training time was around 10 days on 256 GPUs.
Final perplexity on test set is 12.05.
Model parameters: 1.3B.