diff --git a/README.md b/README.md index 3ddf848c..0ec5f8d2 100644 --- a/README.md +++ b/README.md @@ -43,9 +43,9 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/ ![benchmark](assets/benchmark.svg) -- Training Speed: the number of training samples processed per second during the training. (bs=4, cutoff_len=1024) -- BLEU Score: BLEU-4 score on the development set of the [advertising text generation](https://aclanthology.org/D19-1321.pdf) task. (bs=4, cutoff_len=1024) -- GPU Memory: Peak GPU memory usage in the 4-bit quantized training. (bs=1, cutoff_len=1024) +- **Training Speed**: the number of training samples processed per second during the training. (bs=4, cutoff_len=1024) +- **BLEU Score**: BLEU-4 score on the development set of the [advertising text generation](https://aclanthology.org/D19-1321.pdf) task. (bs=4, cutoff_len=1024) +- **GPU Memory**: Peak GPU memory usage in 4-bit quantized training. (bs=1, cutoff_len=1024) - We adopt `pre_seq_len=128` for ChatGLM's P-Tuning and `lora_rank=32` for LLaMA-Factory's LoRA tuning. ## Changelog diff --git a/README_zh.md b/README_zh.md index 2b1f5905..ec3882e0 100644 --- a/README_zh.md +++ b/README_zh.md @@ -43,9 +43,9 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/6ba60acc-e2e2-4bec-b846 ![benchmark](assets/benchmark.svg) -- Training Speed: 训练阶段每秒处理的样本数量。(批处理大小=4,截断长度=1024) -- BLEU Score: [广告文案生成](https://aclanthology.org/D19-1321.pdf)任务验证集上的 BLEU-4 分数。(批处理大小=4,截断长度=1024) -- GPU Memory: 4 比特量化训练的 GPU 显存峰值。(批处理大小=1,截断长度=1024) +- **Training Speed**: 训练阶段每秒处理的样本数量。(批处理大小=4,截断长度=1024) +- **BLEU Score**: [广告文案生成](https://aclanthology.org/D19-1321.pdf)任务验证集上的 BLEU-4 分数。(批处理大小=4,截断长度=1024) +- **GPU Memory**: 4 比特量化训练的 GPU 显存峰值。(批处理大小=1,截断长度=1024) - 我们在 ChatGLM 的 P-Tuning 中采用 `pre_seq_len=128`,在 LLaMA-Factory 的 LoRA 微调中采用 `lora_rank=32`。 ## 更新日志