xulangping comments

Repositories
Issues
Comments

Results 4 comments of


                                            xulangping

Checkpoint fails to load after training

same problem

Checkpoint fails to load after training

while use 7b, there is no problem , but when use 13b, same problem for 00005.bin, maybe oom? @ssemeniuta @thashim

Checkpoint fails to load after training

Loading checkpoint shards: 67%|████████████ | 4/6 [00:27

The step2 scoring looks correct but the step3 model is talking gibberish

> For the step2 scoring: `python3 training/step2_reward_model_finetuning/rw_eval.py --model_name_or_path output/reward-models/350m/ ==================Eval result============================ prompt: Human: Please tell me about Microsoft in a few sentence? Assistant: > > good_ans: Microsoft is a software...