qxde01

--finetuning_type freeze 错误

2

使用`--finetuning_type freeze`时，如果加载上次训练的结果 `--checkpoint_dir output10/checkpoint-900`继续训练 出现下面的错误 ``` File "src/train_sft.py", line 106, in main() File "src/train_sft.py", line 25, in main model, tokenizer = load_pretrained(model_args, finetuning_args, training_args.do_train, stage="sft") File "/root/autodl-tmp/ChatGLM-Efficient-Tuning/src/utils/common.py", line 236, in...

eForce 无法画图

1

eForce里面的例子 没画成功过，一片空白 ` networkMatrix

Early Termination of training：Progress 19.42%

7

nv: 1032440, ne: 987454 Need 0.257797 Mb for storing second-order degrees Generating a corpus for negative samples.. Using vectorized operations lr 0.020144, Progress 19.42% Calculations took 12.13 s to run

rwkv-7 代码和模型不一致

1

rwkv_v7_demo.py : args.vocab_size = 50304 01.b 实际：65536 ` raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format( RuntimeError: Error(s) in loading state_dict for RWKV: Missing key(s) in state_dict: "blocks.0.att.v0", "blocks.0.att.v1", "blocks.0.att.v2". size...