distilling-step-by-step
distilling-step-by-step copied to clipboard
google-research
D:\Users\MFL\anaconda3\envs\distill\pythonw.exe C:\Users\MFL\Desktop\distilling-step-by-step-main\distilling-step-by-step-main\run.py Traceback (most recent call last): File "C:\Users\MFL\Desktop\distilling-step-by-step-main\distilling-step-by-step-main\run.py", line 18, in from datasets import DatasetDict, concatenate_datasets File "D:\Users\MFL\anaconda3\envs\distill\lib\site-packages\datasets\__init__.py", line 24, in import pyarrow File "D:\Users\MFL\anaconda3\envs\distill\lib\site-packages\pyarrow\__init__.py", line 65, in import...
I am looking at the files inside llm folder of anli1, the val_cot_0 has more than 1400 samples (I looked the number of "so the answer is" in the file)...
Hello, I try to run and train `python run.py --from_pretrained google/t5-v1_1-base --dataset cqa --model_type task_prefix --label_type llm --llm palm --alpha 0.5 --batch_size 64` The google/t5-v1_1-base model was downloaded from Hugging...
Hello, I've run and training starts successfully. `python run.py --from_pretrained google/t5-v1_1-base --dataset cqa --model_type task_prefix --label_type gt --llm palm --alpha 0.5 --batch_size 64` However, I get `'eval_test_loss': nan` and `ckpt`...
It's possible to download the distilled/trained models (from google/t5-v1_1-small, google/t5-v1_1-base, google/t5-v1_1-large, google/t5-v1_1-xxl), in order to do some evaluation or more finetuning on them?
Hello, I'm interested in the Few-Shot Examples you used when generating rationales with the LLM model, specifically the PaLM and GPT-NeoX-20B. Could you kindly share them with the community? Thank...
Could you please report numerical results of the experiments? I conduct the standard finetuning on 8*3090s with: `python run.py --from_pretrained google/t5-v1_1-base --dataset cqa --model_type standard --label_type gt --batch_size 64 --grad_steps...
Have you tried other values?
