Skip to content

Issues: EleutherAI/pythia

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Clear current search query, filters, and sorts
17 Open 57 Closed
17 Open 57 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Batch Viewer : Why Sequence Length 2049?
#123 by prakharg24 was closed Nov 2, 2023
12
Mismatch about the evaluation results
#118 by yuzc19 was closed Oct 30, 2023
11
What tool do you use for your data preprocessing/binarization?
#69 by ajesujoba was closed Apr 18, 2023
9
Host Pile pretokenized .bin and .idx megatron files?
#15 by haileyschoelkopf was closed Jan 2, 2023
1
7
Is there an access to the deduplicated version of the data with meta info?
#92 by Jason3900 was closed Jul 21, 2023
6
Weights of "step0" and "step1" checkpoints are identical for all pythia models
#83 by byungdoh was closed Apr 20, 2023
6
release of checkpoints of different steps
#101 by TobiasLee was closed May 26, 2023
5
Add more details for reproducing training runs
#79 by zplizzi was closed Apr 18, 2023
5
Validation Perplexities
#38 by shoaibahmed was closed Dec 31, 2022
5
Host Deduped Pile raw jsonls
#27 by haileyschoelkopf was closed Dec 22, 2022
5
Would it be possible to share training loss curves on the original Pythia models?
#145 by itsnamgyu was closed Jan 22, 2024
4
Ordering of deduplicated datasets?
#76 by zplizzi was closed Mar 20, 2023
4
Pythia few shot capabilities
#56 by AdirRahamim was closed Feb 2, 2023
4
Details about "EleutherAI/pythia-160m-seed*" models
#142 by IanMagnusson was closed Dec 12, 2023
3
the loss of pythia training
#97 by Wangpeiyi9979 was closed May 1, 2023
3
Are pythia_v0 and the new pythia_v1 models using the same input embedding matrix?
#85 by levmckinney was closed Apr 24, 2023
3
.
#140 by ParthaKrPaul was closed Dec 2, 2023
2
Convert the huggingface checkpoint to GPT-Neox checkpoint
#116 by ZhiYuanZeng was closed Aug 13, 2023
2
Error when running unshard_memmap.py
#114 by ShaneeyS was closed Nov 4, 2023
2
Possible error in Pythia-12B-deduped step 32000
#108 by smahdavi4 was closed Jun 15, 2023
2
pythia-12b checkpoints missing on HuggingFace for step4000 and step32000
#107 by byungdoh was closed Jun 4, 2023
2
Will memorization experimental codes be released?
#98 by chujiezheng was closed May 22, 2023
2
Fine-tuning recommendations
#96 by RainIwakura was closed Apr 28, 2023
2
Training time or approximation of TFLOPs?
#87 by zetian1025 was closed Apr 13, 2023
2
How was deduplication done?
#75 by theblackcat102 was closed Mar 27, 2023
2
ProTip! Adding no:label will show everything without a label.