test VS transformers

Sources [1] MMLU Benchmark (Multi-task Language Understanding) | Papers With Code https://paperswithcode.com/sota/multi-task-language-understanding-on-mmlu [2] MMLU Dataset | Papers With Code https://paperswithcode.com/dataset/mmlu [3] hendrycks/test: Measuring Massive Multitask Language Understanding | ICLR 2021 - GitHub https://github.com/hendrycks/test [4] lukaemon/mmlu · Datasets at Hugging Face https://huggingface.co/datasets/lukaemon/mmlu [5] [2009.03300] Measuring Massive Multitask Language Understanding - arXiv https://arxiv.org/abs/2009.03300

With a score of 90.0%, Gemini Ultra is the first model to outperform human experts on MMLU (massive multitask language understanding), which uses a combination of 57 subjects such as math, physics, history, law, medicine and ethics for testing both world knowledge and problem-solving abilities.

One method for comparison is the MMLU https://arxiv.org/abs/2009.03300.

Because there are many benchmarks that measure different things.

You need to look at the benchmark that reflects your specific interest.

So in this case ("I wasn't impressed that 30B didn't seem to know who Captain Picard was") the closest relevant benchmark they performed is MMLU (Massive Multitask Language Understanding"[1].

In the LLAMA paper they publish a figure of 63.4% for the 5-shot average setting without fine tuning on the 65B model, and 68.9% after fine tuning. This is significantly better that the original GPT-3 (43.9% under the same conditions) but as they note:

> "[it is] still far from the state-of-the-art, that is 77.4 for GPT code-davinci-002 on MMLU (numbers taken from Iyer et al. (2022))"

InstructGPT[2] (which OpenAI points at as most relevant ChatGPT publication) doesn't report MMLU performance.

[1] https://github.com/hendrycks/test

[2] https://arxiv.org/abs/2203.02155

Benchmark result is 67.6% which is 7.6% improvement from Gopher. MMLU is multiple choice Q&A over various subjects. Questions can be found linked in this github repo (see data).

Is t5x an encoder/decoder architecture?

Some more general options.

The Flax ecosystem

https://github.com/google/flax?tab=readme-ov-file

or dm-haiku

https://github.com/google-deepmind/dm-haiku

were some of the best developed communities in the Jax AI field

Perhaps the “trax” repo? https://github.com/google/trax

Some HF examples https://github.com/huggingface/transformers/tree/main/exampl...

Sadly it seems much of the work is proprietary these days, but one example could be Grok-1, if you customize the details. https://github.com/xai-org/grok-1/blob/main/run.py

The HuggingFace transformers library already has support for a similar method called prompt lookup decoding that uses the existing context to generate an ngram model: https://github.com/huggingface/transformers/issues/27722

I don't think it would be that hard to switch it out for a pretrained ngram model.

Most of this tutorial is based on Hugging Face course about Transformers and on Niels Rogge's Transformers tutorials: make sure to check their work and give them a star on GitHub, if you please ❤️

* Superconvergence + LR range finder + Fast AI's Ranger21 optimizer was the goto optimizer for CNNs, and worked fabulously well, but on transformers, the learning rate range finder sadi 1e-3 was the best, whilst 1e-5 was better. However, the 1 cycle learning rate stuck. https://github.com/huggingface/transformers/issues/16013

Thanks! :) I'm pushing them into transformers, pytorch-gemma and collabing with the Gemma team to resolve all the issues :)

The RoPE fix should already be in transformers 4.38.2: https://github.com/huggingface/transformers/pull/29285

My main PR for transformers which fixes most of the issues (some still left): https://github.com/huggingface/transformers/pull/29402

If you want to tinker with the architecture Hugging Face has a FOSS implementation in transformers: https://github.com/huggingface/transformers/blob/main/src/tr...

If you want to reproduce the training pipeline, you couldn't do that even if you wanted to because you don't have access to thousands of A100s.

I am aware that using mixed precision reduces the stability of weight and there will be little consistency but don't expect it to be this much. I have attached the graph of evaluation metrics. If someone can give me some insight into this issue, that would be great.