hrezaei/T5LAA2

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

T5LAA2

This model is part of the work published in the paper Interactive Text Games: Lookahead Is All You Need!

Four models are introduced in the above paper:

• —nanoGPTLA
• —nanoGPTLAA
• —nanoGPTLAA2
• —nanoGPTLAE

These models are implemented in this repository which is a customized version of nanoGPT.

The same variations are also implemented in this fork of Transformers library, on top of Google-t5/T5 implementation. These models are also trained and published as follows:

• —T5LA
• —T5LAA
• —T5LAA2
• —T5LAE

All the above models are on the scale of GPT2 (~100M parameters). The work is in progress to train them on larger scales.

Model description

This model is not fine-tuned on any instruction or human feedback datasets. It is just pre-trained on the HuggingFaceFW/fineweb sample-10BT dataset. It achieves the following results on the evaluation set:

• —Loss: 4.9746
• —Accuracy: 0.0349

Since the above fork is not merged into the main Transformers library yet, if you need to load it with AutoModel.frompretrained(), you need to first install Transformers from [this branch](https://github.com/HRezaei/transformers/tree/feature/lookaheadmodels), which contains the code for T5LA models. This can be done by:

pip install git+https://github.com/HRezaei/transformers.git@feature/lookahead_models

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 5e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 2
• —totaltrainbatch_size: 16
• —totalevalbatch_size: 16
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —training_steps: 200000
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —Transformers 4.49.0.dev0
• —Pytorch 2.5.1+cu121
• —Datasets 3.2.0
• —Tokenizers 0.21.0