sbuedenb/beetle-gpn

<!-- 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. -->

third-try-big-data

This model is a a GPN trained on the sbuedenb/bigbeetledataset dataset. It achieves the following results on the evaluation set:

• —Loss: 1.1655

Model description

The default GPN configuration was used.

Intended uses & limitations

This model is meant for DNA analysis of the Cucujiformia infraorder of insects.

Training and evaluation data

The dataset was created from 12 NCBI reference genomes from Cucujiformia.

Training procedure

240000 steps with linear LR 30000 steps with cosine LR

Training hyperparameters

The following hyperparameters were used for first 240000 steps training:

• —learning_rate: 0.001
• —trainbatchsize: 256
• —evalbatchsize: 256
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 4
• —totaltrainbatch_size: 1024
• —totalevalbatch_size: 1024
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: linear
• —training_steps: 240000

The following hyperparameters were used for last 30000 steps training:

• —learning_rate: 0.001
• —trainbatchsize: 256
• —evalbatchsize: 256
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 4
• —totaltrainbatch_size: 1024
• —totalevalbatch_size: 1024
• —optimizer: Use adamwtorch with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: cosine
• —training_steps: 270000

Training results

Framework versions

• —Transformers 4.51.3
• —Pytorch 2.7.0+cu126
• —Datasets 3.6.0.dev0
• —Tokenizers 0.21.1