diff --git a/docs/docs/models/geneformer.md b/docs/docs/models/geneformer.md index ee37a9281..0d506102b 100644 --- a/docs/docs/models/geneformer.md +++ b/docs/docs/models/geneformer.md @@ -150,11 +150,11 @@ NVIDIA believes Trustworthy AI is a shared responsibility and we have establishe ### geneformer-10M -Training was performed on 8 servers with 8 A100 GPUs each for a total of 81485 steps using the CELLxGENE split with a per-gpu micro batch size 32 and global batch size of 2048. Training took a total of 4 days, 8 hours of wallclock time. As can be seen in the following images, training and validation curves both decreased fairly smoothly throughout the course of training. +Training was performed on 8 servers with 8 A100 GPUs each for a total of 81485 steps using the CELLxGENE split with a per-gpu micro batch size 32 and global batch size of 2048. Training took a total of 4 days, 8 hours of wallclock time. As can be seen in the following images, training and validation curves both decreased fairly smoothly throughout the course of training. ![Training Loss Geneformer 10M](../assets/images/geneformer/geneformer_10m_training_loss.png) ![Validation Loss Geneformer 10M](../assets/images/geneformer/geneformer_10m_val_loss.png) - + ### geneformer-106M @@ -204,8 +204,9 @@ Elmentaite et al. (2020), Developmental Cell. This dataset contains approximatel For more details see the example notebook titled Geneformer-celltype-classification-example.ipynb -![F1-score for both released models, a random baseline, and a PCA based transformation of the raw expression.](../assets/images/geneformer/F1-score-models-04-18-25.png) -![Average accuracy across cell types for both released models, a random baseline, and a PCA based transformation of the raw expression.](../assets/images/geneformer/average-accuracy-models-04-18-25.png) + +![F1-score for both released models, a random baseline, and a PCA based transformation of the raw expression.](../assets/images/geneformer/F1-score-models-04-18-2025.png) +![Average accuracy across cell types for both released models, a random baseline, and a PCA based transformation of the raw expression.](../assets/images/geneformer/average-accuracy-models-04-18-2025.png) ### Performance Benchmarks