| data: |
| shuffle: true |
| mean: true |
| multi: true |
| require_sequence_disjoint: true |
| source_schema: dna_inversion_hg38_multilen_v2 |
| source_corpus: data/hg38_multilen_seqdisjoint/hg38_multilen_seqdisjoint.h5 |
| ood_source_corpus: data/1000g_multilen_seqdisjoint/1000g_multilen_seqdisjoint.h5 |
| artifact_dir: data/hg38_multilen_seqdisjoint |
| fm_slug: dnabert2 |
| seq_lengths: |
| - 10 |
| - 15 |
| - 20 |
| - 25 |
| - 30 |
| - 35 |
| - 40 |
| - 45 |
| - 50 |
| - 60 |
| - 70 |
| - 80 |
| - 90 |
| - 100 |
| train_seq_lengths: |
| - 10 |
| - 15 |
| - 20 |
| - 25 |
| - 30 |
| - 35 |
| - 40 |
| - 45 |
| - 50 |
| - 60 |
| - 70 |
| - 80 |
| - 90 |
| - 100 |
| train_csvs: |
| - ${data.artifact_dir}/train_${data.fm_slug}_10_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_15_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_20_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_25_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_30_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_35_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_40_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_45_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_50_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_60_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_70_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_80_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_90_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/train_${data.fm_slug}_100_hg38_multilen_seqdisjoint.h5 |
| val_csvs: |
| - ${data.artifact_dir}/val_${data.fm_slug}_10_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_15_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_20_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_25_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_30_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_35_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_40_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_45_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_50_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_60_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_70_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_80_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_90_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/val_${data.fm_slug}_100_hg38_multilen_seqdisjoint.h5 |
| test_csvs: |
| - ${data.artifact_dir}/test_${data.fm_slug}_10_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_15_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_20_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_25_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_30_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_35_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_40_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_45_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_50_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_60_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_70_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_80_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_90_hg38_multilen_seqdisjoint.h5 |
| - ${data.artifact_dir}/test_${data.fm_slug}_100_hg38_multilen_seqdisjoint.h5 |
| seq_length: 100 |
| skip_sha256_check: true |
| normalization_method: standard |
| subset_fraction: null |
| embedding_dim: 768 |
| tokenizer: |
| type: huggingface |
| model_name: zhihan1996/DNABERT-2-117M |
| checkpoint: zhihan1996/DNABERT-2-117M |
| model: |
| model_file_name: model/query_decoder.py |
| model_name: query_decoder |
| model_type: query_decoder |
| mode: mean |
| d_model: 384 |
| nhead: 8 |
| num_layers: 6 |
| dim_feedforward: 1536 |
| dropout: 0.1 |
| n_context_tokens: 16 |
| aux_length_loss_weight: 0.5 |
| output_dim: 4 |
| hidden_dims: [] |
| optim: |
| lr: 0.001 |
| weight_decay: 0.0001 |
| eps: 1.0e-06 |
| epochs: 20 |
| batch_size: 32 |
| num_workers: 16 |
| grad_clip_norm: 1.0 |
| use_scheduler: true |
| scheduler: |
| max_lr: 0.0005 |
| pct_start: 0.3 |
| anneal_strategy: cos |
| div_factor: 25.0 |
| final_div_factor: 10000.0 |
| train: |
| seed: 42 |
| project: dna-embedding-inversion |
| run_name: null |
| use_wandb: false |
| log_interval: 10000 |
| device: cuda:0 |
| early_stopping: |
| enabled: false |
| patience: 5 |
| min_delta: 1.0e-05 |
| max_val_samples: null |
| nan_backoff: |
| skip_frac_threshold: 0.02 |
| lr_backoff: 0.5 |
|
|
