run_name: camera-ready-ablation-onset-35pct-total-l2-held-33pct-b3-sequential-nld-eng-fineweb-100m hf_user: Beetle-FineWeb-100M model: architecture: pico n_layers: 14 d_model: 768 vocab_size: 50000 attention_n_heads: 12 attention_n_kv_heads: 1 max_seq_len: 512 batch_size: 64 position_emb_theta: 10000.0 activation_hidden_dim: 3072 norm_eps: 1.0e-05 dropout: 0.1 data: data_mix: B3 lang_sources: - Beetle-Data/nl-100M-pretok l2_streams: - Beetle-Data/en-for-nl-100M-pretok pretokenized: true pretokenized_cache_dir: ./pretok_cache/humanscale-100m/nld_L1-eng_L2 tokenizer: pretrained_tokenizer_path: Beetle-Data/tokenizer-nl-en dataset_source: fineweb vocab_size: 50000 vocab_sharing: shared type: bpe target_tokens: 100000000 output_dir: ./tokenizers/fineweb_humanscale_nld_L1-eng_L2_shared overwrite: false push_to_hub: true training: fabric: accelerator: cuda devices: 1 strategy: ddp precision: bf16-mixed optimization: optimizer: adamw lr: 0.0005 lr_warmup_steps: 500 lr_scheduler: linear_with_warmup max_steps: 10000 checkpointing: runs_dir: ./runs run_name: camera-ready-ablation-onset-35pct-total-l2-held-33pct-b3-sequential-nld-eng-fineweb-100m checkpoints_dir: checkpoints fabric_checkpoint_dir: fabric_checkpoint fabric_checkpoint_filename: checkpoint.pt logs_dir: logs save_every_n_steps: 1000 keep_local_checkpoints: 1 save_to_hf: true learning_dynamics: {} compute_gradients: false curriculum: type: smooth mode: tokens schedule: - kind: sigmoid_ramp from_weights: l1: 1.0 l2: 0.0 to_weights: l1: 0.4846 l2: 0.5154 midpoint: 0.35 steepness: 12.0 ewc: enabled: false maml: enabled: false generative_replay: enabled: false polca: enabled: false every_n_steps: 500 k_eigenvectors: 32 basis_rank: 32 holdout_batch_size: 8 holdout_seq_len: 512 artifact_dir: polca push_to_hf: false precision: fp32 monitoring: logging: log_level: INFO log_every_n_steps: 100 save_to_wandb: false wandb: project: '' entity: ''