8d89fe80ff
- Archive: 85 agent .txt files → docs/archive/agents/legacy_txt/ - Scripts: Move 110 shell scripts → scripts/ (keep deploy.sh in root) - Models: Move 18 .safetensors → ml/models/checkpoints/training_artifacts/ - Delete: 34 directories (~33GB freed) - target/, coverage_*, test artifacts - Build: Clean 14 build artifacts (.rlib, .o, .pid, binaries) - Tests: Move 14 .rs files → tests/standalone/ - SQL: Move 5 files → sql/ (keep init-db*.sql for Docker) - Wave 153: Archive to docs/archive/historical/wave153/ - Docs: Archive 9 markdown files to wave_d/reports/ and historical/ Total impact: ~34GB freed (both waves), root directory cleaned from 583 to ~40 essential files Directory count reduced from 65 to 31 (52% reduction) All historical data preserved in organized archive structure
28 lines
1.4 KiB
Diff
28 lines
1.4 KiB
Diff
--- a/ml/examples/hyperopt_mamba2_demo.rs
|
|
+++ b/ml/examples/hyperopt_mamba2_demo.rs
|
|
@@ -66,8 +66,9 @@ struct Args {
|
|
batch_size_min: usize,
|
|
|
|
- /// Maximum batch size for GPU memory constraints (default: 96 for RTX A4000 16GB)
|
|
- /// Examples: RTX 3050 Ti 4GB = 32, RTX A4000 16GB = 96, RTX 4090 24GB = 256
|
|
- #[arg(long, default_value = "96")]
|
|
+ /// Maximum batch size for GPU memory constraints (default: 180 for RTX A4000 16GB)
|
|
+ /// Validated safe limits based on VRAM analysis (AGENT_R3_A5_VRAM_ANALYSIS.md):
|
|
+ /// Examples: RTX 3050 Ti 4GB = 32, RTX A4000 16GB = 180, RTX 4090 24GB = 256
|
|
+ #[arg(long, default_value = "180")]
|
|
batch_size_max: usize,
|
|
}
|
|
|
|
--- a/ml/src/hyperopt/adapters/mamba2.rs
|
|
+++ b/ml/src/hyperopt/adapters/mamba2.rs
|
|
@@ -115,7 +115,8 @@ impl ParameterSpace for Mamba2Params {
|
|
fn continuous_bounds() -> Vec<(f64, f64)> {
|
|
vec![
|
|
(1e-5_f64.ln(), 1e-2_f64.ln()), // learning_rate (log scale)
|
|
- (4.0, 256.0), // batch_size (linear) - wide bounds, clamped by trainer config
|
|
+ (4.0, 180.0), // batch_size (linear) - validated safe for 16GB GPU
|
|
+ // See AGENT_R3_A5_VRAM_ANALYSIS.md for derivation
|
|
(0.0, 0.5), // dropout (linear)
|
|
(1e-6_f64.ln(), 1e-2_f64.ln()), // weight_decay (log scale)
|
|
(0.5_f64.ln(), 5.0_f64.ln()), // grad_clip (log scale)
|