Files
foxhunt/crates/ml/benchmark_results/gpu_training_benchmark_20251017_082124.json
jgrusewski 9c3d741a08 refactor: restructure repo — crates/, bin/, testing/ layout
Move 17 library crates into crates/, CLI binary into bin/fxt,
consolidate 10 test crates into testing/, split config crate
from deployment config files.

Root directory reduced from 38+ to ~17 directories.
All Cargo.toml paths and build.rs proto refs updated.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-25 11:56:00 +01:00

125 lines
3.3 KiB
JSON

{
"timestamp": "2025-10-17T08:21:24.753360416+00:00",
"gpu_info": {
"device_name": "NVIDIA RTX 3050 Ti (4GB)",
"device_available": true,
"vram_total_mb": 4096.0,
"cuda_version": "12.8"
},
"data_info": {
"source": "Databento DBN files (6E.FUT - Euro Futures)",
"symbols": [
"6E.FUT"
],
"total_bars": 10000,
"date_range": "2024-01 to 2024-12"
},
"dqn_results": {
"model_name": "WorkingDQN",
"total_epochs": 10,
"statistics": {
"mean_seconds": 0.0010403124285714286,
"std_dev": 0.00008561190370864938,
"confidence_interval_95": [
0.0009611346234210708,
0.0011194902337217864
],
"p50_median": 0.001008157,
"p95": 0.0011756355,
"p99": 0.0012128127,
"coefficient_of_variation": 0.08229441594407637,
"num_samples": 7,
"outliers_removed": 0
},
"memory_peak_mb": 143.0,
"stability": {
"is_stable": false,
"has_nan_inf": false,
"gradient_health": "Healthy",
"loss_trend": "Diverging",
"warnings": [
"Loss diverging: increased from 4.203730 to 4.946043"
]
},
"batch_config": {
"batch_size": 230,
"gradient_accumulation_steps": 1,
"effective_batch_size": 230
},
"training_losses": [
4.985262870788574,
5.132430553436279,
4.777216911315918,
4.060189247131348,
6.4390106201171875,
3.9263854026794434,
5.328873634338379,
3.3559303283691406,
5.588294982910156,
4.303791046142578
],
"avg_loss": 4.789738559722901
},
"ppo_results": {
"model_name": "PPO",
"total_epochs": 10,
"statistics": {
"mean_seconds": 0.168184648125,
"std_dev": 0.005084581863015776,
"confidence_interval_95": [
0.16393383130977984,
0.17243546494022016
],
"p50_median": 0.1682371755,
"p95": 0.17534651304999999,
"p99": 0.17768017781,
"coefficient_of_variation": 0.03023214020840213,
"num_samples": 8,
"outliers_removed": 0
},
"memory_peak_mb": 145.0,
"stability": {
"is_stable": true,
"has_nan_inf": false,
"gradient_health": "Healthy",
"loss_trend": "Converging",
"warnings": []
},
"batch_config": {
"batch_size": 230,
"gradient_accumulation_steps": 1,
"effective_batch_size": 230
},
"total_training_time_ms": 1697.802204,
"epoch_times_ms": [
186.184101,
165.997634,
163.163858,
161.157464,
167.998949,
167.34253099999998,
178.26359399999998,
169.929077,
168.475402,
169.14631
],
"avg_policy_loss": 0.08274438,
"avg_value_loss": 0.5487219
},
"aggregate_metrics": {
"total_training_time_hours": 0.09372489129960317,
"total_memory_peak_mb": 145.0,
"all_stable": false,
"models_tested": [
"DQN",
"PPO"
]
},
"decision": {
"recommendation": "local_gpu",
"rationale": "Local GPU training is highly viable. Total time 0.1h (<24h threshold), cost $0.00 vs $0.05 cloud. Local GPU provides faster iteration cycles and zero network latency.",
"estimated_local_hours": 0.09372489129960317,
"estimated_cost_local_usd": 0.0021088100542410713,
"estimated_cost_cloud_usd": 0.049299292823591266
}
}