Document 100-episode merged run and 10-episode verification sample
Browse files
README.md
CHANGED
|
@@ -14,7 +14,19 @@ This is still a label-validation repository, not a policy repository. No `pi0.5`
|
|
| 14 |
|
| 15 |
## Current Status
|
| 16 |
|
| 17 |
-
The latest work in this upload
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
|
| 19 |
That run keeps the trusted `iter24` template bundle fixed, adds the fuller dense/debug logging in a single pass, and regenerates the episode-0 visualization suite from the richer artifact. It is the current reference for:
|
| 20 |
|
|
|
|
| 14 |
|
| 15 |
## Current Status
|
| 16 |
|
| 17 |
+
The latest work in this upload now includes:
|
| 18 |
+
|
| 19 |
+
- `artifacts/results/metric_iter30_full100_single_pass_full_logging_fixed_templates_merged/`
|
| 20 |
+
- merged 100-episode dense/fuller-logging result tree from the single-pass fixed-template run
|
| 21 |
+
- `artifacts/results/metric_iter31_sample10_all_metrics_verify/`
|
| 22 |
+
- compact 10-episode verification subset with `all_metrics` GIFs only
|
| 23 |
+
- the fast `all_metrics`-only render path in:
|
| 24 |
+
- `code/scripts/render_oven_metric_frame.py`
|
| 25 |
+
- `code/scripts/render_oven_metric_gifs.py`
|
| 26 |
+
|
| 27 |
+
The new sample verification bundle is meant to be the quickest remote sanity-check entry point. It includes the sampled dense/keyframe tables, per-episode metrics, fuller debug sidecars, fixed templates, selection metadata, and one compact full-metrics GIF per sampled episode.
|
| 28 |
+
|
| 29 |
+
The earlier `metric_iter29_ep0_single_pass_full_logging_fixed_templates` validation pass for episode 0 remains the detailed single-episode reference for the fuller debug logging and the debug-aware GIF renderer.
|
| 30 |
|
| 31 |
That run keeps the trusted `iter24` template bundle fixed, adds the fuller dense/debug logging in a single pass, and regenerates the episode-0 visualization suite from the richer artifact. It is the current reference for:
|
| 32 |
|