training/evals_archive/v0-baseline/8b-full/eval_run.log

Evaluating 19 sessions against hermes3:8b
Skipping sessions with >20 human turns
------------------------------------------------------------
  [1/19] 20260323_154745_7c9379 (1 human turns)... composite=0.563 (17.3s)
  [2/19] 20260323_155153_bbc661 (1 human turns)... composite=0.681 (36.7s)
  [3/19] 20260323_155458_a7563d (1 human turns)... composite=0.521 (26.7s)
  [4/19] 20260323_160415_267a50 (1 human turns)... composite=0.000 (0.0s)
  [5/19] 20260323_160533_edc7cf (4 human turns)... composite=0.692 (35.1s)
  [6/19] 20260323_160633_6fab92 (1 human turns)... composite=0.000 (0.0s)
  [7/19] 20260323_160736_754836 (1 human turns)... composite=0.628 (7.4s)
  [8/19] 20260323_160920_c90867 (2 human turns)... composite=0.572 (34.5s)
  [9/19] 20260323_161348_d553f0 (1 human turns)... composite=0.634 (120.1s)
  [10/19] 20260323_162017_83fe11 (1 human turns)... composite=0.562 (59.7s)
  [11/19] 20260323_162338_0267eb (2 human turns)... composite=0.612 (40.2s)
  [12/19] 20260323_162704_86f56f (1 human turns)... composite=0.623 (8.2s)
  [13/19] 20260323_163322_e45fa8 (1 human turns)... composite=0.624 (8.2s)
  [14/19] 20260323_163943_9ac5e0 (1 human turns)... composite=0.646 (120.0s)
  [15/19] 20260323_164605_a4aedf (1 human turns)... composite=0.644 (120.0s)
  [16/19] 20260323_164606_c000d8 (2 human turns)... composite=0.602 (26.8s)
  [17/19] 20260323_165414_a92bf6 (1 human turns)... composite=0.632 (18.3s)
  [18/19] 20260323_165533_940c49 (1 human turns)... composite=0.521 (17.9s)
  [19/19] 20260323_170039_2a191f (1 human turns)... composite=0.754 (8.2s)

============================================================
RESULTS — hermes3:8b
============================================================
  tool_selection           : 0.895
  length_ratio             : 0.221
  format_compliance        : 0.892
  text_similarity          : 0.039
  brevity                  : 0.719
  composite                : 0.553

Saved to ../evals/v0-baseline/8b-full/scores.json
feat: migrate autolora pipeline into training/ Per direction shift (the-nexus#542). Replaces the autolora repo (1,500 lines of custom pipeline code) with config files for existing tools: - axolotl.yaml: replaces train_modal.py (239 lines) - mlx-lora.yaml: replaces MLX training scripts - eval-tasks.yaml: replaces run_eval.py (300 lines) - Makefile: replaces run_vibes.py, compare.py, convert_to_mlx.py Data migrated as-is: - curated_dataset.jsonl (26 gold-standard conversations) - preference_pairs.jsonl (DPO pairs) - prompts_vibes.yaml, prompts_nexus_vibes.yaml - v0-baseline eval results (historical record) Thin glue kept: - build_curated.py (data authoring, not infrastructure) - ingest_trajectories.py (domain-specific quality filter) Dependencies: pip install axolotl mlx-lm lm-evaluation-harness 2026-03-25 23:05:45 +00:00			`Evaluating 19 sessions against hermes3:8b`
			`Skipping sessions with >20 human turns`
			`------------------------------------------------------------`
			`[1/19] 20260323_154745_7c9379 (1 human turns)... composite=0.563 (17.3s)`
			`[2/19] 20260323_155153_bbc661 (1 human turns)... composite=0.681 (36.7s)`
			`[3/19] 20260323_155458_a7563d (1 human turns)... composite=0.521 (26.7s)`
			`[4/19] 20260323_160415_267a50 (1 human turns)... composite=0.000 (0.0s)`
			`[5/19] 20260323_160533_edc7cf (4 human turns)... composite=0.692 (35.1s)`
			`[6/19] 20260323_160633_6fab92 (1 human turns)... composite=0.000 (0.0s)`
			`[7/19] 20260323_160736_754836 (1 human turns)... composite=0.628 (7.4s)`
			`[8/19] 20260323_160920_c90867 (2 human turns)... composite=0.572 (34.5s)`
			`[9/19] 20260323_161348_d553f0 (1 human turns)... composite=0.634 (120.1s)`
			`[10/19] 20260323_162017_83fe11 (1 human turns)... composite=0.562 (59.7s)`
			`[11/19] 20260323_162338_0267eb (2 human turns)... composite=0.612 (40.2s)`
			`[12/19] 20260323_162704_86f56f (1 human turns)... composite=0.623 (8.2s)`
			`[13/19] 20260323_163322_e45fa8 (1 human turns)... composite=0.624 (8.2s)`
			`[14/19] 20260323_163943_9ac5e0 (1 human turns)... composite=0.646 (120.0s)`
			`[15/19] 20260323_164605_a4aedf (1 human turns)... composite=0.644 (120.0s)`
			`[16/19] 20260323_164606_c000d8 (2 human turns)... composite=0.602 (26.8s)`
			`[17/19] 20260323_165414_a92bf6 (1 human turns)... composite=0.632 (18.3s)`
			`[18/19] 20260323_165533_940c49 (1 human turns)... composite=0.521 (17.9s)`
			`[19/19] 20260323_170039_2a191f (1 human turns)... composite=0.754 (8.2s)`

			`============================================================`
			`RESULTS — hermes3:8b`
			`============================================================`
			`tool_selection : 0.895`
			`length_ratio : 0.221`
			`format_compliance : 0.892`
			`text_similarity : 0.039`
			`brevity : 0.719`
			`composite : 0.553`

			`Saved to ../evals/v0-baseline/8b-full/scores.json`