Update README.md

README.md

@@ -11,7 +11,7 @@ https://wandb.ai/leon_at_work/soni_ablation_4b/workspace
 |---|---|---|
 | `Baseline 4B` | Baseline configuration used for comparison | 200 |
 | `a2_sapo` | Vanilla SAPO (norm_by_std=true + sapo + eps=0.2 + sequence_mean) | 200 |
-| a3_dr_grpo_pure | Dr.GRPO pure (grpo + regular + seq_mean_token_sum_norm + no-std + eps=0.2) | 200 |
+| `a3_dr_grpo_pure` | Dr.GRPO pure (grpo + regular + seq_mean_token_sum_norm + no-std + eps=0.2) | 200 |
 | `a4_length_norm_sqrt` | GRPO with sqrt length normalization (plus normalized reduction) | 200 |
 | `a5_sapo_on_sqrt` | SAPO on top of sqrt length-normalized setting | 200 |
 | `a6_eps_clip_02` | Sqrt length-normalized setting with PPO clip set to 0.2/0.2 | 200 |
@@ -28,7 +28,7 @@ Baseline reference (`Baseline 4B`):
 | Variant Folder | Parameter Delta vs `Baseline 4B` |
 |---|---|
 | `a2_sapo` | `advantage_estimator=grpo`; `policy_loss_type=sapo`; `loss_reduction=sequence_mean`; `eps_clip_low/high=0.2/0.2`; `grpo_norm_by_std=true` |
-| a3_dr_grpo_pure | advantage_estimator=grpo; policy_loss_type=regular; loss_reduction=seq_mean_token_sum_norm; eps_clip_low/high=0.2/0.2; grpo_norm_by_std=false |
+| `a3_dr_grpo_pure` | advantage_estimator=grpo; policy_loss_type=regular; loss_reduction=seq_mean_token_sum_norm; eps_clip_low/high=0.2/0.2; grpo_norm_by_std=false |
 | `a4_length_norm_sqrt` | `advantage_estimator=grpo_length_norm_sqrt`; `loss_reduction=seq_mean_token_sum_norm` |
 | `a5_sapo_on_sqrt` | same as `a4_length_norm_sqrt`, plus `policy_loss_type=sapo` |
 | `a6_eps_clip_02` | `a4`-style setup, with `eps_clip_low=0.2`, `eps_clip_high=0.2` |