Update README.md

README.md

@@ -11,10 +11,19 @@ base_model:
 
 <!-- Provide a quick summary of what the model is/does. -->
 
-A debug model fine-tuned on 128 token context on `PrimeIntellect/Reverse-Text-SFT`. To be used as warmed up model to RL in `vf-reverse-text`.
+A debug model fine-tuned on `willcb/R1-reverse-wikipedia-paragraphs-v1-1000`. To be used as warmed up model to RL in `vf-reverse-text`.
 
-Created with this training command from [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl) (commit hash: `ed25704`)
+Created with this training command from [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl) (commit hash: `8262560`)
 
 ```bash
-uv run sft @ configs/reverse_text/sft.toml --ckpt
-```
+uv run torchrun --nproc-per-node 8 src/prime_rl/trainer/sft/train.py \
+  --model.name PrimeIntellect/Qwen3-0.6B \
+  --data.name willcb/R1-reverse-wikipedia-paragraphs-v1-1000 \
+  --max-steps 100 \
+  --data.batch-size 16 \
+  --data.micro-batch-size 1 \
+  --data.seq-len 4096 \
+  --optim.lr 2e-5
+```
+
+Check the run out on [W&B](https://wandb.ai/primeintellect/mika/runs/odsfiekx?nw=nwusermikasenghaas_).