Buckets:
| # Wait for RL checkpoint-60 to be fully written, stop the RL session by name, then run the post-RL eval. | |
| cd /workspace/decision-reasoner/runs/v2 | |
| C=checkpoints/rl_grpo/checkpoint-60 | |
| until [ -f "$C/trainer_state.json" ] && [ -f "$C/adapter_model.safetensors" ]; do sleep 20; done | |
| sleep 60 # let the save finish (optimizer, rng state) | |
| echo "{\"time\": \"$(date -u +%FT%TZ)\", \"event\": \"stopped_at\", \"stage\": \"rl_grpo step 60\"}" >> ../../logs/v2_timeline.jsonl | |
| tmux kill-session -t rl4b | |
| sleep 30 | |
| CKPT=$C NAME=rl60 bash run_rl_eval.sh > ../../logs/rl_eval_driver.log 2>&1 | |
| echo "DRIVER_EXIT $?" >> ../../logs/rl_eval_driver.log | |
Xet Storage Details
- Size:
- 685 Bytes
- Xet hash:
- 0c69faf4f1b76038e3d50d34b25d6234044748b461b046125813751021511147
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.