Hugging Face's logo

LorMolf
/
Connect4-CK

Model card Files
xet
 Community
Connect4-CK / README.md
LorMolf's picture
LorMolf
Update connect4 latest-best pointer
5ab28ac verified
preview code
|
Raw
History Blame Contribute Delete
1.44 kB

connect4 checkpoint

Accepted fixed-bot initialization checkpoint for the selected-five MuZero/EfficientZero training sequence.

  • Source run: connect4_hf_bot_mode_1m_20260522
  • Checkpoint: checkpoints/envstep_1000000.pth.tar
  • Uploaded: 2026-05-23T11:46:20+00:00

Latest Best Checkpoint

The current latest best checkpoint pointer for this repository is:

checkpoints/main5_bot_only_stabilize_overnight_20260524/ckpt_last.pth.tar

Metadata:

  • Game: connect4
  • Source run: main5_bot_only_stabilize_overnight_20260524
  • Checkpoint role: final bot-only stabilization ckpt_last.pth.tar
  • Local source at upload: /mnt/nvme/home/molfetta/molfetta-reasoning/models/main5_bot_only_stabilize_overnight_20260524/connect4/attempt-01_260524_201948/ckpt/ckpt_last.pth.tar
  • Checkpoint SHA256 at upload: 8c4430c0379133c879389372c0a60b3195ea44d48c57b7b25db02a3ae5349b0e
  • Final env steps: 199673
  • Validation note: final watchdog gate on 2026-05-24/2026-05-25 reported the last three non-initial fixed-bot evals at reward_mean=1.0; seat-swapped fixed-bot gate; seat1_reward_mean=1.0 and seat2_reward_mean=1.0.
  • Upload manifest: metadata/main5_bot_only_stabilize_overnight_20260524_latest_best_manifest.json

Older checkpoint files in this repository are preserved; this section is the canonical pointer to use when a consumer needs the latest best checkpoint.