9 commits

Author	SHA1	Message	Date
51616	650395874f	toy exp w/ self-gen + use double bos for eval (following vllm 0.8.4)	2025-09-07 17:16:20 +09:00
51616	1201fcf7bc	watcher save state	2025-09-04 13:54:49 +00:00
51616	c30ae19a02	more robust watcher	2025-08-18 09:49:08 +00:00
Rujikorn Charakorn	891c0bd256	Refactor_and_improve_data (#7) ... * faster slice * add facts + ctx_qa * new configs * new scripts * intx_sft.py to train.py * add kaggle for downloading facts * max_new_tokens cli for eval * generate negative_nq * scripts + configs * default vals * max_val_samples_per_ds=500 * more efficient layer-to-layer ctx encoder * use_per_ctx_average_loss * faster processing * small exp distill * scripts * more robust watcher * per-module l1_norm avg * per-ctx average loss * clear_gpu	2025-08-04 20:52:37 +09:00
51616	82e44c72c8	more robust watcher	2025-07-22 00:48:29 +00:00
51616	0079464e42	max_qas_per_sample and fix flash attn w/ padded ctx!!	2025-07-21 09:08:22 +00:00
51616	dcda29bae6	watcher + partial refactor eval + debug train w/ pwc and hotpot	2025-06-02 09:02:20 +00:00
Rujikorn Charakorn	9f986cf938	rearrange + move to uv (#1)	2025-05-27 21:18:15 +09:00
51616	cce43deb64	restructure	2025-01-17 17:41:10 +00:00

Renamed from hyperlora/watcher.py (Browse further)