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
..
small_exp	Refactor_and_improve_data (#7)	2025-08-04 20:52:37 +09:00
context_numbers_10.yaml	refactor after distillation (#6)	2025-07-30 18:38:51 +09:00
context_numbers_10_self_gen.yaml	Refactor_and_improve_data (#7)	2025-08-04 20:52:37 +09:00
fw_qa_v2_level_0.yaml	qa data exp	2025-06-26 15:30:26 +09:00
fw_qa_v2_level_1.yaml	qa data exp	2025-06-26 15:30:26 +09:00
fw_qa_v2_level_2.yaml	qa data exp	2025-06-26 15:30:26 +09:00
fw_qa_v2_level_3.yaml	clean up + configs + scripts	2025-06-24 21:51:33 +09:00
pwc_tiny.yaml	Add distillation training (#5)	2025-07-29 15:32:06 +09:00
qa_short_ctx.yaml	small configs	2025-07-21 09:03:58 +00:00
qa_short_ctx_compact.yaml	small configs	2025-07-21 09:03:58 +00:00
qa_short_ctx_self_gen.yaml	tiny configs + fix dataset gen (remove repeated response + qa template for compact ds) + add ropes and drop eval ds	2025-06-30 16:10:52 +09:00
qa_short_ctx_self_gen_no_fw_qa.yaml	Add distillation training (#5)	2025-07-29 15:32:06 +09:00
qa_short_ctx_self_gen_squad.yaml	Add distillation training (#5)	2025-07-29 15:32:06 +09:00
squad.yaml	transformers ver + squad only example	2025-06-20 21:38:26 +09:00
squad_compact.yaml	small configs	2025-07-21 09:03:58 +00:00
squad_fw_qa_v2_level_3.yaml	clean up + configs + scripts	2025-06-24 21:51:33 +09:00
squad_hotpot_qa.yaml	squad_hotpot config	2025-06-19 23:08:14 +09:00