self_gen parquet pattern + configs

This commit is contained in:
51616 2025-07-10 09:09:28 +00:00
parent c39e44cc90
commit f60d98aa8b
4 changed files with 30 additions and 22 deletions

View file

@ -39,7 +39,7 @@ target_modules:
# data
train_ds_names:
- self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/fw_qa_v2_2k_len_level_1_small
- self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/fw_qa_v2/min_0_to_2000/*level_0.parquet
- self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/pwc_compact
# these provide exact tokens needed, no need to use self-gen data
- squad_compact

View file

@ -39,7 +39,7 @@ target_modules:
# data
train_ds_names:
- self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.5/fw_qa_v2_2k_len_level_3_small
- self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.5/fw_qa_v2/min_0_to_2000/*level_3.parquet
- self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/pwc_compact
# these provide exact tokens needed, no need to use self-gen data
- squad_compact

View file

@ -39,7 +39,7 @@ target_modules:
# data
train_ds_names:
- self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/fw_qa_v2_2k_len_level_3_small
- self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/fw_qa_v2/min_0_to_2000/*level_3.parquet
- self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/pwc_compact
# these provide exact tokens needed, no need to use self-gen data
- squad_compact