mirror of
https://github.com/SakanaAI/doc-to-lora.git
synced 2026-07-26 17:11:02 +02:00
iclr 2026
This commit is contained in:
parent
76bf6981ba
commit
c21ba2b481
20 changed files with 1204 additions and 23 deletions
60
configs/large_exp/fw_qa_v3.yaml
Normal file
60
configs/large_exp/fw_qa_v3.yaml
Normal file
|
|
@ -0,0 +1,60 @@
|
|||
# LoRA
|
||||
lora_r: 8
|
||||
lora_dropout: 0.0
|
||||
target_modules:
|
||||
- down_proj
|
||||
|
||||
use_kl_loss: true
|
||||
|
||||
ctx_encoder_type: per_layer_activations
|
||||
n_latent_queries: 8
|
||||
num_blocks: 8
|
||||
num_self_attn_per_block: 0
|
||||
|
||||
# gradient_accumulation_steps: 11
|
||||
# max_packed_inp_len: 6144
|
||||
# max_packed_ctx_len: 6144
|
||||
|
||||
gradient_accumulation_steps: 8
|
||||
max_packed_inp_len: 8192
|
||||
max_packed_ctx_len: 8192
|
||||
|
||||
|
||||
# data
|
||||
train_ds_names:
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/fw_qa_v2/min_0_to_2000/train/*level_1*.parquet
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/fw_qa_v2/min_0_to_2000/train/*level_3*.parquet
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/pwc_compact
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/squad_compact
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/ropes_compact
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/drop_compact
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.0_summ_prob_0.0_struct_prob_0.1/smol-rewrite
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.0_summ_prob_0.0_struct_prob_0.1/smol-summarize
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.0_summ_prob_1.0_struct_prob_1.0/bookqa
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.0_summ_prob_1.0_struct_prob_1.0/gov_report_qa
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/openhermes
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/smol-magpie-ultra
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/systemchats
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.2_summ_prob_0.0_struct_prob_0.0/ctx-q-gsm
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.1_cot_prob_0.0_summ_prob_1.0_struct_prob_1.0/synthetic_convqa
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.1_cot_prob_0.0_summ_prob_1.0_struct_prob_1.0/tatqa
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.8_cot_prob_0.0_summ_prob_0.0_struct_prob_0.0/quoref
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.8_cot_prob_0.0_summ_prob_1.0_struct_prob_1.0/hotpot_qa
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.8_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/drop
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.8_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/pwc
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.8_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/ropes
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.8_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/squad
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.01_cot_prob_0.1_summ_prob_0.05_struct_prob_0.1/fw_qa_v3/min_0_to_8000
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.01_cot_prob_0.1_summ_prob_0.05_struct_prob_0.1/fw_qa_v3/min_0_to_10000
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.01_cot_prob_0.1_summ_prob_0.05_struct_prob_0.1/fw_qa_v3/min_0_to_15000
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.01_cot_prob_0.1_summ_prob_0.05_struct_prob_0.1/fw_qa_v3/min_0_to_20000
|
||||
|
||||
|
||||
|
||||
val_ds_names:
|
||||
- squad
|
||||
- pwc
|
||||
- drop
|
||||
- ropes
|
||||
- hotpot_qa
|
||||
- self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/fw_qa_v2/min_0_to_2000/train/*level_0_val*.parquet
|
||||
68
configs/large_exp/fw_qa_v3_only_0_to_20k.yaml
Normal file
68
configs/large_exp/fw_qa_v3_only_0_to_20k.yaml
Normal file
|
|
@ -0,0 +1,68 @@
|
|||
# LoRA
|
||||
lora_r: 8
|
||||
lora_dropout: 0.0
|
||||
target_modules:
|
||||
- down_proj
|
||||
|
||||
use_kl_loss: true
|
||||
|
||||
ctx_encoder_type: per_layer_activations
|
||||
n_latent_queries: 8
|
||||
num_blocks: 8
|
||||
num_self_attn_per_block: 0
|
||||
|
||||
# gradient_accumulation_steps: 11
|
||||
# max_packed_inp_len: 6144
|
||||
# max_packed_ctx_len: 6144
|
||||
|
||||
gradient_accumulation_steps: 8
|
||||
max_packed_inp_len: 8192
|
||||
max_packed_ctx_len: 8192
|
||||
|
||||
|
||||
# data
|
||||
train_ds_names:
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/fw_qa_v2/min_0_to_2000/train/*level_1*.parquet
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/fw_qa_v2/min_0_to_2000/train/*level_3*.parquet
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/pwc_compact
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/squad_compact
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/ropes_compact
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_1.0/drop_compact
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.0_summ_prob_0.0_struct_prob_0.1/smol-rewrite
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.0_summ_prob_0.0_struct_prob_0.1/smol-summarize
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.0_summ_prob_1.0_struct_prob_1.0/bookqa
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.0_summ_prob_1.0_struct_prob_1.0/gov_report_qa
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/openhermes
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/smol-magpie-ultra
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/systemchats
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0_cot_prob_0.2_summ_prob_0.0_struct_prob_0.0/ctx-q-gsm
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.1_cot_prob_0.0_summ_prob_1.0_struct_prob_1.0/synthetic_convqa
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.1_cot_prob_0.0_summ_prob_1.0_struct_prob_1.0/tatqa
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.8_cot_prob_0.0_summ_prob_0.0_struct_prob_0.0/quoref
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.8_cot_prob_0.0_summ_prob_1.0_struct_prob_1.0/hotpot_qa
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.8_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/drop
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.8_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/pwc
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.8_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/ropes
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.8_cot_prob_0.1_summ_prob_0.0_struct_prob_0.0/squad
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.01_cot_prob_0.1_summ_prob_0.05_struct_prob_0.1/fw_qa_v3/min_0_to_8000
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.01_cot_prob_0.1_summ_prob_0.05_struct_prob_0.1/fw_qa_v3/min_0_to_10000
|
||||
# - data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.01_cot_prob_0.1_summ_prob_0.05_struct_prob_0.1/fw_qa_v3/min_0_to_15000
|
||||
- data/raw_datasets/self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.01_cot_prob_0.1_summ_prob_0.05_struct_prob_0.1/fw_qa_v3/min_0_to_20000
|
||||
|
||||
|
||||
|
||||
val_ds_names:
|
||||
- squad
|
||||
- pwc
|
||||
- drop
|
||||
- ropes
|
||||
- hotpot_qa
|
||||
- booksum
|
||||
- self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/fw_qa_v2/min_0_to_2000/train/*level_0_val*.parquet
|
||||
- self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/ctx_qa/validation/*.parquet
|
||||
# - self_gen/google/gemma-2-2b-it_temp_0.0_closed_qa_prob_0.0/facts/validation/*.parquet
|
||||
|
||||
|
||||
# - negative_nq
|
||||
|
||||
|
||||
Loading…
Add table
Add a link
Reference in a new issue