mirror of
https://github.com/SakanaAI/doc-to-lora.git
synced 2026-07-23 17:01:04 +02:00
59 lines
1.1 KiB
YAML
59 lines
1.1 KiB
YAML
output_dir: "" # just a placeholder
|
|
bf16: true
|
|
model_name_or_path: google/gemma-3-1b-it
|
|
label_names: ["labels"]
|
|
# eval_on_start: True
|
|
# eval_strategy: "steps"
|
|
# eval_steps: 500
|
|
# save_strategy: "no"
|
|
# # save_steps: 500
|
|
# logging_strategy: "steps"
|
|
# logging_steps: 100
|
|
# use_liger_kernel: true
|
|
# remove_unused_columns: false
|
|
|
|
# needed to avoid OOM by compute the metrics batch by batch
|
|
# w/o this the trainer stores logits of all sample in memory...
|
|
# batch_eval_metrics: true
|
|
|
|
per_device_train_batch_size: 8
|
|
per_device_eval_batch_size: 8
|
|
max_val_samples_per_ds: 1000
|
|
# optim: schedule_free_adamw
|
|
|
|
learning_rate: 0.00004
|
|
# lr_scheduler_type: "constant_with_warmup"
|
|
neftune_noise_alpha: 1
|
|
weight_decay: 0.01
|
|
|
|
warmup_steps: 100
|
|
|
|
dataloader_prefetch_factor: 16
|
|
dataloader_num_workers: 8
|
|
|
|
# LoRA
|
|
lora_r: 8
|
|
lora_dropout: 0.0
|
|
target_modules:
|
|
- down_proj
|
|
|
|
# short ctx data
|
|
train_ds_names:
|
|
- fw_qa_v2_2k_len_level_3
|
|
- squad
|
|
- pwc
|
|
- drop
|
|
- ropes
|
|
|
|
# the contexts are kinda long-ish
|
|
# - narrativeqa
|
|
# - quoref
|
|
# - synthetic_convqa
|
|
|
|
val_ds_names:
|
|
- fw_qa_v2_2k_len_level_0
|
|
- squad
|
|
- drop
|
|
- ropes
|
|
- pwc
|
|
|