mirror of
https://github.com/wassname/alignment-handbook.git
synced 2026-06-27 17:29:09 +08:00
Kashif Rasul
95dc47218c
* update API * update deepspeed * update black * remove unused import * fix typos * fix typos in readmes * fix grammer * removed as it exists in superclass * fixes in readme * Update README.md Co-authored-by: Alvaro Bartolome <36760800+alvarobartt@users.noreply.github.com> * Update src/alignment/configs.py Co-authored-by: Alvaro Bartolome <36760800+alvarobartt@users.noreply.github.com> * Update src/alignment/configs.py Co-authored-by: Alvaro Bartolome <36760800+alvarobartt@users.noreply.github.com> * Update src/alignment/configs.py Co-authored-by: Alvaro Bartolome <36760800+alvarobartt@users.noreply.github.com> * Update src/alignment/configs.py Co-authored-by: Alvaro Bartolome <36760800+alvarobartt@users.noreply.github.com> * add back dataset_kwargs * use hub_model_revision in sft and dpo * fix duplicate --------- Co-authored-by: Alvaro Bartolome <36760800+alvarobartt@users.noreply.github.com>
41 lines
890 B
YAML
41 lines
890 B
YAML
# Model arguments
|
|
model_name_or_path: mistralai/Mistral-7B-v0.1
|
|
model_revision: main
|
|
torch_dtype: bfloat16
|
|
attn_implementation: flash_attention_2
|
|
|
|
# Data training arguments
|
|
dataset_mixer:
|
|
HuggingFaceH4/ultrachat_200k: 1.0
|
|
dataset_splits:
|
|
- train_sft
|
|
- test_sft
|
|
preprocessing_num_workers: 12
|
|
|
|
# SFT trainer config
|
|
bf16: true
|
|
do_eval: true
|
|
eval_strategy: epoch
|
|
gradient_accumulation_steps: 2
|
|
gradient_checkpointing: true
|
|
hub_model_id: zephyr-7b-sft-full
|
|
hub_strategy: every_save
|
|
learning_rate: 2.0e-05
|
|
log_level: info
|
|
logging_steps: 5
|
|
logging_strategy: steps
|
|
lr_scheduler_type: cosine
|
|
max_seq_length: 2048
|
|
max_steps: -1
|
|
num_train_epochs: 1
|
|
output_dir: data/zephyr-7b-sft-full
|
|
overwrite_output_dir: true
|
|
per_device_eval_batch_size: 16
|
|
per_device_train_batch_size: 32
|
|
push_to_hub: true
|
|
remove_unused_columns: true
|
|
report_to:
|
|
- tensorboard
|
|
save_strategy: "no"
|
|
save_total_limit: null
|
|
seed: 42 |