mirror of
https://github.com/hanzoai/open-instruct.git
synced 2026-11-02 13:38:22 +00:00
8710794223
* init pr * add script * clean config folders * organization * up * tokenizer fixes * Fix dpo script tokenizer setup + minor fixes (#184) * copy tokenizer setup * minor fixes --------- Co-authored-by: Hamish Ivison <[email protected]>
23 lines
728 B
YAML
23 lines
728 B
YAML
# Note, the exact model was trained on TPUs in a different repo
|
|
model_name_or_path: meta-llama/Llama-2-7b
|
|
model_revision: main
|
|
use_flash_attn: true
|
|
tokenizer_name: meta-llama/Llama-2-7b
|
|
use_slow_tokenizer: true
|
|
dataset_name: allenai/tulu-v2-sft-mixture
|
|
max_seq_length: 4096 # Note, reduced from 8192 to fit on one GPU with DeepSpeed Stage3
|
|
preprocessing_num_workers: 128
|
|
per_device_train_batch_size: 1 # note, this is set up for 8 GPUs
|
|
gradient_accumulation_steps: 16 # effective batch size 128 for tulu 2
|
|
learning_rate: 2.0e-05
|
|
lr_scheduler_type: linear
|
|
warmup_ratio: 0.03
|
|
weight_decay: 0.0
|
|
num_train_epochs: 3
|
|
output_dir: output/tulu_v2_7b/
|
|
with_tracking: true
|
|
report_to:
|
|
- wandb
|
|
logging_steps: 1
|
|
checkpointing_steps: epoch
|