metadata
license: apache-2.0
base_model:
- meta-llama/Llama-3.1-8B-Instruct
A preview version of FuseChat-3.0, more details coming soon...
Training configs
# Model arguments
model_name_or_path: AALF/FuseChat-Llama-3.1-8B-SFT
torch_dtype: null
attn_implementation: flash_attention_2
# Data training arguments
dataset_mixer: FuseChat-Mixture-v3-DPO
dataset_splits:
- train
- test
preprocessing_num_workers: 12
# DPOTrainer arguments
bf16: true
beta: 10
avg_logp: true
gradient_accumulation_steps: 8
gradient_checkpointing: true
gradient_checkpointing_kwargs:
use_reentrant: False
hub_model_id: wrpo-models
learning_rate: 8.0e-7
log_level: info
logging_steps: 5
lr_scheduler_type: cosine
max_length: 2048
max_prompt_length: 1800
num_train_epochs: 1
optim: adamw_torch
output_dir: outputs/FuseChat-Llama-3.1-8B-Instruct
run_name: FuseChat-Llama-3.1-8B-Instruct
per_device_train_batch_size: 2
per_device_eval_batch_size: 4
push_to_hub: false
save_strategy: "steps"
save_steps: 101
save_total_limit: 20
seed: 42
warmup_ratio: 0.1
save_only_model: true