Training hyperparameters LoRA: r=16 lora_alpha=16 lora_dropout=0.05 bias="none" task_type="CAUSAL_LM" target_modules=['k_proj', 'gate_proj', 'v_proj', 'up_proj', 'q_proj', 'o_proj', 'down_proj']

Training arguments: auto_find_batch_size=True gradient_checkpointing=True learning_rate=5e-7 lr_scheduler_type="cosine" max_steps=3922 optim="paged_adamw_32bit" warmup_steps=100

DPOTrainer: beta=0.1 max_prompt_length=1024 max_length=1536

Arxiv link: https://arxiv.org/abs/2403.02745

Downloads last month
52
Safetensors
Model size
7.24B params
Tensor type
FP16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for sonthenguyen/OpenHermes-2.5-Mistral-7B-mt-bench-DPO-recovered

Quantizations
2 models