--- license: cc-by-nc-4.0 base_model: mlabonne/NeuralMonarch-7B tags: - generated_from_trainer - axolotl - mistral - instruct - finetune - chatml - gpt4 - synthetic data - distillation model-index: - name: AlphaMonarch-laser results: [] datasets: - argilla/OpenHermes2.5-dpo-binarized-alpha language: - en library_name: transformers pipeline_tag: text-generation --- # AlphaMonarch-laser ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/64e380b2e12618b261fa6ba0/62S_ExHO6NKCM3NhPDrds.jpeg) AlphaMonarch-laser is a DPO fine-tuned of [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B/) using the [argilla/OpenHermes2.5-dpo-binarized-alpha](https://huggingface.co/datasets/argilla/OpenHermes2.5-dpo-binarized-alpha) preference dataset but achieves better performance then [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B/) using This model is a fine-tuned version of [mlabonne/NeuralMonarch-7B](https://huggingface.co/mlabonne/NeuralMonarch-7B) on ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-07 - train_batch_size: 1 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 100 - training_steps: 1080 ### 📝 Axolotl Configuration ```yaml base_model: mlabonne/NeuralMonarch-7B model_type: MistralForCausalLM tokenizer_type: LlamaTokenizer is_mistral_derived_model: true load_in_8bit: false load_in_4bit: true strict: false rl: dpo chat_template: chatml datasets: - path: mlabonne/chatml-OpenHermes2.5-dpo-binarized-alpha split: train type: chatml.intel dataset_prepared_path: val_set_size: 0.01 output_dir: ./out adapter: qlora lora_model_dir: sequence_len: 1800 sample_packing: false pad_to_sequence_len: false lora_r: 16 lora_alpha: 16 lora_dropout: 0.05 lora_target_linear: true lora_fan_in_fan_out: lora_target_modules: - layers.1.self_attn.q_proj - layers.0.self_attn.q_proj - layers.15.self_attn.q_proj - layers.12.self_attn.q_proj - layers.11.self_attn.q_proj - layers.14.self_attn.q_proj - layers.9.self_attn.q_proj - layers.16.self_attn.q_proj - layers.30.self_attn.q_proj - layers.18.self_attn.q_proj - layers.13.self_attn.q_proj - layers.10.self_attn.q_proj - layers.7.self_attn.q_proj - layers.8.self_attn.q_proj - layers.4.self_attn.q_proj - layers.19.self_attn.q_proj - layers.27.self_attn.k_proj - layers.24.self_attn.k_proj - layers.25.self_attn.k_proj - layers.22.self_attn.k_proj - layers.26.self_attn.k_proj - layers.29.self_attn.k_proj - layers.23.self_attn.k_proj - layers.28.self_attn.k_proj - layers.21.self_attn.k_proj - layers.31.self_attn.k_proj - layers.30.self_attn.k_proj - layers.20.self_attn.k_proj - layers.5.self_attn.k_proj - layers.19.self_attn.k_proj - layers.17.self_attn.k_proj - layers.18.self_attn.k_proj - layers.19.self_attn.v_proj - layers.24.self_attn.v_proj - layers.18.self_attn.v_proj - layers.5.self_attn.v_proj - layers.3.self_attn.v_proj - layers.16.self_attn.v_proj - layers.23.self_attn.v_proj - layers.27.self_attn.v_proj - layers.25.self_attn.v_proj - layers.26.self_attn.v_proj - layers.20.self_attn.v_proj - layers.6.self_attn.v_proj - layers.15.self_attn.v_proj - layers.17.self_attn.v_proj - layers.29.self_attn.v_proj - layers.22.self_attn.v_proj - layers.12.self_attn.o_proj - layers.9.self_attn.o_proj - layers.14.self_attn.o_proj - layers.0.self_attn.o_proj - layers.6.self_attn.o_proj - layers.8.self_attn.o_proj - layers.10.self_attn.o_proj - layers.11.self_attn.o_proj - layers.13.self_attn.o_proj - layers.24.self_attn.o_proj - layers.7.self_attn.o_proj - layers.15.self_attn.o_proj - layers.5.self_attn.o_proj - layers.17.self_attn.o_proj - layers.25.self_attn.o_proj - layers.4.self_attn.o_proj - layers.31.mlp.gate_proj - layers.30.mlp.gate_proj - layers.4.mlp.gate_proj - layers.3.mlp.gate_proj - layers.29.mlp.gate_proj - layers.28.mlp.gate_proj - layers.6.mlp.gate_proj - layers.27.mlp.gate_proj - layers.5.mlp.gate_proj - layers.26.mlp.gate_proj - layers.25.mlp.gate_proj - layers.7.mlp.gate_proj - layers.2.mlp.gate_proj - layers.24.mlp.gate_proj - layers.23.mlp.gate_proj - layers.10.mlp.gate_proj - layers.6.mlp.up_proj - layers.4.mlp.up_proj - layers.5.mlp.up_proj - layers.27.mlp.up_proj - layers.25.mlp.up_proj - layers.26.mlp.up_proj - layers.17.mlp.up_proj - layers.24.mlp.up_proj - layers.7.mlp.up_proj - layers.10.mlp.up_proj - layers.3.mlp.up_proj - layers.11.mlp.up_proj - layers.23.mlp.up_proj - layers.9.mlp.up_proj - layers.14.mlp.up_proj - layers.18.mlp.up_proj - layers.19.mlp.down_proj - layers.20.mlp.down_proj - layers.18.mlp.down_proj - layers.21.mlp.down_proj - layers.29.mlp.down_proj - layers.1.mlp.down_proj - layers.22.mlp.down_proj - layers.28.mlp.down_proj - layers.23.mlp.down_proj - layers.30.mlp.down_proj - layers.17.mlp.down_proj - layers.4.mlp.down_proj - layers.2.mlp.down_proj - layers.15.mlp.down_proj - layers.5.mlp.down_proj wandb_project: axolotl wandb_entity: wandb_watch: wandb_name: wandb_log_model: gradient_accumulation_steps: 8 micro_batch_size: 1 num_epochs: 1 optimizer: paged_adamw_32bit lr_scheduler: cosine learning_rate: 5e-7 train_on_inputs: false group_by_length: false bf16: true fp16: false tf32: true gradient_checkpointing: true early_stopping_patience: resume_from_checkpoint: local_rank: logging_steps: 1 xformers_attention: flash_attention: true warmup_steps: 100 evals_per_epoch: 1 eval_table_size: eval_table_max_new_tokens: 128 save_steps: 1080 max_steps: 1080 debug: deepspeed: weight_decay: 0.0 fsdp: fsdp_config: special_tokens: ``` ### Framework versions - Transformers 4.38.0.dev0 - Pytorch 2.1.2+cu118 - Datasets 2.17.0 - Tokenizers 0.15.0 - axolotl: 0.4.0 [Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl)