--- library_name: peft base_model: inflatebot/MN-12B-Mag-Mell-R1 tags: - axolotl - generated_from_trainer datasets: - ToastyPigeon/steve-and-marvin - ToastyPigeon/kimi-stories-completion - Alfitaria/bodinforg-completions model-index: - name: nemo-kimi-lora-2e results: [] --- [Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl)
See axolotl config axolotl version: `0.11.0.dev0` ```yaml # === Model Configuration === base_model: inflatebot/MN-12B-Mag-Mell-R1 load_in_8bit: false load_in_4bit: true # === HF Configuration === hub_model_id: ToastyPigeon/nemo-kimi-lora-2e hub_strategy: "checkpoint" # === Training Setup === num_epochs: 2 micro_batch_size: 1 gradient_accumulation_steps: 2 sequence_len: 32768 sequence_parallel_degree: 2 heads_k_stride: 1 sample_packing: true pad_to_sequence_len: false #max_steps: 10 # === Evaluation === val_set_size: 0.01 evals_per_epoch: 10 #eval_steps: 20 #max_steps: 60 #eval_table_size: eval_max_new_tokens: 128 eval_sample_packing: true #eval_strategy: "no" # === LoRA Configuration === adapter: qlora lora_model_dir: lora_r: 32 lora_alpha: 32 lora_dropout: 0.1 lora_target_linear: true lora_fan_in_fan_out: lora_target_modules: peft_use_rslora: false lora_modules_to_save: # - embed_tokens # - lm_head #fix_untrained_tokens: true #lora_mlp_kernel: true #lora_qkv_kernel: true #lora_o_kernel: true # === Hyperparameter Configuration === #optimizer: apollo_adamw_layerwise warmup_steps: 0 optimizer: adamw_torch_fused #optimizer: paged_adamw_8bit #optim_args: # enable_stochastic_rounding: true # enable_cautious: true # enable_8bit: true # Apollo-mini configuration: #optim_args: "proj=random,rank=128,scale=128.0,scale_type=tensor,update_proj_gap=100" # Regular Apollo configuration: # optim_args: #optim_target_modules: all_linear learning_rate: 5e-6 lr_scheduler: cosine #cosine_min_lr_ratio: 0.2 #lr_scheduler: cosine_with_min_lr #lr_scheduler_kwargs: # cosine_min_lr: 1e-6 weight_decay: 0.01 max_grad_norm: 1.0 #warmup_steps: 0 #warmup_ratio: 0.025 # === Data Configuration === #chat_template: jinja #chat_template_jinja: "{%- set default_system_message = \"You are Mistral Small 3, a Large Language Model (LLM) created by Mistral AI, a French startup headquartered in Paris. You obediently fulfill the user's requests.\" %}\n\n{{- bos_token }}\n\n{%- if messages[0]['role'] == 'system' %}\n {%- if messages[0]['content'] is string %}\n {%- set system_message = messages[0]['content'] %}\n {%- else %}\n {%- set system_message = messages[0]['content'][0]['text'] %}\n {%- endif %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set system_message = default_system_message %}\n {%- set loop_messages = messages %}\n{%- endif %}\n{{- '[SYSTEM_PROMPT]' + system_message + '[/SYSTEM_PROMPT]' }}\n\n{%- for message in loop_messages %}\n {%- if message['role'] == 'user' %}\n {%- if message['content'] is string %}\n {{- '[INST]' + message['content'] + '[/INST]' }}\n {%- else %}\n {{- '[INST]' }}\n {%- for bl (line truncated to 1000 characters) #chat_template: chatml special_tokens: pad_token: "" #tokenizer_use_mistral_common: true shuffle_merged_datasets: true datasets: - path: ToastyPigeon/steve-and-marvin type: completion data_files: marvin.json - path: ToastyPigeon/kimi-stories-completion type: completion - path: Alfitaria/bodinforg-completions type: completion dataset_prepared_path: last_run_prepared # === Plugins === plugins: - axolotl.integrations.liger.LigerPlugin - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin # === Hardware Optimization === #gradient_checkpointing: offload #gradient_checkpointing_kwargs: # use_reentrant: false liger_rope: true liger_rms_norm: true liger_layer_norm: true liger_glu_activation: true #liger_fused_linear_cross_entropy: true cut_cross_entropy: true #deepspeed: /workspace/axolotl/deepspeed_configs/zero2.json # === FSDP Config === fsdp: - full_shard - auto_wrap fsdp_config: fsdp_limit_all_gathers: true fsdp_sync_module_states: true fsdp_offload_params: true fsdp_activation_checkpointing: true fsdp_use_orig_params: false fsdp_cpu_ram_efficient_loading: true fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP fsdp_transformer_layer_cls_to_wrap: MistralDecoderLayer fsdp_state_dict_type: FULL_STATE_DICT fsdp_sharding_strategy: FULL_SHARD # === Wandb Tracking === wandb_project: Nemo # wandb_entity: [WANDB_ENTITY] # wandb_name: [WANDB_RUN_NAME] # === Checkpointing === saves_per_epoch: 10 save_total_limit: 1 # === Advanced Settings === output_dir: /workspace/aibox-standalone-pool/axolotl/nemo-writer-ckpts-2e bf16: auto flash_attention: true train_on_inputs: false group_by_length: false save_safetensors: true logging_steps: 1 gc_steps: 10 seed: 69 ```

# nemo-kimi-lora-2e This model is a fine-tuned version of [inflatebot/MN-12B-Mag-Mell-R1](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1) on the ToastyPigeon/steve-and-marvin, the ToastyPigeon/kimi-stories-completion and the Alfitaria/bodinforg-completions datasets. It achieves the following results on the evaluation set: - Loss: 2.5237 ## 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-06 - train_batch_size: 1 - eval_batch_size: 1 - seed: 69 - distributed_type: multi-GPU - num_devices: 2 - gradient_accumulation_steps: 2 - total_train_batch_size: 4 - total_eval_batch_size: 2 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: cosine - lr_scheduler_warmup_steps: 29 - training_steps: 984 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | No log | 0 | 0 | 2.9604 | | 2.6808 | 0.1016 | 50 | 2.7132 | | 3.1442 | 0.2033 | 100 | 2.6132 | | 2.8972 | 0.3049 | 150 | 2.5786 | | 2.4404 | 0.4065 | 200 | 2.5598 | | 2.5215 | 0.5081 | 250 | 2.5512 | | 2.5145 | 0.6098 | 300 | 2.5456 | | 2.5293 | 0.7114 | 350 | 2.5412 | | 2.5439 | 0.8130 | 400 | 2.5380 | | 2.2925 | 0.9146 | 450 | 2.5342 | | 2.4822 | 1.0163 | 500 | 2.5326 | | 2.382 | 1.1179 | 550 | 2.5299 | | 2.6777 | 1.2195 | 600 | 2.5282 | | 2.5493 | 1.3211 | 650 | 2.5264 | | 2.5682 | 1.4228 | 700 | 2.5257 | | 2.4425 | 1.5244 | 750 | 2.5248 | | 2.5204 | 1.6260 | 800 | 2.5243 | | 2.5435 | 1.7276 | 850 | 2.5239 | | 2.8078 | 1.8293 | 900 | 2.5237 | | 2.8416 | 1.9309 | 950 | 2.5237 | ### Framework versions - PEFT 0.15.2 - Transformers 4.52.4 - Pytorch 2.7.0+cu126 - Datasets 3.6.0 - Tokenizers 0.21.1