--- library_name: transformers license: llama3.1 base_model: meta-llama/Meta-Llama-3.1-8B-Instruct tags: - generated_from_trainer datasets: - shisa-ai/shisav1-deepseek-ai_DeepSeek-V3-0324-reannotated-filtered - shisa-ai/shisa-v2-roleplaying-sft - shisa-ai/translation_expanded_master_set_filtered - shisa-ai/rewild-set - shisa-ai/magpie-ultra-set - shisa-ai/magpie-advanced-questions-set - shisa-ai/japan-magpie-set model-index: - name: outputs/ablation-139-shisav2.ds.gbs128.1e5-shisa-v2-llama-3.1-8b results: [] --- [Built with Axolotl](https://github.com/axolotl-ai-cloud/axolotl)
See axolotl config axolotl version: `0.8.0.dev0` ```yaml # train w/ shisa-ai/shisa-v1-athenev2-reannotated-filtered base_model: meta-llama/Meta-Llama-3.1-8B-Instruct model_type: LlamaForCausalLM tokenizer_type: AutoTokenizer load_in_8bit: false load_in_4bit: false strict: false # User Liger plugins: - axolotl.integrations.liger.LigerPlugin liger_rope: true liger_rms_norm: true liger_glu_activation: true liger_fused_linear_cross_entropy: true chat_template: llama3 datasets: - path: shisa-ai/shisav1-deepseek-ai_DeepSeek-V3-0324-reannotated-filtered # type: sharegpt deprecated type: chat_template field_messages: conversations message_field_role: from message_field_content: value - path: shisa-ai/shisa-v2-roleplaying-sft type: chat_template field_messages: conversations message_property_mappings: role: role content: content roles: system: - system assistant: - gpt - model - assistant user: - human - user roles_to_train: ["assistant"] - path: shisa-ai/translation_expanded_master_set_filtered split: train[:25%] type: chat_template field_messages: conversations message_property_mappings: role: role content: content roles: system: - system assistant: - gpt - model - assistant user: - human - user roles_to_train: ["assistant"] - path: shisa-ai/rewild-set split: train[:5%] type: chat_template field_messages: conversations message_property_mappings: role: role content: content roles: system: - system assistant: - gpt - model - assistant user: - human - user roles_to_train: ["assistant"] - path: shisa-ai/magpie-ultra-set split: train[:8%] type: chat_template field_messages: conversations message_property_mappings: role: role content: content roles: system: - system assistant: - gpt - model - assistant user: - human - user roles_to_train: ["assistant"] - path: shisa-ai/magpie-advanced-questions-set split: train[:8%] type: chat_template field_messages: conversations message_property_mappings: role: role content: content roles: system: - system assistant: - gpt - model - assistant user: - human - user roles_to_train: ["assistant"] - path: shisa-ai/japan-magpie-set split: train type: chat_template field_messages: conversations message_property_mappings: role: role content: content roles: system: - system assistant: - gpt - model - assistant user: - human - user roles_to_train: ["assistant"] dataset_prepared_path: last_run_prepared val_set_size: 0.05 output_dir: ./outputs/ablation-139-shisav2.ds.gbs128.1e5-shisa-v2-llama-3.1-8b sequence_len: 8192 sample_packing: true pad_to_sequence_len: true # marginal difference neftune_noise_alpha: 5 use_wandb: true wandb_project: shisa-v2 wandb_entity: augmxnt wandb_name: ablation-139-shisav2.ds.gbs128.1e5-shisa-v2-llama-3.1-8b gradient_accumulation_steps: 2 micro_batch_size: 4 num_epochs: 3 optimizer: paged_adamw_8bit lr_scheduler: linear learning_rate: 1e-5 train_on_inputs: false group_by_length: false bf16: auto fp16: tf32: false gradient_checkpointing: true gradient_checkpointing_kwargs: use_reentrant: false early_stopping_patience: resume_from_checkpoint: logging_steps: 1 xformers_attention: flash_attention: true warmup_steps: 100 evals_per_epoch: 2 eval_table_size: saves_per_epoch: 0 save_total_limit: 1 # Only store a single checkpoint debug: deepspeed: zero3_bf16.json weight_decay: 1e-4 fsdp: fsdp_config: special_tokens: pad_token: <|end_of_text|> ```

# outputs/ablation-139-shisav2.ds.gbs128.1e5-shisa-v2-llama-3.1-8b This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the shisa-ai/shisav1-deepseek-ai_DeepSeek-V3-0324-reannotated-filtered, the shisa-ai/shisa-v2-roleplaying-sft, the shisa-ai/translation_expanded_master_set_filtered, the shisa-ai/rewild-set, the shisa-ai/magpie-ultra-set, the shisa-ai/magpie-advanced-questions-set and the shisa-ai/japan-magpie-set datasets. It achieves the following results on the evaluation set: - Loss: 0.7148 ## 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: 1e-05 - train_batch_size: 4 - eval_batch_size: 4 - seed: 42 - distributed_type: multi-GPU - num_devices: 16 - gradient_accumulation_steps: 2 - total_train_batch_size: 128 - total_eval_batch_size: 64 - optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 3.0 ### Training results | Training Loss | Epoch | Step | Validation Loss | |:-------------:|:------:|:----:|:---------------:| | 1.2007 | 0.0026 | 1 | 1.1957 | | 0.7755 | 0.5013 | 193 | 0.7861 | | 0.6593 | 1.0026 | 386 | 0.7374 | | 0.6288 | 1.5039 | 579 | 0.7210 | | 0.5564 | 2.0052 | 772 | 0.7137 | | 0.5417 | 2.5065 | 965 | 0.7148 | ### Framework versions - Transformers 4.50.0 - Pytorch 2.6.0+cu124 - Datasets 3.4.1 - Tokenizers 0.21.1