diff --git a/recipes/A5000_24GB_x8/Mistral-7B-v0.1/i18n-ja-wikipedia-sakura.yaml b/recipes/A5000_24GB_x8/Mistral-7B-v0.1/i18n-ja-wikipedia-sakura.yaml new file mode 100644 index 0000000..588e496 --- /dev/null +++ b/recipes/A5000_24GB_x8/Mistral-7B-v0.1/i18n-ja-wikipedia-sakura.yaml @@ -0,0 +1,18 @@ +target_task: tasks/i18n/ja.md +base_model_id: yuiseki/Mistral-7B-v0.1-ja-wikipedia-v0.1 +model_name: Mistral-7B-v0.1-ja-wikipedia-sakura-v0.1 +output_base_dir: output +dataset_id: saldra/sakura_japanese_dataset +dataset_context_field_name: input +dataset_input_field_name: instruction +dataset_output_field_name: output +dataset_filter_field_value: 0 +dataset_train_split_seed: 42 +dataset_train_split_test_size: 0.2 +lora_r: 8 +lora_alpha: 16 +lora_dropout: 0.05 +train_claim_gpu_num: 2 +train_per_device_train_batch_size: 2 +train_gradient_accumulation_steps: 16 +train_num_train_epochs: 4