SEOje/japdongsani
收藏资源简介：
--- license: other library_name: peft tags: - llama-factory - lora - generated_from_trainer base_model: yanolja/EEVE-Korean-Instruct-10.8B-v1.0 model-index: - name: train_2024-06-03-09-50-18 results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # train_2024-06-03-09-50-18 This model is a fine-tuned version of [yanolja/EEVE-Korean-Instruct-10.8B-v1.0](https://huggingface.co/yanolja/EEVE-Korean-Instruct-10.8B-v1.0) on the assay dataset. ## 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: 0.0003 - train_batch_size: 2 - eval_batch_size: 8 - seed: 42 - gradient_accumulation_steps: 8 - total_train_batch_size: 16 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: cosine - num_epochs: 3.0 - mixed_precision_training: Native AMP ### Training results ### Framework versions - PEFT 0.11.1 - Transformers 4.41.2 - Pytorch 2.1.0+cu118 - Datasets 2.19.2 - Tokenizers 0.19.1
数据集概述
基本信息
- 许可证: other
- 库名称: peft
- 标签:
- llama-factory
- lora
- generated_from_trainer
- 基础模型: yanolja/EEVE-Korean-Instruct-10.8B-v1.0
模型详情
- 模型名称: train_2024-06-03-09-50-18
- 描述: 该模型是基于yanolja/EEVE-Korean-Instruct-10.8B-v1.0在assay数据集上进行微调的版本。
训练参数
- 学习率: 0.0003
- 训练批次大小: 2
- 评估批次大小: 8
- 种子: 42
- 梯度累积步骤: 8
- 总训练批次大小: 16
- 优化器: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 学习率调度器类型: cosine
- 训练周期数: 3.0
- 混合精度训练: Native AMP
框架版本
- PEFT: 0.11.1
- Transformers: 4.41.2
- Pytorch: 2.1.0+cu118
- Datasets: 2.19.2
- Tokenizers: 0.19.1
