Hugging Face's logo

REILX
/
Llama-3-8B-Instruct-750Mb-lora

Safetensors
Chinese
English
text-generation-inference
llama
chat
sft
lora
Model card Files Community

数据集

使用以下8个数据集 image/png 对Llama-3-8B-Instruct进行微调。

基础模型：

训练工具

https://github.com/hiyouga/LLaMA-Factory

测评方式：

使用opencompass(https://github.com/open-compass/OpenCompass/ )， 测试工具基于CEval和MMLU对微调之后的模型和原始模型进行测试。
测试模型分别为：

  • Llama-3-8B
  • Llama-3-8B-Instruct
  • Llama-3-8B-Instruct-750Mb-lora, 使用8DataSets数据集对Llama-3-8B-Instruct模型进行sft方式lora微调

测试机器

8*A800

8DataSets数据集：

大约750Mb的微调数据集

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 4
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 300
  • num_epochs: 1.0
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .

Model tree for REILX/Llama-3-8B-Instruct-750Mb-lora

Merges
1 model

Datasets used to train REILX/Llama-3-8B-Instruct-750Mb-lora

Collection including REILX/Llama-3-8B-Instruct-750Mb-lora