Rajadurai/llama2-docsum-adapter

<!-- 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. -->

llama2-docsum-adapter

This model is a fine-tuned version of NousResearch/Llama-2-7b-hf on the None dataset. It achieves the following results on the evaluation set:

• —Loss: 0.1430

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

The following bitsandbytes quantization config was used during training:

• —quant_method: bitsandbytes
• —loadin_8bit: False
• —loadin_4bit: True
• —llmint8threshold: 6.0
• —llmint8skip_modules: None
• —llmint8enablefp32cpu_offload: False
• —llmint8hasfp16weight: False
• —bnb4bitquant_type: nf4
• —bnb4bitusedoublequant: True
• —bnb4bitcompute_dtype: bfloat16
• —bnb4bitquant_storage: uint8
• —loadin4bit: True
• —loadin8bit: False

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 0.0001
• —trainbatchsize: 4
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 4
• —totaltrainbatch_size: 16
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.05
• —num_epochs: 35
• —mixedprecisiontraining: Native AMP

Training results

Framework versions

• —PEFT 0.4.0
• —Transformers 4.39.2
• —Pytorch 2.2.1+cu121
• —Datasets 2.18.0
• —Tokenizers 0.15.2