CoolFace
Modelpublic

rhdeng/llama3-8B-EIP-8bit-lora

sourceHugging Facellama3updated 2y agoView on Hugging Face
0likes3downloads
Model Card

<!-- 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. -->

llama3-8B-EIP-8bit-lora

This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B on an unknown dataset. It achieves the following results on the evaluation set:

  • —Loss: 1.5218

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: 5e-05
  • —trainbatchsize: 8
  • —evalbatchsize: 8
  • —seed: 42
  • —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • —lrschedulertype: linear
  • —num_epochs: 1
  • —mixedprecisiontraining: Native AMP

Training results

Training LossEpochStepValidation Loss
2.47430.04331001.7806
1.68380.08662001.6540
1.60550.12993001.6010
1.58090.17324001.5646
1.54720.21655001.5350
1.52060.25996001.5218
1.53580.30327001.5218
1.51020.34658001.5218
1.5520.38989001.5218
1.53540.433110001.5218
1.52690.476411001.5218
1.52020.519712001.5218
1.54340.563013001.5218
1.53250.606314001.5218
1.53070.649615001.5218
1.52870.692916001.5218
1.52770.736217001.5218
1.51760.779618001.5218
1.52680.822919001.5218
1.53060.866220001.5218
1.53090.909521001.5218
1.54840.952822001.5218
1.510.996123001.5218

Framework versions

  • —PEFT 0.11.1
  • —Transformers 4.42.3
  • —Pytorch 2.1.0a0+4136153
  • —Datasets 2.20.0
  • —Tokenizers 0.19.1