Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama3-8b-math-sft-subtask-0-subset - GGUF

• Model creator: https://huggingface.co/Dynosaur/
• Original model: https://huggingface.co/Dynosaur/llama3-8b-math-sft-subtask-0-subset/

Original model description:

• trl
• sft
• generatedfromtrainer

• name: llama3-8b-math-sft-subtask-0-subset

llama3-8b-math-sft-subtask-0-subset

This model is a fine-tuned version of Dynosaur/llama3-8b-math-sft on an unknown 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:

• learningrate: 2e-05
• trainbatchsize: 4
• evalbatchsize: 8
• seed: 42
• distributedtype: multi-GPU
• numdevices: 8
• gradientaccumulationsteps: 4
• totaltrainbatchsize: 128
• totalevalbatchsize: 64
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lrschedulertype: cosine
• lrschedulerwarmupratio: 0.1
• num_epochs: 2

Training results

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.0
• Tokenizers 0.19.1