RichardErkhov/mlfoundations-dev_-_hp_ablations_grid_mistral_base-mistralv0.3-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

hpablationsgridmistralbase-mistralv0.3 - GGUF

• —Model creator: https://huggingface.co/mlfoundations-dev/
• —Original model: https://huggingface.co/mlfoundations-dev/hpablationsgridmistralbase-mistralv0.3/

Original model description: --- libraryname: transformers license: apache-2.0 basemodel: mistralai/Mistral-7B-v0.3 tags:

• —llama-factory
• —full
• —generatedfromtrainer model-index:
• —name: hpablationsgridmistralbase-mistralv0.3 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. -->

hpablationsgridmistralbase-mistralv0.3

This model is a fine-tuned version of mistralai/Mistral-7B-v0.3 on the mlfoundations-dev/oh-dcft-v3-llama3.1-nemotron-70bshareGPTformat dataset. It achieves the following results on the evaluation set:

• —Loss: 0.0616

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-06
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 512
• —totalevalbatch_size: 64
• —optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
• —lrschedulertype: constant
• —num_epochs: 3.0

Training results

Framework versions

• —Transformers 4.46.1
• —Pytorch 2.3.0
• —Datasets 3.1.0
• —Tokenizers 0.20.3