RichardErkhov/barc0_-_google_cloude_test_20k_transduction-gpt4omini_lr1e-5_epoch2_seed50-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

googlecloudetest20ktransduction-gpt4ominilr1e-5epoch2_seed50 - GGUF

• —Model creator: https://huggingface.co/barc0/
• —Original model: https://huggingface.co/barc0/googlecloudetest20ktransduction-gpt4ominilr1e-5epoch2_seed50/

Original model description: --- libraryname: transformers license: llama3.1 basemodel: meta-llama/Meta-Llama-3.1-8B-Instruct tags:

• —alignment-handbook
• —trl
• —sft
• —generatedfromtrainer
• —trl
• —sft
• —generatedfromtrainer datasets:
• —barc0/transduction20kgpt4o-minigeneratedproblemsseed50.jsonlmessagesformat0.3 model-index:
• —name: googlecloudetest20ktransduction-gpt4ominilr1e-5epoch2_seed50 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. -->

googlecloudetest20ktransduction-gpt4ominilr1e-5epoch2_seed50

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the barc0/transduction20kgpt4o-minigeneratedproblemsseed50.jsonlmessagesformat0.3 dataset. It achieves the following results on the evaluation set:

• —Loss: 0.0609

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: 1e-05
• —trainbatchsize: 8
• —evalbatchsize: 4
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 8
• —gradientaccumulationsteps: 2
• —totaltrainbatch_size: 128
• —totalevalbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 2

Training results

Framework versions

• —Transformers 4.45.0.dev0
• —Pytorch 2.4.0+cu121
• —Datasets 3.0.0
• —Tokenizers 0.19.1