RichardErkhov/barc0_-_transduction-run6-20k-seed100-gpt4omini-instruct-fft_lr1e-5_epoch2-gguf
Quantization made by Richard Erkhov.
transduction-run6-20k-seed100-gpt4omini-instruct-fftlr1e-5epoch2 - GGUF
- Model creator: https://huggingface.co/barc0/
- Original model: https://huggingface.co/barc0/transduction-run6-20k-seed100-gpt4omini-instruct-fftlr1e-5epoch2/
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-minigeneratedproblemsseed100.jsonlmessagesformat0.3 model-index:
- name: transduction-run6-20k-seed100-gpt4omini-instruct-fftlr1e-5epoch2 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. -->
transduction-run6-20k-seed100-gpt4omini-instruct-fftlr1e-5epoch2
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the barc0/transduction20kgpt4o-minigeneratedproblemsseed100.jsonlmessagesformat0.3 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0623
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: 6
- 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 3.0.1
- Tokenizers 0.19.1