RichardErkhov/mlfoundations-dev_-_oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_camel_biology-4bits
06
Quantization made by Richard Erkhov.
oh-dcft-v1.2no-curationgpt-4o-miniwocamel_biology - bnb 4bits
- Model creator: https://huggingface.co/mlfoundations-dev/
- Original model: https://huggingface.co/mlfoundations-dev/oh-dcft-v1.2no-curationgpt-4o-miniwocamel_biology/
Original model description: --- libraryname: transformers license: llama3.1 basemodel: meta-llama/Meta-Llama-3.1-8B tags:
- llama-factory
- full
- generatedfromtrainer model-index:
- name: oh-dcft-v1.2no-curationgpt-4o-miniwocamel_biology 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. -->
oh-dcft-v1.2no-curationgpt-4o-miniwocamel_biology
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B on the mlfoundations-dev/oh-dcft-v1.2no-curationgpt-4o-miniwocamel_biology dataset. It achieves the following results on the evaluation set:
- Loss: 0.6339
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: 16
- evalbatchsize: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- totaltrainbatch_size: 512
- totalevalbatch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lrschedulertype: constant
- lrschedulerwarmup_ratio: 0.1
- lrschedulerwarmup_steps: 1738
- num_epochs: 3.0
Training results
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 3.0.2
- Tokenizers 0.19.1