RichardErkhov/pkarypis_-_gpt2-sft-dutch-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

gpt2-sft-dutch - GGUF

• —Model creator: https://huggingface.co/pkarypis/
• —Original model: https://huggingface.co/pkarypis/gpt2-sft-dutch/

Original model description: --- license: apache-2.0 base_model: JackFram/llama-68m tags:

• —alignment-handbook
• —trl
• —sft
• —generatedfromtrainer
• —trl
• —sft
• —generatedfromtrainer datasets:
• —HuggingFaceH4/ultrachat_200k model-index:
• —name: gpt2-sft-dutch 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. -->

gpt2-sft-dutch

This model is a fine-tuned version of JackFram/llama-68m on the HuggingFaceH4/ultrachat_200k dataset. It achieves the following results on the evaluation set:

• —Loss: 2.0464

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: 2e-05
• —trainbatchsize: 8
• —evalbatchsize: 8
• —seed: 42
• —distributed_type: multi-GPU
• —num_devices: 4
• —totaltrainbatch_size: 32
• —totalevalbatch_size: 32
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: cosine
• —lrschedulerwarmup_ratio: 0.1
• —num_epochs: 1.0

Training results

Framework versions

• —Transformers 4.38.2
• —Pytorch 2.1.2
• —Datasets 2.14.6
• —Tokenizers 0.15.2