vericava/llm-jp-3-vericava-posts-v1

<!-- 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. -->

llm-jp-3-vericava-posts-v1

This model is a fine-tuned version of llm-jp/llm-jp-3-3.7b on the dataset of my posts on the Internet.

Model description

It generates text resembling what I post on the Internet.

Intended uses & limitations

CAUTION: It may produce something I'd never say. I do not impose any restriction(s) on the use of this model.

Training and evaluation data

Twitter/X: https://x.com/vericava

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 0.0002
• —trainbatchsize: 16
• —evalbatchsize: 16
• —seed: 42
• —gradientaccumulationsteps: 8
• —totaltrainbatch_size: 128
• —optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• —lrschedulertype: cosine
• —lrschedulerwarmup_steps: 300
• —num_epochs: 4

Training results

Framework versions

• —Transformers 4.55.0
• —Pytorch 2.8.0+cu128
• —Datasets 4.0.0
• —Tokenizers 0.21.4