becares/finetuned_phi_15_plantuml_generation

finetunedphi15plantumlgeneration

This model is a fine-tuned version of microsoft/phi-1_5 on coai/plantuml_generation dataset.

Training hyperparameters

The following hyperparameters were used during training:

• —learning_rate: 0.0001
• —trainbatchsize: 1
• —evalbatchsize: 8
• —seed: 42
• —gradientaccumulationsteps: 12
• —totaltrainbatch_size: 12
• —optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• —lrschedulertype: linear
• —lrschedulerwarmup_steps: 100
• —num_epochs: 3

Framework versions

• —PEFT 0.11.1
• —Transformers 4.41.2
• —Pytorch 2.3.1+cu118
• —Datasets 2.19.2
• —Tokenizers 0.19.1