WO_CausalModel_2x

This model is a fine-tuned version of distilgpt2 on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 0.6035

Model description

It is focused on generating realistic WO descriptions when prompted with a given WO's priority, activity type, maintenance type, and location.

Intended uses & limitations

This is a proof of concept model for a larger project.

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	151	0.6217
No log	2.0	302	0.6133
No log	3.0	453	0.6087
0.6243	4.0	604	0.6079
0.6243	5.0	755	0.6049
0.6243	6.0	906	0.6035

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.17.1
• Tokenizers 0.15.2