# Load model directly
from transformers import AutoTokenizer, AutoModelForMaskedLM
tokenizer = AutoTokenizer.from_pretrained("gokulsrinivasagan/bert_base_code_uml")
model = AutoModelForMaskedLM.from_pretrained("gokulsrinivasagan/bert_base_code_uml")Quick Links
bert_base_code_uml
This model is a fine-tuned version of google-bert/bert-base-uncased on the devgpt-aimotion/the-stack-v2_PlantUML_filtered dataset. It achieves the following results on the evaluation set:
- Loss: 0.8230
- Accuracy: 0.8297
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: 0.0001
- train_batch_size: 96
- eval_batch_size: 96
- seed: 10
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10000
- num_epochs: 25
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.4929 | 7.8493 | 10000 | 2.1514 | 0.5692 |
| 0.9263 | 15.6986 | 20000 | 0.9068 | 0.8143 |
| 0.8293 | 23.5479 | 30000 | 0.8292 | 0.8286 |
Framework versions
- Transformers 4.51.2
- Pytorch 2.6.0+cu126
- Datasets 3.5.0
- Tokenizers 0.21.1
- Downloads last month
- 2
Model tree for gokulsrinivasagan/bert_base_code_uml
Base model
google-bert/bert-base-uncasedDataset used to train gokulsrinivasagan/bert_base_code_uml
Evaluation results
- Accuracy on devgpt-aimotion/the-stack-v2_PlantUML_filteredself-reported0.830
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("fill-mask", model="gokulsrinivasagan/bert_base_code_uml")