codet5-python-summarizer-v4
This model is a fine-tuned version of Salesforce/codet5-small on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0161
- Rouge1: 0.9933
- Rouge2: 0.9923
- Rougel: 0.9933
- Rougelsum: 0.9934
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: 0.0003
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.0252 | 1.0 | 6117 | 0.0187 | 0.989 | 0.9879 | 0.9889 | 0.989 |
| 0.0203 | 2.0 | 12234 | 0.0173 | 0.9916 | 0.9906 | 0.9915 | 0.9916 |
| 0.0099 | 3.0 | 18351 | 0.0165 | 0.9924 | 0.9916 | 0.9924 | 0.9924 |
| 0.0065 | 4.0 | 24468 | 0.0182 | 0.9908 | 0.9901 | 0.9907 | 0.9908 |
| 0.0092 | 5.0 | 30585 | 0.0161 | 0.9933 | 0.9923 | 0.9933 | 0.9934 |
Framework versions
- PEFT 0.18.1
- Transformers 4.44.2
- Pytorch 2.10.0+cu128
- Datasets 4.0.0
- Tokenizers 0.19.1
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Azirqui/codet5-python-summarizer-v4
Base model
Salesforce/codet5-small
from peft import PeftModel from transformers import AutoModelForSeq2SeqLM base_model = AutoModelForSeq2SeqLM.from_pretrained("Salesforce/codet5-small") model = PeftModel.from_pretrained(base_model, "Azirqui/codet5-python-summarizer-v4")