metadata
library_name: peft
license: apache-2.0
base_model: Salesforce/codet5-small
tags:
- base_model:adapter:Salesforce/codet5-small
- lora
- transformers
metrics:
- rouge
model-index:
- name: codet5-python-doc-generator-v2
results: []
codet5-python-doc-generator-v2
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: 0.0036
- Rouge1: 0.9894
- Rouge2: 0.9853
- Rougel: 0.9894
- Rougelsum: 0.9894
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: 5e-05
- 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 0.0046 | 1.0 | 12278 | 0.0046 | 0.9898 | 0.9856 | 0.9899 | 0.9899 |
| 0.0043 | 2.0 | 24556 | 0.0038 | 0.9891 | 0.9849 | 0.9891 | 0.9891 |
| 0.0044 | 3.0 | 36834 | 0.0036 | 0.9894 | 0.9853 | 0.9894 | 0.9894 |
Framework versions
- PEFT 0.18.1
- Transformers 4.44.2
- Pytorch 2.10.0+cu128
- Datasets 4.6.1
- Tokenizers 0.19.1