metadata
license: apache-2.0
base_model: Salesforce/codet5-small
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: codet5-small-v1
results: []
codet5-small-v1
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: 0.3476
- Rouge1: 72.8353
- Rouge2: 55.3177
- Rougel: 68.1464
- Rougelsum: 67.5838
- Gen Len: 13.4595
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: 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 20 | 1.6944 | 60.3962 | 43.2915 | 57.1491 | 57.0619 | 13.4595 |
| No log | 2.0 | 40 | 0.8389 | 77.3091 | 66.2349 | 74.0686 | 74.0976 | 13.7027 |
| No log | 3.0 | 60 | 0.4161 | 74.7004 | 60.1588 | 70.1567 | 70.0012 | 13.3514 |
| No log | 4.0 | 80 | 0.3476 | 72.8353 | 55.3177 | 68.1464 | 67.5838 | 13.4595 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1