metadata
license: apache-2.0
base_model: Salesforce/codet5-small
tags:
- generated_from_trainer
model-index:
- name: codet5-small-v31
results: []
codet5-small-v31
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: 0.2023
- Bleu Score: 0.0013
- Gen Len: 14.2125
Model description
trained on:
- dataset: [BUG]......[CONTEXT]...
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: 30
- eval_batch_size: 30
- 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 | Bleu Score | Gen Len |
|---|---|---|---|---|---|
| 0.3058 | 1.0 | 1518 | 0.2471 | 0.0013 | 14.0882 |
| 0.2444 | 2.0 | 3036 | 0.2102 | 0.0013 | 14.218 |
| 0.2223 | 3.0 | 4554 | 0.2023 | 0.0013 | 14.2125 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2