metadata
license: apache-2.0
base_model: Salesforce/codet5-small
tags:
- generated_from_trainer
model-index:
- name: codet5-small-v13
results: []
codet5-small-v13
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: 0.1512
- Bleu Score: 0.0007
- Gen Len: 14.6798
Model description
Trained,
- on: chathuranga-jayanath/context-5-finmath-times4j-html-mavendoxia-wro4j-guava-supercsv-len-30000-prompt-1
- data sample count: 91.9k
- prompt: [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 |
|---|---|---|---|---|---|
| 0.237 | 1.0 | 3064 | 0.1859 | 0.0007 | 14.6328 |
| 0.1928 | 2.0 | 6128 | 0.1572 | 0.0007 | 14.6804 |
| 0.1733 | 3.0 | 9192 | 0.1512 | 0.0007 | 14.6798 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1