metadata
license: bsd-3-clause
base_model: Salesforce/codet5p-220m
tags:
- generated_from_trainer
model-index:
- name: codet5p-220m-v1
results: []
codet5p-220m-v1
This model is a fine-tuned version of Salesforce/codet5p-220m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0157
- Bleu Score: 0.0023
- Gen Len: 15.7245
Model description
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: 10
- eval_batch_size: 10
- 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 |
|---|---|---|---|---|---|
| 0.0494 | 1.0 | 1967 | 0.0300 | 0.0023 | 15.7086 |
| 0.0165 | 2.0 | 3934 | 0.0180 | 0.0023 | 15.7338 |
| 0.0097 | 3.0 | 5901 | 0.0157 | 0.0023 | 15.7245 |
Framework versions
- Transformers 4.38.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1