metadata
library_name: transformers
license: apache-2.0
base_model: Salesforce/codet5-base
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: CodeT5-KeyPhrases-Filtered-Valid-Phase1
results: []
CodeT5-KeyPhrases-Filtered-Valid-Phase1
This model is a fine-tuned version of Salesforce/codet5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5395
- Rouge1: 0.3357
- Rouge2: 0.1004
- Rougel: 0.3230
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: 14
- eval_batch_size: 4
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|---|---|---|---|---|---|---|
| 1.2932 | 1.0 | 8 | 0.8983 | 0.2450 | 0.0317 | 0.2338 |
| 0.7191 | 2.0 | 16 | 0.7307 | 0.3123 | 0.0742 | 0.3011 |
| 0.812 | 3.0 | 24 | 0.6878 | 0.3304 | 0.0994 | 0.3186 |
| 0.4139 | 4.0 | 32 | 0.6456 | 0.3431 | 0.1057 | 0.3313 |
| 0.482 | 5.0 | 40 | 0.6134 | 0.3445 | 0.0942 | 0.3327 |
| 0.3675 | 6.0 | 48 | 0.5809 | 0.3318 | 0.0924 | 0.3210 |
| 0.4833 | 7.0 | 56 | 0.5530 | 0.3408 | 0.0963 | 0.3282 |
| 0.3695 | 8.0 | 64 | 0.5395 | 0.3357 | 0.1004 | 0.3230 |
Framework versions
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1