metadata
license: apache-2.0
base_model: Salesforce/codet5-base
tags:
- generated_from_trainer
model-index:
- name: codet5-with-doc-new-v3
results: []
codet5-with-doc-new-v3
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: 1.3350
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: 1
- eval_batch_size: 1
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 230 | 1.7676 |
| No log | 2.0 | 460 | 1.5304 |
| 1.9937 | 3.0 | 690 | 1.4249 |
| 1.9937 | 4.0 | 920 | 1.3746 |
| 1.0274 | 5.0 | 1150 | 1.3364 |
| 1.0274 | 6.0 | 1380 | 1.3554 |
| 0.741 | 7.0 | 1610 | 1.3405 |
| 0.741 | 8.0 | 1840 | 1.3406 |
| 0.6108 | 9.0 | 2070 | 1.3383 |
| 0.6108 | 10.0 | 2300 | 1.3350 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1