metadata
license: apache-2.0
base_model: Salesforce/codet5-base
tags:
- generated_from_trainer
model-index:
- name: v9.8-codet5-bert-finetuned-code_function-to-test_case_function
results: []
v9.8-codet5-bert-finetuned-code_function-to-test_case_function
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: 2.2449
- Gen Len: 157.2
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: 8
- eval_batch_size: 8
- 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 | Gen Len |
|---|---|---|---|---|
| No log | 1.0 | 10 | 3.4550 | 76.2 |
| No log | 2.0 | 20 | 2.8713 | 116.25 |
| No log | 3.0 | 30 | 2.6550 | 98.9 |
| No log | 4.0 | 40 | 2.5123 | 122.65 |
| No log | 5.0 | 50 | 2.4152 | 98.25 |
| No log | 6.0 | 60 | 2.3636 | 107.3 |
| No log | 7.0 | 70 | 2.3242 | 108.05 |
| No log | 8.0 | 80 | 2.2844 | 120.35 |
| No log | 9.0 | 90 | 2.2518 | 167.5 |
| No log | 10.0 | 100 | 2.2449 | 157.2 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1