|
--- |
|
license: bsd-3-clause |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
- bleu |
|
model-index: |
|
- name: CommitPredictorT5 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# CommitPredictorT5 |
|
|
|
This model is a fine-tuned version of [Salesforce/codet5-base-multi-sum](https://huggingface.co/Salesforce/codet5-base-multi-sum) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.7383 |
|
- Rouge1: 0.0001 |
|
- Rouge2: 0.0 |
|
- Rougel: 0.0001 |
|
- Rougelsum: 0.0001 |
|
- Gen Len: 1.0 |
|
- Bleu: 0.0003 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 100 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len | Bleu | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|:------:| |
|
| 3.2223 | 1.0 | 837 | 2.6672 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0003 | |
|
| 2.6296 | 2.0 | 1674 | 2.5416 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0003 | |
|
| 2.4155 | 3.0 | 2511 | 2.4725 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0003 | |
|
| 2.2666 | 4.0 | 3348 | 2.4331 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0003 | |
|
| 2.112 | 5.0 | 4185 | 2.4343 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 1.0 | 0.0003 | |
|
| 1.9833 | 6.0 | 5022 | 2.4283 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 1.0 | 0.0003 | |
|
| 1.8833 | 7.0 | 5859 | 2.4360 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0003 | |
|
| 1.7778 | 8.0 | 6696 | 2.4457 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 1.0 | 0.0003 | |
|
| 1.6767 | 9.0 | 7533 | 2.4696 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 1.0 | 0.0003 | |
|
| 1.5805 | 10.0 | 8370 | 2.4829 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 1.0 | 0.0003 | |
|
| 1.4918 | 11.0 | 9207 | 2.5202 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 1.0 | 0.0003 | |
|
| 1.4137 | 12.0 | 10044 | 2.5357 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0003 | |
|
| 1.3351 | 13.0 | 10881 | 2.5621 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 1.0 | 0.0003 | |
|
| 1.2533 | 14.0 | 11718 | 2.5992 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0003 | |
|
| 1.1952 | 15.0 | 12555 | 2.6149 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 1.0 | 0.0003 | |
|
| 1.122 | 16.0 | 13392 | 2.6565 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 1.0 | 0.0003 | |
|
| 1.0543 | 17.0 | 14229 | 2.6823 | 0.0 | 0.0 | 0.0 | 0.0 | 1.0 | 0.0003 | |
|
| 1.0017 | 18.0 | 15066 | 2.7106 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 1.0 | 0.0003 | |
|
| 0.9437 | 19.0 | 15903 | 2.7383 | 0.0001 | 0.0 | 0.0001 | 0.0001 | 1.0 | 0.0003 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.25.1 |
|
- Pytorch 1.13.0+cu117 |
|
- Datasets 2.7.1 |
|
- Tokenizers 0.13.2 |
|
|
