|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
- precision |
|
- recall |
|
model-index: |
|
- name: Roberta-base-Rewritten-commit_messages_v1 |
|
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. --> |
|
|
|
# Roberta-base-Rewritten-commit_messages_v1 |
|
|
|
This model was trained from scratch on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 4.0366 |
|
- Accuracy: 0.7334 |
|
- F1: 0.7333 |
|
- Precision: 0.7485 |
|
- Recall: 0.7334 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 2 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 3 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|:---------:|:------:| |
|
| 0.211 | 0.09 | 100 | 0.5038 | 0.7716 | 0.7710 | 0.7712 | 0.7716 | |
|
| 0.1021 | 0.17 | 200 | 1.4349 | 0.6967 | 0.6878 | 0.7575 | 0.6967 | |
|
| 0.21 | 0.26 | 300 | 1.6924 | 0.6772 | 0.6621 | 0.7604 | 0.6772 | |
|
| 0.3015 | 0.34 | 400 | 1.2524 | 0.7688 | 0.7689 | 0.7691 | 0.7688 | |
|
| 0.0545 | 0.43 | 500 | 0.6203 | 0.7967 | 0.7944 | 0.7996 | 0.7967 | |
|
| 0.2606 | 0.52 | 600 | 1.9708 | 0.7812 | 0.7816 | 0.7831 | 0.7812 | |
|
| 0.2303 | 0.6 | 700 | 4.2551 | 0.7003 | 0.6877 | 0.7822 | 0.7003 | |
|
| 0.3791 | 0.69 | 800 | 3.9563 | 0.6449 | 0.6287 | 0.7176 | 0.6449 | |
|
| 0.1818 | 0.77 | 900 | 3.2710 | 0.7413 | 0.7382 | 0.7798 | 0.7413 | |
|
| 0.2664 | 0.86 | 1000 | 3.1223 | 0.7541 | 0.7545 | 0.7637 | 0.7541 | |
|
| 0.0975 | 0.95 | 1100 | 4.2953 | 0.6628 | 0.6504 | 0.7279 | 0.6628 | |
|
| 0.0994 | 1.03 | 1200 | 3.0247 | 0.7577 | 0.7568 | 0.7808 | 0.7577 | |
|
| 0.0 | 1.12 | 1300 | 4.3038 | 0.7094 | 0.7048 | 0.7515 | 0.7094 | |
|
| 0.1308 | 1.2 | 1400 | 3.6026 | 0.7497 | 0.7502 | 0.7576 | 0.7497 | |
|
| 0.0518 | 1.29 | 1500 | 3.1581 | 0.7629 | 0.7634 | 0.7669 | 0.7629 | |
|
| 0.0444 | 1.38 | 1600 | 3.5891 | 0.7485 | 0.7481 | 0.7480 | 0.7485 | |
|
| 0.0904 | 1.46 | 1700 | 3.5088 | 0.7206 | 0.7162 | 0.7224 | 0.7206 | |
|
| 0.2481 | 1.55 | 1800 | 3.5703 | 0.7083 | 0.7077 | 0.7257 | 0.7083 | |
|
| 0.2444 | 1.63 | 1900 | 2.8876 | 0.7740 | 0.7688 | 0.7829 | 0.7740 | |
|
| 0.1379 | 1.72 | 2000 | 3.2268 | 0.7385 | 0.7336 | 0.7426 | 0.7385 | |
|
| 0.1244 | 1.81 | 2100 | 3.4375 | 0.7413 | 0.7417 | 0.7519 | 0.7413 | |
|
| 0.0826 | 1.89 | 2200 | 3.1960 | 0.7688 | 0.7689 | 0.7689 | 0.7688 | |
|
| 0.1172 | 1.98 | 2300 | 3.0243 | 0.7784 | 0.7784 | 0.7784 | 0.7784 | |
|
| 0.1066 | 2.06 | 2400 | 3.2134 | 0.7764 | 0.7769 | 0.7790 | 0.7764 | |
|
| 0.0 | 2.15 | 2500 | 3.3545 | 0.7664 | 0.7670 | 0.7694 | 0.7664 | |
|
| 0.1429 | 2.24 | 2600 | 3.7563 | 0.7393 | 0.7389 | 0.7574 | 0.7393 | |
|
| 0.0451 | 2.32 | 2700 | 3.4993 | 0.7537 | 0.7540 | 0.7548 | 0.7537 | |
|
| 0.0 | 2.41 | 2800 | 3.7249 | 0.7501 | 0.7504 | 0.7511 | 0.7501 | |
|
| 0.0273 | 2.49 | 2900 | 4.2791 | 0.7190 | 0.7175 | 0.7434 | 0.7190 | |
|
| 0.0789 | 2.58 | 3000 | 4.2166 | 0.7178 | 0.7161 | 0.7438 | 0.7178 | |
|
| 0.0527 | 2.67 | 3100 | 4.0366 | 0.7334 | 0.7333 | 0.7485 | 0.7334 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.3 |
|
- Pytorch 2.1.2+cu121 |
|
- Datasets 2.16.1 |
|
- Tokenizers 0.15.1 |
|
|
