|
--- |
|
base_model: microsoft/codebert-base-mlm |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: CBertbase-mlm-APPS10k |
|
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. --> |
|
|
|
# CBertbase-mlm-APPS10k |
|
|
|
This model is a fine-tuned version of [microsoft/codebert-base-mlm](https://huggingface.co/microsoft/codebert-base-mlm) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.0911 |
|
|
|
## 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: 4 |
|
- eval_batch_size: 4 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 100 |
|
- training_steps: 10000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:-----:|:---------------:| |
|
| 2.1352 | 0.05 | 500 | 1.8774 | |
|
| 1.1754 | 0.1 | 1000 | 1.4835 | |
|
| 1.4127 | 0.15 | 1500 | 1.4475 | |
|
| 1.0497 | 0.2 | 2000 | 1.3342 | |
|
| 1.0403 | 0.25 | 2500 | 1.2589 | |
|
| 1.0754 | 0.3 | 3000 | 1.2174 | |
|
| 0.8836 | 0.35 | 3500 | 1.2265 | |
|
| 0.95 | 0.4 | 4000 | 1.1931 | |
|
| 1.0324 | 0.45 | 4500 | 1.1729 | |
|
| 1.0296 | 0.5 | 5000 | 1.1462 | |
|
| 0.886 | 0.55 | 5500 | 1.1364 | |
|
| 0.9352 | 0.6 | 6000 | 1.1201 | |
|
| 1.0547 | 0.65 | 6500 | 1.1481 | |
|
| 0.8277 | 0.7 | 7000 | 1.1128 | |
|
| 0.8685 | 0.75 | 7500 | 1.1153 | |
|
| 0.9277 | 0.8 | 8000 | 1.1194 | |
|
| 0.8111 | 0.85 | 8500 | 1.0975 | |
|
| 0.9345 | 0.9 | 9000 | 1.0913 | |
|
| 0.9166 | 0.95 | 9500 | 1.0904 | |
|
| 0.952 | 1.0 | 10000 | 1.0911 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
