|
--- |
|
base_model: bigcode/starencoder |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- precision |
|
- recall |
|
- accuracy |
|
model-index: |
|
- name: stack-edu-classifier-rust |
|
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. --> |
|
|
|
# stack-edu-classifier-rust |
|
|
|
This model is a fine-tuned version of [bigcode/starencoder](https://huggingface.co./bigcode/starencoder) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4309 |
|
- Precision: 0.4200 |
|
- Recall: 0.3245 |
|
- F1 Macro: 0.3364 |
|
- Accuracy: 0.5715 |
|
- F1 Binary Minimum3: 0.6938 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 256 |
|
- seed: 0 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 128 |
|
- total_eval_batch_size: 512 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 200 |
|
- num_epochs: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 Macro | Accuracy | F1 Binary Minimum3 | |
|
|:-------------:|:-------:|:-----:|:---------------:|:---------:|:------:|:--------:|:--------:|:------------------:| |
|
| No log | 0 | 0 | 6.3938 | 0.0009 | 0.1667 | 0.0018 | 0.0054 | 0 | |
|
| 0.4784 | 1.4535 | 1000 | 0.4524 | 0.4359 | 0.3052 | 0.3115 | 0.5596 | 0.6790 | |
|
| 0.4553 | 2.9070 | 2000 | 0.4622 | 0.4179 | 0.3081 | 0.3193 | 0.5299 | 0.7012 | |
|
| 0.4397 | 4.3605 | 3000 | 0.4428 | 0.4256 | 0.3126 | 0.3225 | 0.5646 | 0.6890 | |
|
| 0.4463 | 5.8140 | 4000 | 0.4417 | 0.4252 | 0.3155 | 0.3242 | 0.5667 | 0.6850 | |
|
| 0.4305 | 7.2674 | 5000 | 0.4419 | 0.4416 | 0.3232 | 0.3397 | 0.5488 | 0.7001 | |
|
| 0.4499 | 8.7209 | 6000 | 0.4361 | 0.4250 | 0.3185 | 0.3282 | 0.5682 | 0.6878 | |
|
| 0.4339 | 10.1744 | 7000 | 0.4351 | 0.4452 | 0.3258 | 0.3384 | 0.5711 | 0.6884 | |
|
| 0.449 | 11.6279 | 8000 | 0.4386 | 0.4217 | 0.3180 | 0.3291 | 0.5718 | 0.6782 | |
|
| 0.425 | 13.0814 | 9000 | 0.4360 | 0.4224 | 0.3213 | 0.3323 | 0.5737 | 0.6828 | |
|
| 0.4434 | 14.5349 | 10000 | 0.4328 | 0.4376 | 0.3280 | 0.3436 | 0.5626 | 0.6957 | |
|
| 0.4396 | 15.9884 | 11000 | 0.4347 | 0.4170 | 0.3243 | 0.3384 | 0.5576 | 0.6994 | |
|
| 0.4207 | 17.4419 | 12000 | 0.4326 | 0.4181 | 0.3233 | 0.3365 | 0.5606 | 0.6996 | |
|
| 0.4334 | 18.8953 | 13000 | 0.4309 | 0.4200 | 0.3245 | 0.3364 | 0.5715 | 0.6938 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.43.4 |
|
- Pytorch 2.4.0+cu121 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
