metadata
base_model: microsoft/codebert-base
tags:
- generated_from_trainer
model-index:
- name: CodeBert-finetuned-the-stack-bash
results: []
CodeBert-finetuned-the-stack-bash
This model is a fine-tuned version of microsoft/codebert-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.0540
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: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 4
- 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 |
|---|---|---|---|
| 4.3461 | 0.05 | 500 | 4.6252 |
| 3.028 | 0.1 | 1000 | 3.2745 |
| 2.978 | 0.15 | 1500 | 2.8286 |
| 3.2116 | 0.2 | 2000 | 2.5426 |
| 2.9872 | 0.25 | 2500 | 2.4032 |
| 2.5853 | 0.3 | 3000 | 2.3376 |
| 2.6977 | 0.35 | 3500 | 2.2992 |
| 2.5997 | 0.4 | 4000 | 2.2394 |
| 2.3712 | 0.45 | 4500 | 2.1834 |
| 2.1944 | 0.5 | 5000 | 2.1589 |
| 2.4029 | 0.55 | 5500 | 2.1265 |
| 2.3307 | 0.6 | 6000 | 2.1207 |
| 2.45 | 0.65 | 6500 | 2.0951 |
| 2.3575 | 0.7 | 7000 | 2.0987 |
| 2.3894 | 0.75 | 7500 | 2.0740 |
| 2.741 | 0.8 | 8000 | 2.0610 |
| 1.6001 | 0.85 | 8500 | 2.0542 |
| 2.5929 | 0.9 | 9000 | 2.0488 |
| 2.0965 | 0.95 | 9500 | 2.0473 |
| 2.6814 | 1.0 | 10000 | 2.0540 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1