metadata
base_model: huggingface/CodeBERTa-small-v1
tags:
- generated_from_trainer
model-index:
- name: huggingfaceCodeBerta-finetuned-the-stack-bash
results: []
huggingfaceCodeBerta-finetuned-the-stack-bash
This model is a fine-tuned version of huggingface/CodeBERTa-small-v1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.4191
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 |
|---|---|---|---|
| 3.3233 | 0.05 | 500 | 3.4143 |
| 3.2135 | 0.1 | 1000 | 3.0184 |
| 3.1977 | 0.15 | 1500 | 2.8537 |
| 2.9303 | 0.2 | 2000 | 2.7396 |
| 3.1618 | 0.25 | 2500 | 2.6954 |
| 2.9122 | 0.3 | 3000 | 2.6338 |
| 2.8965 | 0.35 | 3500 | 2.5881 |
| 2.599 | 0.4 | 4000 | 2.5677 |
| 2.8213 | 0.45 | 4500 | 2.5247 |
| 2.516 | 0.5 | 5000 | 2.5118 |
| 2.8975 | 0.55 | 5500 | 2.4817 |
| 2.3503 | 0.6 | 6000 | 2.4803 |
| 2.1736 | 0.65 | 6500 | 2.4650 |
| 2.8777 | 0.7 | 7000 | 2.4394 |
| 2.5809 | 0.75 | 7500 | 2.4391 |
| 2.6986 | 0.8 | 8000 | 2.4199 |
| 3.2199 | 0.85 | 8500 | 2.4354 |
| 2.3214 | 0.9 | 9000 | 2.4174 |
| 0.7788 | 0.95 | 9500 | 2.4156 |
| 2.6361 | 1.0 | 10000 | 2.4191 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1