metadata
base_model: microsoft/codebert-base
tags:
- generated_from_trainer
model-index:
- name: santacoder-finetuned-the-stack-bash
results: []
santacoder-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: 2.4920
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: 3500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.3682 | 0.14 | 500 | 4.6028 |
| 3.0913 | 0.29 | 1000 | 3.3129 |
| 3.0878 | 0.43 | 1500 | 2.8594 |
| 3.3334 | 0.57 | 2000 | 2.6359 |
| 3.1875 | 0.71 | 2500 | 2.5355 |
| 2.7736 | 0.86 | 3000 | 2.5017 |
| 3.152 | 1.0 | 3500 | 2.4920 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu118
- Datasets 2.14.6
- Tokenizers 0.14.1