metadata
library_name: peft
tags:
- generated_from_trainer
base_model: microsoft/codebert-base
model-index:
- name: codebertbasePEFTLORA-finetuned-the-stack-bash
results: []
codebertbasePEFTLORA-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: 5.6253
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 |
|---|---|---|---|
| 8.0071 | 0.05 | 500 | 7.3041 |
| 6.7238 | 0.1 | 1000 | 6.7353 |
| 6.0485 | 0.15 | 1500 | 6.4389 |
| 7.5991 | 0.2 | 2000 | 6.1635 |
| 7.0524 | 0.25 | 2500 | 6.0566 |
| 6.4077 | 0.3 | 3000 | 5.9759 |
| 6.2579 | 0.35 | 3500 | 5.9255 |
| 6.2236 | 0.4 | 4000 | 5.9026 |
| 6.6512 | 0.45 | 4500 | 5.7760 |
| 6.0908 | 0.5 | 5000 | 5.7303 |
| 6.3444 | 0.55 | 5500 | 5.6846 |
| 7.097 | 0.6 | 6000 | 5.7699 |
| 5.9796 | 0.65 | 6500 | 5.6752 |
| 5.2663 | 0.7 | 7000 | 5.7492 |
| 6.065 | 0.75 | 7500 | 5.6354 |
| 6.5333 | 0.8 | 8000 | 5.6294 |
| 6.1995 | 0.85 | 8500 | 5.6278 |
| 6.0109 | 0.9 | 9000 | 5.6193 |
| 5.8204 | 0.95 | 9500 | 5.6142 |
| 6.7558 | 1.0 | 10000 | 5.6253 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0