metadata
base_model: microsoft/codebert-base-mlm
tags:
- generated_from_trainer
model-index:
- name: huggingfacecodebert-base-mlm-finetuned-st
results: []
huggingfacecodebert-base-mlm-finetuned-st
This model is a fine-tuned version of microsoft/codebert-base-mlm on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9298
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 |
|---|---|---|---|
| 1.761 | 0.05 | 500 | 1.6477 |
| 1.2184 | 0.1 | 1000 | 1.2377 |
| 0.9962 | 0.15 | 1500 | 1.1013 |
| 0.026 | 0.2 | 2000 | 1.0762 |
| 0.0266 | 0.25 | 2500 | 1.0639 |
| 0.6503 | 0.3 | 3000 | 0.9464 |
| 0.382 | 0.35 | 3500 | 0.9406 |
| 0.6019 | 0.4 | 4000 | 0.9027 |
| 0.39 | 0.45 | 4500 | 0.8842 |
| 0.0243 | 0.5 | 5000 | 0.9107 |
| 0.0238 | 0.55 | 5500 | 0.9165 |
| 0.205 | 0.6 | 6000 | 0.9304 |
| 0.4026 | 0.65 | 6500 | 0.9098 |
| 0.334 | 0.7 | 7000 | 0.9271 |
| 0.2539 | 0.75 | 7500 | 0.9402 |
| 0.1819 | 0.8 | 8000 | 0.9272 |
| 0.5093 | 0.85 | 8500 | 0.9314 |
| 0.0882 | 0.9 | 9000 | 0.9259 |
| 0.3341 | 0.95 | 9500 | 0.9275 |
| 0.0233 | 1.0 | 10000 | 0.9298 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Tokenizers 0.15.0