metadata
base_model: microsoft/codebert-base-mlm
tags:
- generated_from_trainer
model-index:
- name: CBERT-MBPP
results: []
metrics:
- bleu
pipeline_tag: text2text-generation
CBERT-MBPP
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: 0.0099
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0215 | 0.05 | 500 | 0.0196 |
| 0.0087 | 0.1 | 1000 | 0.0091 |
| 0.0093 | 0.15 | 1500 | 0.0090 |
| 0.0096 | 0.2 | 2000 | 0.0094 |
| 0.009 | 0.25 | 2500 | 0.0095 |
| 0.01 | 0.3 | 3000 | 0.0091 |
| 0.01 | 0.35 | 3500 | 0.0093 |
| 0.0093 | 0.4 | 4000 | 0.0094 |
| 0.0086 | 0.45 | 4500 | 0.0098 |
| 0.0085 | 0.5 | 5000 | 0.0097 |
| 0.0094 | 0.55 | 5500 | 0.0099 |
| 0.0099 | 0.6 | 6000 | 0.0101 |
| 0.0096 | 0.65 | 6500 | 0.0099 |
| 0.0104 | 0.7 | 7000 | 0.0099 |
| 0.0096 | 0.75 | 7500 | 0.0097 |
| 0.0087 | 0.8 | 8000 | 0.0098 |
| 0.0105 | 0.85 | 8500 | 0.0099 |
| 0.0098 | 0.9 | 9000 | 0.0098 |
| 0.0091 | 0.95 | 9500 | 0.0099 |
| 0.0101 | 1.0 | 10000 | 0.0099 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2