metadata
license: gemma
library_name: peft
tags:
- generated_from_trainer
base_model: google/gemma-2b
model-index:
- name: CodeGemma2b-300APPS
results: []
CodeGemma2b-300APPS
This model is a fine-tuned version of google/gemma-2b on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9701
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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 20
- training_steps: 300
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0902 | 0.1667 | 50 | 1.0826 |
| 0.9774 | 0.3333 | 100 | 1.0107 |
| 0.9138 | 0.5 | 150 | 0.9829 |
| 0.8657 | 0.6667 | 200 | 0.9703 |
| 0.8228 | 0.8333 | 250 | 0.9685 |
| 0.8886 | 1.0 | 300 | 0.9701 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1