falcon-7b-code-python
This model is a fine-tuned version of tiiuae/falcon-7b-instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1486
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: 2e-05
- train_batch_size: 6
- eval_batch_size: 6
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 24
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3986 | 0.3183 | 30 | 1.4874 |
| 1.3762 | 0.6366 | 60 | 1.4038 |
| 1.2544 | 0.9549 | 90 | 1.3065 |
| 1.1233 | 1.2732 | 120 | 1.2405 |
| 1.1611 | 1.5915 | 150 | 1.1918 |
| 1.1243 | 1.9098 | 180 | 1.1603 |
| 1.0911 | 2.2281 | 210 | 1.1504 |
| 1.1027 | 2.5464 | 240 | 1.1489 |
| 1.1615 | 2.8647 | 270 | 1.1486 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 3
Model tree for amztheory/falcon-7b-code-python
Base model
tiiuae/falcon-7b-instruct