pdazad/bloom-560-finetuned-owasp-8epochs
By pdazad · ↓ 4 · ♥ 0 · Updated 2025-01-27
What's in this repo
This page lists the files in pdazad/bloom-560-finetuned-owasp-8epochs, including model.onnx and more.
- 2 ONNX models (.onnx files)
- 13 files, including 5 .json, 2 .onnx, 2 .onnx_data, 1 .md, 1 .safetensors, 1 .bin
- Last updated 2025-01-27
ONNX files
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
fine_tuned_bloom
This model is a fine-tuned version of bigscience/bloom-560m on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.5997
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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 14 | 2.7228 |
| No log | 2.0 | 28 | 1.8992 |
| No log | 3.0 | 42 | 1.3979 |
| No log | 4.0 | 56 | 1.4067 |
| No log | 5.0 | 70 | 1.4500 |
| No log | 6.0 | 84 | 1.5997 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
Model info
Created: 2025-01-27
Updated: 2025-01-27
View on Hugging Face