ROE_Patent_Breeze7B_Type1_V1
This model is a fine-tuned version of MediaTek-Research/Breeze-7B-Instruct-v1_0 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9755
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: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Use paged_adamw_32bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 10.45 | 1.0 | 13 | 1.2662 |
| 9.2302 | 2.0 | 26 | 1.1565 |
| 8.3397 | 3.0 | 39 | 1.0916 |
| 7.9208 | 4.0 | 52 | 1.0503 |
| 7.4182 | 5.0 | 65 | 1.0230 |
| 7.0309 | 6.0 | 78 | 1.0007 |
| 7.1363 | 7.0 | 91 | 0.9841 |
| 6.2854 | 8.0 | 104 | 0.9740 |
| 6.147 | 9.0 | 117 | 0.9698 |
| 6.1537 | 9.2424 | 120 | 0.9755 |
Framework versions
- PEFT 0.14.1.dev0
- Transformers 4.48.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
- Downloads last month
- 2
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for allen0909/ROE_Patent_Breeze7B_Type1_V1
Base model
MediaTek-Research/Breeze-7B-Instruct-v1_0