V1
This model is a fine-tuned version of dmen24/my_fantastic_patent_model on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9191
- Rouge1: 0.2245
- Rouge2: 0.1261
- Rougel: 0.1952
- Rougelsum: 0.1951
- Gen Len: 18.971
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| 2.1187 | 1.0 | 625 | 1.9743 | 0.2248 | 0.1246 | 0.1947 | 0.1947 | 18.9375 |
| 2.0797 | 2.0 | 1250 | 1.9624 | 0.225 | 0.1253 | 0.1953 | 0.1953 | 18.9375 |
| 2.0864 | 3.0 | 1875 | 1.9530 | 0.2254 | 0.1258 | 0.1956 | 0.1956 | 18.9678 |
| 2.0669 | 4.0 | 2500 | 1.9499 | 0.2258 | 0.126 | 0.1959 | 0.1959 | 18.9678 |
Framework versions
- Transformers 4.46.2
- Pytorch 2.5.1+cu121
- Datasets 3.1.0
- Tokenizers 0.20.3
- Downloads last month
- 4
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support