SummarEaseFocusV2
This model is a fine-tuned version of notBanana/SummarEaseFocus on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8433
- Rouge1: 0.1827
- Rouge2: 0.0704
- Rougel: 0.1516
- Rougelsum: 0.1494
- Gen Len: 20.0
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: 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: linear
- num_epochs: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 1 | 2.0431 | 0.1766 | 0.0679 | 0.1479 | 0.1457 | 20.0 |
| No log | 2.0 | 2 | 1.9573 | 0.1766 | 0.0679 | 0.1479 | 0.1457 | 20.0 |
| No log | 3.0 | 3 | 1.8788 | 0.1766 | 0.0679 | 0.1479 | 0.1457 | 20.0 |
| No log | 4.0 | 4 | 1.8433 | 0.1827 | 0.0704 | 0.1516 | 0.1494 | 20.0 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 108
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.