<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
bart-large-cnn-samsum-ElectrifAi_v12
This model is a fine-tuned version of philschmid/bart-large-cnn-samsum on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.9357
- Rouge1: 52.8096
- Rouge2: 30.6135
- Rougel: 40.9225
- Rougelsum: 48.0235
- Gen Len: 80.6
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
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 11 | 2.1692 | 50.8653 | 25.2603 | 37.6053 | 46.5156 | 86.0 |
| No log | 2.0 | 22 | 1.9852 | 49.1764 | 25.9935 | 38.3519 | 44.5786 | 75.4 |
| No log | 3.0 | 33 | 1.9357 | 52.8096 | 30.6135 | 40.9225 | 48.0235 | 80.6 |
Framework versions
- Transformers 4.25.1
- Pytorch 1.13.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.2
