bart-cnn-samsum-peft
This model is a fine-tuned version of ishjha1/bart-cnn-samsum-finetuned on the samsum dataset. It achieves the following results on the evaluation set:
- Loss: 0.0938
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.0312 | 1.0 | 185 | 0.0925 |
0.0312 | 2.0 | 370 | 0.0928 |
0.0301 | 3.0 | 555 | 0.0932 |
0.0275 | 4.0 | 740 | 0.0936 |
0.0305 | 5.0 | 925 | 0.0938 |
0.0375 | 6.0 | 1110 | 0.0938 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 1
Model tree for ishjha1/bart-cnn-samsum-peft
Base model
facebook/bart-large-cnn
Finetuned
ishjha1/bart-cnn-samsum-finetuned