bart-summarizer-finetuned
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1077
- Rouge1: 0.4257
- Rouge2: 0.2026
- Rougel: 0.2947
- Rougelsum: 0.3949
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: 3e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 0.1
- num_epochs: 4
- mixed_precision_training: Native AMP
- label_smoothing_factor: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum |
|---|---|---|---|---|---|---|---|
| 28.2868 | 1.0 | 375 | 3.1823 | 0.4189 | 0.1985 | 0.2928 | 0.3898 |
| 26.9410 | 2.0 | 750 | 3.1390 | 0.4264 | 0.2029 | 0.2948 | 0.3942 |
| 26.0567 | 3.0 | 1125 | 3.1106 | 0.4254 | 0.2008 | 0.2942 | 0.3948 |
| 25.8507 | 4.0 | 1500 | 3.1077 | 0.4257 | 0.2026 | 0.2947 | 0.3949 |
Framework versions
- Transformers 5.0.0
- Pytorch 2.10.0+cu128
- Datasets 5.0.0
- Tokenizers 0.22.2
- Downloads last month
- 68
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Abhishekpendyala06/bart-summarizer-finetuned
Base model
facebook/bart-base